NevaMind-AI/memU

contact_links:   - name: GitHub Discussions     url: https://github.com/NevaMind-AI/memU/discussions

- name: GitHub Discussions     url: https://github.com/NevaMind-AI/memU/discussions     about: For questions and general discussions about memU

url: https://github.com/NevaMind-AI/memU/discussions

about: For questions and general discussions about memU   - name: Documentation     url: https://github.com/NevaMind-AI/memU/blob/main/README.md

- name: Documentation     url: https://github.com/NevaMind-AI/memU/blob/main/README.md     about: Check out the memU documentation

url: https://github.com/NevaMind-AI/memU/blob/main/README.md

#   This is especially recommended for binary packages to ensure reproducibility, and is more #   commonly ignored for libraries. #   https://python-poetry.org/docs/basic-usage/#commit-your-poetrylock-file-to-version-control

#   commonly ignored for libraries. #   https://python-poetry.org/docs/basic-usage/#commit-your-poetrylock-file-to-version-control #poetry.lock

#   https://python-poetry.org/docs/basic-usage/#commit-your-poetrylock-file-to-version-control

#   pdm stores project-wide configurations in .pdm.toml, but it is recommended to not include it #   in version control. #   https://pdm.fming.dev/#use-with-ide

#   in version control. #   https://pdm.fming.dev/#use-with-ide .pdm.toml

#   https://pdm.fming.dev/#use-with-ide

[Credential-related source omitted]

repos:   - repo: https://github.com/pre-commit/pre-commit-hooks

- repo: https://github.com/pre-commit/pre-commit-hooks

- repo: https://github.com/astral-sh/ruff-pre-commit

## [2.0.0-beta.0](https://github.com/NevaMind-AI/memU/compare/v1.5.1...v2.0.0-beta.0) (2026-07-23)

* **blob:** ingest rich documents (PDF/Office/HTML) via MarkItDown ([#447](https://github.com/NevaMind-AI/memU/issues/447)) ([1e16341](https://github.com/NevaMind-AI/memU/commit/1e1634131f84ceb023d03cd87bcf062317abd5ba))

* Codex session-bridging pipeline and scheduled-task skill ([#477](https://github.com/NevaMind-AI/memU/issues/477)) ([1a8edb5](https://github.com/NevaMind-AI/memU/commit/1a8edb57110ebfd208b2fe1f52e3998058fed408))

* **doctor:** diagnose proxy hijacking instead of printing a bare 502 ([7c41eec](https://github.com/NevaMind-AI/memU/commit/7c41eecd53e4c13b1a5c25b01b70f484147295fb))

* **env:** config.env carries NO_PROXY; MEMU_HTTP_PROXY works from the file ([5265945](https://github.com/NevaMind-AI/memU/commit/5265945e3063529819415194e79c46b7614d6081))

* from memory item/category to tracked entry/file for workspace memorization (ADR 0006) ([#456](https://github.com/NevaMind-AI/memU/issues/456)) ([68877da](https://github.com/NevaMind-AI/memU/commit/68877da10a1a18be5c708ec1ab7eb6c45b80ae50)

* **hermes:** install retrieval as a skill ([#536](https://github.com/NevaMind-AI/memU/issues/536)) ([8766d3d](https://github.com/NevaMind-AI/memU/commit/8766d3d3903383a3d4ff38d0f0d620cdf97418ec))

* **hosts:** add Claude Code, Cursor, OpenClaw, and Hermes host adapters ([#494](https://github.com/NevaMind-AI/memU/issues/494)) ([24d1b3b](https://github.com/NevaMind-AI/memU/commit/24d1b3b4f345106f07f1262dc2756b49fb7102cf))

* **hosts:** add memu-agent, a generic adapter for any other agent ([#496](https://github.com/NevaMind-AI/memU/issues/496)) ([e46a1f0](https://github.com/NevaMind-AI/memU/commit/e46a1f04a216a80b3a38064866420c79205fbe22))

* **hosts:** agent-driven uninstall — remove-instruction, docs uninstall, per-host guides ([#509](https://github.com/NevaMind-AI/memU/issues/509)) ([f51673e](https://github.com/NevaMind-AI/memU/commit/f51673e6e80b23c570a7364b415bf6148195697

* **hosts:** install retrieval as a skill on Codex and Claude Code ([#535](https://github.com/NevaMind-AI/memU/issues/535)) ([2ed480e](https://github.com/NevaMind-AI/memU/commit/2ed480ebe462fe4008fdb4315cf5ab9e0316dba4))

* layered, track-aware workspace memorize & retrieve ([#466](https://github.com/NevaMind-AI/memU/issues/466)) ([094e22f](https://github.com/NevaMind-AI/memU/commit/094e22f0e10e7fe71c079608407b6a01b4d67e55))

* **llm,vlm:** multi-provider LLM gateway, modular preprocessing, and VLM package ([#442](https://github.com/NevaMind-AI/memU/issues/442)) ([6f1b0bc](https://github.com/NevaMind-AI/memU/commit/6f1b0bc19d600e77abe7d6ec82d4196d1efe1516))

* **memory_fs:** workspace memorize + markdown memory file system ([#439](https://github.com/NevaMind-AI/memU/issues/439)) ([1b1ad61](https://github.com/NevaMind-AI/memU/commit/1b1ad61bdb96030f00e169b14d7864c1f6adb931))

* memu CLI, npm launcher, and agent skills for the workspace pair ([#467](https://github.com/NevaMind-AI/memU/issues/467)) ([c861974](https://github.com/NevaMind-AI/memU/commit/c8619744b13c67f7efc3322c060e6090255a8522))

* **npm:** point the launcher at the memu-cli PyPI channel ([#483](https://github.com/NevaMind-AI/memU/issues/483)) ([5056389](https://github.com/NevaMind-AI/memU/commit/505638905f279e0b2fac61572ea551f819007aa1))

* **openclaw:** install retrieval as a skill ([#537](https://github.com/NevaMind-AI/memU/issues/537)) ([3cef5ae](https://github.com/NevaMind-AI/memU/commit/3cef5ae2610ce9227de6471a63cc139ff09cf63c))

* **preprocess:** classify audio type and add an overview on ingest ([#448](https://github.com/NevaMind-AI/memU/issues/448)) ([f7601da](https://github.com/NevaMind-AI/memU/commit/f7601daf4ed89815af5c1c1c9011db6af63c1fa5))

* **vlm,preprocess:** native whole-video understanding via OpenRouter ([#450](https://github.com/NevaMind-AI/memU/issues/450)) ([1de5784](https://github.com/NevaMind-AI/memU/commit/1de57847e0ffc430cbf5d6dc17183f33d08be8fe))

* **app:** unpack the (vectors, raw_response) tuple embed() returns ([#504](https://github.com/NevaMind-AI/memU/issues/504)) ([9b2a70c](https://github.com/NevaMind-AI/memU/commit/9b2a70ca214cd3a5b22e902cad0dc19ad07bfeb9))

* **bridging:** advance the cursor and snapshot at commit, not prepare ([#531](https://github.com/NevaMind-AI/memU/issues/531)) ([0ceaa19](https://github.com/NevaMind-AI/memU/commit/0ceaa190d92f8c7c6705db0dcfd6628581d10213))

* **ci:** sort workbuddy cli imports so make check passes ([#522](https://github.com/NevaMind-AI/memU/issues/522)) ([151298c](https://github.com/NevaMind-AI/memU/commit/151298c3c03a6b3cc9ef371d8211b469fffc2469))

* **cli:** force UTF-8 stdio so piped output survives non-UTF-8 Windows code pages ([#513](https://github.com/NevaMind-AI/memU/issues/513)) ([b521453](https://github.com/NevaMind-AI/memU/commit/b5214536c5fce628c174c9c074b9c1d0a53da2ca))

* **codex:** drop harness-injected user records from the conversation seam ([#511](https://github.com/NevaMind-AI/memU/issues/511)) ([c827157](https://github.com/NevaMind-AI/memU/commit/c827157ead066f0a859cb2f1e5deac62ffbe63a5))

* **embedding:** never route loopback embedding calls through a proxy ([#519](https://github.com/NevaMind-AI/memU/issues/519)) ([df6cfba](https://github.com/NevaMind-AI/memU/commit/df6cfba6b9741cc062b7d219af042ddddffcbb5c))

* handle multiple root-level XML elements from non-conformant LLMs ([#409](https://github.com/NevaMind-AI/memU/issues/409)) ([fed42b6](https://github.com/NevaMind-AI/memU/commit/fed42b6142ec1e9f9820e46d8899823d68de8276))

* **hermes:** escape the state.db path when building the SQLite URI ([#503](https://github.com/NevaMind-AI/memU/issues/503)) ([3135132](https://github.com/NevaMind-AI/memU/commit/313513204d87e7156d6a7d459df1bcac64469044))

* **llm/vlm:** correct OpenAI token-limit param and simplify conversation preprocess ([#449](https://github.com/NevaMind-AI/memU/issues/449)) ([ff3c2be](https://github.com/NevaMind-AI/memU/commit/ff3c2bee2ec96ebd303f3e22dae1977ff6388120))

* make lazyllm an optional dependency (fixes [#373](https://github.com/NevaMind-AI/memU/issues/373)) ([#402](https://github.com/NevaMind-AI/memU/issues/402)) ([7652982](https://github.com/NevaMind-AI/memU/commit/7652982a016b2a2426d20bc11c46

* **memory_fs:** restore LLM-free skill bypass and unify synthesis paths ([#444](https://github.com/NevaMind-AI/memU/issues/444)) ([bc13bd4](https://github.com/NevaMind-AI/memU/commit/bc13bd43c6ed3d480b671736bab987434675c717))

* **openclaw:** scan only main session transcripts, not trajectory/checkpoint sidecars ([0245de9](https://github.com/NevaMind-AI/memU/commit/0245de9710f8f73a8b21361442ac3dfd6c7829c7))

* optimize category initialization to avoid unnecessary embedding ([#388](https://github.com/NevaMind-AI/memU/issues/388)) ([a92f266](https://github.com/NevaMind-AI/memU/commit/a92f2666bf94336f8c6bf950088249e611915e7d))

* remove broken memu-server entry point (fixes [#354](https://github.com/NevaMind-AI/memU/issues/354)) ([#398](https://github.com/NevaMind-AI/memU/issues/398)) ([0672b56](https://github.com/NevaMind-AI/memU/commit/0672b56725e12c35bd46061bb2

* remove duplicate document text from preprocess prompt ([#420](https://github.com/NevaMind-AI/memU/issues/420)) ([44aa5ff](https://github.com/NevaMind-AI/memU/commit/44aa5ff0cbceae56ab283848e722a9d4bd8eddd0))

* remove stale memu-server script entry point (fixes [#393](https://github.com/NevaMind-AI/memU/issues/393)) ([#403](https://github.com/NevaMind-AI/memU/issues/403)) ([c5fe493](https://github.com/NevaMind-AI/memU/commit/c5fe493b0596d68479b0

* resolve SQLite embedding TypeError by using sa_column=False ([#401](https://github.com/NevaMind-AI/memU/issues/401)) ([7e198f3](https://github.com/NevaMind-AI/memU/commit/7e198f3718fa6028c809ba7d816a96541fe7e13f))

* return empty list for non-positive top_k in cosine_topk ([#423](https://github.com/NevaMind-AI/memU/issues/423)) ([39023a8](https://github.com/NevaMind-AI/memU/commit/39023a81d758eb4447ed7d88503b8d782aecaf73))

* **tests:** pin UTF-8 on test file I/O so the suite passes on non-UTF-8-locale Windows ([#501](https://github.com/NevaMind-AI/memU/issues/501)) ([dda515a](https://github.com/NevaMind-AI/memU/commit/dda515a4eb3117ff804cd7ce1ae66e03c23028b6)

* add ADR 0008 — trajectory as the source, hooks over API ([#476](https://github.com/NevaMind-AI/memU/issues/476)) ([ff90dac](https://github.com/NevaMind-AI/memU/commit/ff90dac6976bc920667e03d295a75d5da8626f75))

* add INSTALL-LATEST.md and register the WorkBuddy adapter ([#527](https://github.com/NevaMind-AI/memU/issues/527)) ([4871c55](https://github.com/NevaMind-AI/memU/commit/4871c558d5b84c7649d822015dab617a095d678f))

* add SKILL.md, one routing entry point for agent-driven install ([#497](https://github.com/NevaMind-AI/memU/issues/497)) ([bf7aaf3](https://github.com/NevaMind-AI/memU/commit/bf7aaf3bf95cb37f723e7a81b6d5bcdaf35a0f2e))

* add the architecture image the README references ([#492](https://github.com/NevaMind-AI/memU/issues/492)) ([c07b905](https://github.com/NevaMind-AI/memU/commit/c07b9055dc245680c67df02199d4c95cd7a9a62f))

* add under-construction notice, stabilizing ~July 15 ([#472](https://github.com/NevaMind-AI/memU/issues/472)) ([6426ff0](https://github.com/NevaMind-AI/memU/commit/6426ff02aacca12e9d4efbcfc89f53eeed2ae55b))

* ADR 0007 — drop the graph, retrieval is hybrid (embedding + BM25) ([#464](https://github.com/NevaMind-AI/memU/issues/464)) ([3dd7d5c](https://github.com/NevaMind-AI/memU/commit/3dd7d5c055fc6a3244d4c2390f7b8e6bc4321857))

* ADR 0007 — invert L1/L2 (L1 = coarse doc, L2 = item slices) ([#465](https://github.com/NevaMind-AI/memU/issues/465)) ([0afbcc5](https://github.com/NevaMind-AI/memU/commit/0afbcc550ac5b816e5ae9ad309e62adbdf4b80b4))

* ADR 0007 — replace the explicit item graph with entity linking ([#463](https://github.com/NevaMind-AI/memU/issues/463)) ([0bd3c77](https://github.com/NevaMind-AI/memU/commit/0bd3c7765ac791020941de8791ba5b7c50ecc5e0))

* ADR 0007 — three independent memory lines on a layered wiki-graph kernel ([#461](https://github.com/NevaMind-AI/memU/issues/461)) ([a6cf62e](https://github.com/NevaMind-AI/memU/commit/a6cf62e069765b7b234597e537ec170d169d751c))

* align architecture.md and READMEs with ADR 0006 data model ([#460](https://github.com/NevaMind-AI/memU/issues/460)) ([8062b91](https://github.com/NevaMind-AI/memU/commit/8062b91776e69757fd467e79e56cd72eba62c72c))

* consolidate agent skills into one memu SKILL.md, link it atop README ([#469](https://github.com/NevaMind-AI/memU/issues/469)) ([6f0ae82](https://github.com/NevaMind-AI/memU/commit/6f0ae82aaf9d1193841b8e082a2f9fed8753ed70))

* drop the API and CLI reference sections from the README ([#489](https://github.com/NevaMind-AI/memU/issues/489)) ([94a1111](https://github.com/NevaMind-AI/memU/commit/94a11117cf5684888fb7858356c51203c903e9bb))

* expand the README; rename provider var to MEMU_EMBED_PROVIDER ([#486](https://github.com/NevaMind-AI/memU/issues/486)) ([96da89b](https://github.com/NevaMind-AI/memU/commit/96da89bfe048b86516faa4b86f69b508fb4c4c3c))

* focus readme on workspace APIs ([9241f31](https://github.com/NevaMind-AI/memU/commit/9241f3112e912bd47add2fabe6dc2611a4bdac8c))

* **grok:** fix MemoryService initialization example ([#405](https://github.com/NevaMind-AI/memU/issues/405)) ([96e693a](https://github.com/NevaMind-AI/memU/commit/96e693aa09add032f67b342e21b86fa96078611b))

* highlight self-evolving skills in README and description ([#452](https://github.com/NevaMind-AI/memU/issues/452)) ([fb68d22](https://github.com/NevaMind-AI/memU/commit/fb68d22c3caa4a9b6f5cb2a57d185bb9b5e22a5f))

* **hosts:** bind the session cursor's lifecycle to the store's ([75959a6](https://github.com/NevaMind-AI/memU/commit/75959a6e72727c35929f4296c087ed00c97971bf))

* **hosts:** correct the Claude Code multi-block claim and pin it with tests ([#502](https://github.com/NevaMind-AI/memU/issues/502)) ([5995e05](https://github.com/NevaMind-AI/memU/commit/5995e05f27c7d90231468bcb062713af30813b08))

* **hosts:** default bridging schedule to hourly ([#516](https://github.com/NevaMind-AI/memU/issues/516)) ([c1046bb](https://github.com/NevaMind-AI/memU/commit/c1046bb1954c3dd7b16ced769da030d8a02c8d32))

* **hosts:** name the OS system-wide proxy as a 502 source ([#523](https://github.com/NevaMind-AI/memU/issues/523)) ([2b79803](https://github.com/NevaMind-AI/memU/commit/2b79803612872e65201a40dde95ac00541f93fae))

* **hosts:** no-key local fallback hint; default bridging schedule to cron ([#508](https://github.com/NevaMind-AI/memU/issues/508)) ([d155c48](https://github.com/NevaMind-AI/memU/commit/d155c48ac6a35465ad47848927b271f34e2dc4d0))

* **hosts:** scheduled runs drain leftover jobs first; config repairs stay at the connection layer ([9195d14](https://github.com/NevaMind-AI/memU/commit/9195d14cef2d308cff3fcb853a6274e1f0db9d31))

* **hosts:** the scheduler's PATH is not your shell's — fix and honest verify for the bridging guides ([#530](https://github.com/NevaMind-AI/memU/issues/530)) ([19302d2](https://github.com/NevaMind-AI/memU/commit/19302d24260c7b941bdfee66bba

* lead the README with the one-message agent-driven install ([#498](https://github.com/NevaMind-AI/memU/issues/498)) ([aae3d44](https://github.com/NevaMind-AI/memU/commit/aae3d44b0a4332981c4459e7da9258298bcc0fb1))

* make the workspace pair primary, mark memorize/retrieve as legacy ([#470](https://github.com/NevaMind-AI/memU/issues/470)) ([6f3c1be](https://github.com/NevaMind-AI/memU/commit/6f3c1beb36bba21a7d640b0dbdead9361a90a811))

* never fall back to legacy memorize/retrieve ([#471](https://github.com/NevaMind-AI/memU/issues/471)) ([28ee09d](https://github.com/NevaMind-AI/memU/commit/28ee09de54de5bd74f4f6bb1e0185c854ecf1053))

* pitch memU as a 500-line memory system ([#488](https://github.com/NevaMind-AI/memU/issues/488)) ([2a8f8b3](https://github.com/NevaMind-AI/memU/commit/2a8f8b3403548a8d8917a19d5ac0015adf4eab17))

* point the README at the memu-cli package ([#491](https://github.com/NevaMind-AI/memU/issues/491)) ([9ceea5b](https://github.com/NevaMind-AI/memU/commit/9ceea5b32a2694cf4ab5e5f0069b029ac13800b3))

* **readme:** readme accuracy updates ([#430](https://github.com/NevaMind-AI/memU/issues/430)) ([5f17725](https://github.com/NevaMind-AI/memU/commit/5f1772579c8d0881ec1c9ab071404aea6b3bfadc))

* **readme:** reframe intro around MEMORY.md, SKILL.md, and INDEX.md ([#434](https://github.com/NevaMind-AI/memU/issues/434)) ([ca0c755](https://github.com/NevaMind-AI/memU/commit/ca0c755dcc06874c227df811d6b7a3ca972f6be2))

* **readme:** reframe README around file-system-as-memory narrative ([#432](https://github.com/NevaMind-AI/memU/issues/432)) ([cd8150a](https://github.com/NevaMind-AI/memU/commit/cd8150ac7d68f4972d9a9e8268e3169da9b4cfc3))

* **readme:** reframe README around workspace-runtime narrative ([#438](https://github.com/NevaMind-AI/memU/issues/438)) ([7c104b1](https://github.com/NevaMind-AI/memU/commit/7c104b1eb0883437d49bea0edae3a24eea12f275))

* **readme:** sync translated READMEs to file-system-as-memory narrative ([#433](https://github.com/NevaMind-AI/memU/issues/433)) ([f4e82ce](https://github.com/NevaMind-AI/memU/commit/f4e82cec1898e34f82612ec3628f8de1faedf701))

* refine ADR 0007 with the L0/L1/L2 layer model ([#462](https://github.com/NevaMind-AI/memU/issues/462)) ([6456c35](https://github.com/NevaMind-AI/memU/commit/6456c357b22039a3b12ba2f2bc0294a8693bceb5))

* Refine OpenClaw reference and feature descriptions ([#410](https://github.com/NevaMind-AI/memU/issues/410)) ([707b80e](https://github.com/NevaMind-AI/memU/commit/707b80e5f4394b8e4aafff1ef23fd331a8b557f8))

* refine README memory filesystem positioning ([#429](https://github.com/NevaMind-AI/memU/issues/429)) ([dda0374](https://github.com/NevaMind-AI/memU/commit/dda03743b007c0863c7fe7237592f7e4a0de32b6))

* refine README positioning around personal memory as files ([#455](https://github.com/NevaMind-AI/memU/issues/455)) ([88982d3](https://github.com/NevaMind-AI/memU/commit/88982d3d22640501be09ced1876520e95d956312))

* reframe README and description around personal-information memory ([#451](https://github.com/NevaMind-AI/memU/issues/451)) ([6b5b11c](https://github.com/NevaMind-AI/memU/commit/6b5b11c0787704c119b8d2e2d3c779bd56ee66fa))

* refresh memory diagrams ([#473](https://github.com/NevaMind-AI/memU/issues/473)) ([0d8770f](https://github.com/NevaMind-AI/memU/commit/0d8770f0c9d49f3a09e6ac33ca72b34c8128a855))

* retitle around file-based memory and trim README ([#453](https://github.com/NevaMind-AI/memU/issues/453)) ([2c1cc86](https://github.com/NevaMind-AI/memU/commit/2c1cc86ba66f31ffb7c6afcd0717f7e1880c0fd0))

* rewrite README — raw data → memory → agent ([#426](https://github.com/NevaMind-AI/memU/issues/426)) ([c2a2aac](https://github.com/NevaMind-AI/memU/commit/c2a2aac52b4424583955f85f5a35776e76beb68a))

* swap the tagline to lead with Across Agents ([#490](https://github.com/NevaMind-AI/memU/issues/490)) ([6e0fc06](https://github.com/NevaMind-AI/memU/commit/6e0fc068a1e3a2212dfea52f52438b438dae88f3))

* tagline across sessions/agents/devices, lowercase memU in banner alt ([#515](https://github.com/NevaMind-AI/memU/issues/515)) ([1f4f831](https://github.com/NevaMind-AI/memU/commit/1f4f8315bc0a68a6d2c2fa8018d64e7f22e5b164))

* tighten the README intro to two sentences ([#487](https://github.com/NevaMind-AI/memU/issues/487)) ([da160f2](https://github.com/NevaMind-AI/memU/commit/da160f2155439923bfe744ac770733c1c9824cd9))

* release 2.0.0-beta.0 ([#541](https://github.com/NevaMind-AI/memU/issues/541)) ([3dc60ce](https://github.com/NevaMind-AI/memU/commit/3dc60cea094e29f86ead2fad148ea0fbeab198c3))

## [1.5.1](https://github.com/NevaMind-AI/memU/compare/v1.5.0...v1.5.1) (2026-03-23)

* use correct interpolation in alembic url ([#390](https://github.com/NevaMind-AI/memU/issues/390)) ([fd87ceb](https://github.com/NevaMind-AI/memU/commit/fd87ceb558eaa800aeb694b045847971958f23a3))

## [1.5.0](https://github.com/NevaMind-AI/memU/compare/v1.4.0...v1.5.0) (2026-03-17)

* add non-propagate option for memory patch ([#386](https://github.com/NevaMind-AI/memU/issues/386)) ([3b67458](https://github.com/NevaMind-AI/memU/commit/3b67458c6325b4fcdaccbc34f6e0fea491b7ba96))

* **http:** add HTTP proxy support for LLM & embedding clients ([#310](https://github.com/NevaMind-AI/memU/issues/310)) ([a3d45e2](https://github.com/NevaMind-AI/memU/commit/a3d45e2f4174702fd8fd83cd13862285cd47cad9))

* httpx base_url path discarded when endpoint starts with / ([#328](https://github.com/NevaMind-AI/memU/issues/328), [#336](https://github.com/NevaMind-AI/memU/issues/336), [#341](https://github.com/NevaMind-AI/memU/issues/341), [#329](http

* add architecture explanation and adrs ([#353](https://github.com/NevaMind-AI/memU/issues/353)) ([8676a27](https://github.com/NevaMind-AI/memU/commit/8676a2721917f4e0baee6d01a9d6b95bd642be97))

* add pull request template to improve contribution quality ([#261](https://github.com/NevaMind-AI/memU/issues/261)) ([2256119](https://github.com/NevaMind-AI/memU/commit/2256119fb2d177890c7f738c926f437a355e7359))

* Update Discord link in README.md ([#377](https://github.com/NevaMind-AI/memU/issues/377)) ([163d050](https://github.com/NevaMind-AI/memU/commit/163d050299b77143226e9727f67d4826c9a69f92))

* update memU Bot section with GitHub reference and "Now open source" ([#366](https://github.com/NevaMind-AI/memU/issues/366)) ([dc6880a](https://github.com/NevaMind-AI/memU/commit/dc6880a793d40b04cd599298a110af5f0f0b9cb5))

## [1.4.0](https://github.com/NevaMind-AI/memU/compare/v1.3.0...v1.4.0) (2026-02-06)

* Add inline memory item references in category summaries ([#202](https://github.com/NevaMind-AI/memU/issues/202)) ([#205](https://github.com/NevaMind-AI/memU/issues/205)) ([5213571](https://github.com/NevaMind-AI/memU/commit/5213571b218d85

* Add salience-aware memory with reinforcement tracking ([#186](https://github.com/NevaMind-AI/memU/issues/186)) ([#206](https://github.com/NevaMind-AI/memU/issues/206)) ([2bdbcce](https://github.com/NevaMind-AI/memU/commit/2bdbcce1a87ae101

* Add Tool Memory type with specialized metadata and statistics ([#247](https://github.com/NevaMind-AI/memU/issues/247)) ([4e8a035](https://github.com/NevaMind-AI/memU/commit/4e8a03578641afd0e07f9700629dff8d91d2b3fb))

* add chat() API and stop misusing summarize() ([#208](https://github.com/NevaMind-AI/memU/issues/208)) ([be0a5c7](https://github.com/NevaMind-AI/memU/commit/be0a5c73250f0a21ad5e0d39b0e66e3018809e0f))

* remove unused type: ignore comment and add lazyllm mypy override ([#275](https://github.com/NevaMind-AI/memU/issues/275)) ([0e490f7](https://github.com/NevaMind-AI/memU/commit/0e490f7333feecffaef0901cccb1c9a5dbb7bafb))

* **video:** cleanup temp files on extraction failure ([#295](https://github.com/NevaMind-AI/memU/issues/295)) ([16b65e5](https://github.com/NevaMind-AI/memU/commit/16b65e54aef69dfe617835ca534c12752e06eda8))

* file system in readme ([#301](https://github.com/NevaMind-AI/memU/issues/301)) ([ee27d8a](https://github.com/NevaMind-AI/memU/commit/ee27d8aa5e42d249963b08d5775338080b0255f8))

* fix name ([#291](https://github.com/NevaMind-AI/memU/issues/291)) ([fd0d179](https://github.com/NevaMind-AI/memU/commit/fd0d17998f6c0c9ba5c7e91964c39ee909f2b366))

* fix readme lint ([#290](https://github.com/NevaMind-AI/memU/issues/290)) ([a7a5516](https://github.com/NevaMind-AI/memU/commit/a7a55169ecbc1579ae87dc68c5e09b1d62f07b56))

* lint error ([#287](https://github.com/NevaMind-AI/memU/issues/287)) ([7f61dc7](https://github.com/NevaMind-AI/memU/commit/7f61dc72ffbadf849f227cf314bba7ce7964761b))

* readme memubot ([#289](https://github.com/NevaMind-AI/memU/issues/289)) ([2f30798](https://github.com/NevaMind-AI/memU/commit/2f30798367e3591107e1e66a184d0dd4ad6c2f93))

* Update README.md ([#300](https://github.com/NevaMind-AI/memU/issues/300)) ([1075d7c](https://github.com/NevaMind-AI/memU/commit/1075d7c9ec3a272846c9fdb8c22ec58ff73cf6e7))

## [1.3.0](https://github.com/NevaMind-AI/memU/compare/v1.2.0...v1.3.0) (2026-01-29)

* add happened at and extra fields to memory item ([#262](https://github.com/NevaMind-AI/memU/issues/262)) ([77938e9](https://github.com/NevaMind-AI/memU/commit/77938e9c282e1c0eda11088675c35975d85c4ff0))

* add proactive example ([#268](https://github.com/NevaMind-AI/memU/issues/268)) ([d3d1de1](https://github.com/NevaMind-AI/memU/commit/d3d1de1d9b0f45d9b14479cbaa4462458b172005))

* add Sealos support agent use case (Track G) ([#255](https://github.com/NevaMind-AI/memU/issues/255)) ([8fbdf3c](https://github.com/NevaMind-AI/memU/commit/8fbdf3c301f74f2aa85604837e00bb305b8801ec))

* integrate LazyLLM to provide more llm services ([#265](https://github.com/NevaMind-AI/memU/issues/265)) ([c03f639](https://github.com/NevaMind-AI/memU/commit/c03f639677d6c897b75dfe28d0cd92d5b5270957))

* **integrations:** Add LangGraph Adapter for MemU (Track A) ([#258](https://github.com/NevaMind-AI/memU/issues/258)) ([50b5502](https://github.com/NevaMind-AI/memU/commit/50b5502ebcacd86401f98b1bb7e5a6577fab7126))

* **llm:** add Grok (xAI) integration ([#179](https://github.com/NevaMind-AI/memU/issues/179)) ([#236](https://github.com/NevaMind-AI/memU/issues/236)) ([1e16309](https://github.com/NevaMind-AI/memU/commit/1e1630948af535f8ed9d608e6c4f9d2748

* Openrouter integration as backend provider ([#182](https://github.com/NevaMind-AI/memU/issues/182)) ([cba667a](https://github.com/NevaMind-AI/memU/commit/cba667a56daca5093c9b79a598c7d2ffda813756))

* memory type & proactive example ([#272](https://github.com/NevaMind-AI/memU/issues/272)) ([710f14d](https://github.com/NevaMind-AI/memU/commit/710f14d4b171c5cde609a9dc2caf454681ab94b3))

* proactive examples ([#273](https://github.com/NevaMind-AI/memU/issues/273)) ([603ae12](https://github.com/NevaMind-AI/memU/commit/603ae122b94741bb350656086960c4e2bb868c2a))

* Add link to memU bot ([#276](https://github.com/NevaMind-AI/memU/issues/276)) ([2f84231](https://github.com/NevaMind-AI/memU/commit/2f842311ed592c1a45cdb9e24f7a128da97a0a39))

* multilingual readme ([#271](https://github.com/NevaMind-AI/memU/issues/271)) ([200f47a](https://github.com/NevaMind-AI/memU/commit/200f47a15ff7d05fc435abe1d2cefbb3774548fe))

* Update memU bot link to include full URL ([#277](https://github.com/NevaMind-AI/memU/issues/277)) ([6874eaf](https://github.com/NevaMind-AI/memU/commit/6874eaf278e910d07a4427dd4c06f9c4c21283ce))

* update readme ([#266](https://github.com/NevaMind-AI/memU/issues/266)) ([16ae534](https://github.com/NevaMind-AI/memU/commit/16ae534675a5e0711256a5e2147b9190fd8b2524))

* update README ([#270](https://github.com/NevaMind-AI/memU/issues/270)) ([b531d39](https://github.com/NevaMind-AI/memU/commit/b531d39e5538449b31cb212aea1deea24e12180f))

## [1.2.0](https://github.com/NevaMind-AI/memU/compare/v1.1.2...v1.2.0) (2026-01-14)

* clear memory ([#239](https://github.com/NevaMind-AI/memU/issues/239)) ([7da36da](https://github.com/NevaMind-AI/memU/commit/7da36da57d7013df213e537b1f238f5a526e69d9))

* **database:** add SQLite storage backend ([#201](https://github.com/NevaMind-AI/memU/issues/201)) ([4b899d7](https://github.com/NevaMind-AI/memU/commit/4b899d7b768fcd48b6456234800033e3b2e3173c))

* improve issue template ([#199](https://github.com/NevaMind-AI/memU/issues/199)) ([abe0f1b](https://github.com/NevaMind-AI/memU/commit/abe0f1b77d5f8294ff45c9f57f5aeb6de33977d6))

* optimize topk pick function ([#196](https://github.com/NevaMind-AI/memU/issues/196)) ([b474c54](https://github.com/NevaMind-AI/memU/commit/b474c54a7eea06ba56844d6482d5e78b3cb3f020))

* workflow step interceptor ([#240](https://github.com/NevaMind-AI/memU/issues/240)) ([bf2ac96](https://github.com/NevaMind-AI/memU/commit/bf2ac96f1cb26b196f27b543d4c3e157f408f343))

* allow nullable resource_id in Postgres items ([#232](https://github.com/NevaMind-AI/memU/issues/232)) ([ae2ffbb](https://github.com/NevaMind-AI/memU/commit/ae2ffbb0bcd69170875a47cebf322b71a15f4bd3))

* correct coverage source to track memu package instead of tests ([#220](https://github.com/NevaMind-AI/memU/issues/220)) ([2460bbd](https://github.com/NevaMind-AI/memU/commit/2460bbd2a2c4df5b3664db81d89886b926b51031))

* correct typo in PromptBlock class label attribute ([#231](https://github.com/NevaMind-AI/memU/issues/231)) ([d69053c](https://github.com/NevaMind-AI/memU/commit/d69053cece3467dd7c8cbf0634e72447649095f7))

* default embed size ([#192](https://github.com/NevaMind-AI/memU/issues/192)) ([144fd32](https://github.com/NevaMind-AI/memU/commit/144fd32cfd6917b08f29cf56f251f239c360d2ae))

* readme partners link & github issue link ([#198](https://github.com/NevaMind-AI/memU/issues/198)) ([849f881](https://github.com/NevaMind-AI/memU/commit/849f881f004b0772f372069e40f937731c114c89))

* add Chinese translation of README ([#212](https://github.com/NevaMind-AI/memU/issues/212)) ([d15ecf9](https://github.com/NevaMind-AI/memU/commit/d15ecf97647d8fd9f1d2ae95008a08bbba93a44a))

* add How to Contribute section to README ([#215](https://github.com/NevaMind-AI/memU/issues/215)) ([bf44de7](https://github.com/NevaMind-AI/memU/commit/bf44de722965fd611c0dc585712eac587caa9e6c))

* **readme:** update Chinese README with fixes and improvements ([#221](https://github.com/NevaMind-AI/memU/issues/221)) ([75a8f65](https://github.com/NevaMind-AI/memU/commit/75a8f651bb4b491ab5b0363de789c0dcd0291287))

## [1.1.2](https://github.com/NevaMind-AI/memU/compare/v1.1.1...v1.1.2) (2026-01-08)

* custom memory type default prompt ([#169](https://github.com/NevaMind-AI/memU/issues/169)) ([5a0032f](https://github.com/NevaMind-AI/memU/commit/5a0032fc0f29229524d0356d454a3f5991e04f7b))

* prompt & item fallback ([#183](https://github.com/NevaMind-AI/memU/issues/183)) ([bc95ade](https://github.com/NevaMind-AI/memU/commit/bc95adeb26789104c0bbe199e126cf05def27941))

* add docs folder ([#181](https://github.com/NevaMind-AI/memU/issues/181)) ([919d2ca](https://github.com/NevaMind-AI/memU/commit/919d2caef23107d539c36f30c44d4fb5aa38b324))

* fix issue template dropdown ([#167](https://github.com/NevaMind-AI/memU/issues/167)) ([14d0333](https://github.com/NevaMind-AI/memU/commit/14d03331ed14f1e593fdebbf561189a3775651be))

* issue template fix ([#165](https://github.com/NevaMind-AI/memU/issues/165)) ([5d91237](https://github.com/NevaMind-AI/memU/commit/5d912372e1bf70d7ff573cd5b92e917118048e25))

## [1.1.1](https://github.com/NevaMind-AI/memU/compare/v1.1.0...v1.1.1) (2026-01-07)

* ensure both Linux x86_64 and ARM64 wheels are built ([#162](https://github.com/NevaMind-AI/memU/issues/162)) ([51c9ea4](https://github.com/NevaMind-AI/memU/commit/51c9ea4335a1e9eac227c79783d7aa8cca2b883b))

* add custom LLM and embedding configuration guide ([#160](https://github.com/NevaMind-AI/memU/issues/160)) ([29c414a](https://github.com/NevaMind-AI/memU/commit/29c414a84d1c9c2f989e2165d0b6508c3fe62862))

* add template ([#158](https://github.com/NevaMind-AI/memU/issues/158)) ([b79a78d](https://github.com/NevaMind-AI/memU/commit/b79a78d25b96e670888c18b8f09277db33803865))

## [1.1.0](https://github.com/NevaMind-AI/memU/compare/v1.0.1...v1.1.0) (2026-01-07)

* add Linux ARM64 (aarch64) build target ([#156](https://github.com/NevaMind-AI/memU/issues/156)) ([0c90fcf](https://github.com/NevaMind-AI/memU/commit/0c90fcfb19fc3e91b951f4ba7454798e4b83e42c))

* llm client profile & wrapper ([#157](https://github.com/NevaMind-AI/memU/issues/157)) ([e55c668](https://github.com/NevaMind-AI/memU/commit/e55c66847eac3ceaf276587d58b76d953d7be9f8))

* remove legacy docs ([#154](https://github.com/NevaMind-AI/memU/issues/154)) ([11fda41](https://github.com/NevaMind-AI/memU/commit/11fda41dda8a5c38b790d3c2fb7053b57b16606e))

## [1.0.1](https://github.com/NevaMind-AI/memU/compare/v1.0.0...v1.0.1) (2026-01-06)

* get embedding client ([#152](https://github.com/NevaMind-AI/memU/issues/152)) ([76716a4](https://github.com/NevaMind-AI/memU/commit/76716a4f00127a3cc21444996f32a9cf810c9282))

* Readme incomplete ([#148](https://github.com/NevaMind-AI/memU/issues/148)) ([f8bc748](https://github.com/NevaMind-AI/memU/commit/f8bc748b9ebfb652ca8a5e06edbbe7eb648ed4f6))

## [1.0.0](https://github.com/NevaMind-AI/memU/compare/v0.9.0...v1.0.0) (2026-01-05)

* v1.0.0 ([#147](https://github.com/NevaMind-AI/memU/issues/147))

* v1.0.0 ([#147](https://github.com/NevaMind-AI/memU/issues/147)) ([23f37ee](https://github.com/NevaMind-AI/memU/commit/23f37ee403ecaf88b48af0144e3d701c22ccfddd))

* add readme cloud api ([#144](https://github.com/NevaMind-AI/memU/issues/144)) ([42fd5ba](https://github.com/NevaMind-AI/memU/commit/42fd5babe6748ef54254cf114a54bdefea304f07))

* fix api doc link ([#146](https://github.com/NevaMind-AI/memU/issues/146)) ([23ce7d1](https://github.com/NevaMind-AI/memU/commit/23ce7d19b1d68f4fd0a5a5ac6b756f69fede8d09))

## [0.9.0](https://github.com/NevaMind-AI/memU/compare/v0.8.0...v0.9.0) (2026-01-04)

* add GitHub issue templates (bug report, designer feedback, feat… ([#132](https://github.com/NevaMind-AI/memU/issues/132)) ([aee22ee](https://github.com/NevaMind-AI/memU/commit/aee22ee94f275749f69367b83a02a2e819cfd001))

* add LLM wrapper and interceptors for LLM calls ([#131](https://github.com/NevaMind-AI/memU/issues/131)) ([416e102](https://github.com/NevaMind-AI/memU/commit/416e1029e7752f173c133ebc83bc42801a313059))

* patch & crud workflows ([#127](https://github.com/NevaMind-AI/memU/issues/127)) ([3cd3dc6](https://github.com/NevaMind-AI/memU/commit/3cd3dc65ae9488207ff8fb0c81e4adb0d22c0f91))

* category summary & category user scopes ([#125](https://github.com/NevaMind-AI/memU/issues/125)) ([a24efd5](https://github.com/NevaMind-AI/memU/commit/a24efd57df2e305fa3eae8622ea889318979c2f7))

* config & resource caption ([#142](https://github.com/NevaMind-AI/memU/issues/142)) ([ea4be13](https://github.com/NevaMind-AI/memU/commit/ea4be1396c0f55b02d706819f6c2b4d5c6e68be8))

* remove duplicate and unnecessary issue templates ([#133](https://github.com/NevaMind-AI/memU/issues/133)) ([559ec14](https://github.com/NevaMind-AI/memU/commit/559ec14d2561ac09162bbb93f178e0f74cc58b23))

* fix README and CONTRIBUTING to match actual codebase ([#130](https://github.com/NevaMind-AI/memU/issues/130)) ([65d7ef4](https://github.com/NevaMind-AI/memU/commit/65d7ef414563395c6cfa0a75343864671c11b62d))

* modify readme.md 0102 ([#136](https://github.com/NevaMind-AI/memU/issues/136)) ([f114ee4](https://github.com/NevaMind-AI/memU/commit/f114ee46c8639b256472a8e989695b2f2215f4d4))

## [0.8.0](https://github.com/NevaMind-AI/memU/compare/v0.7.0...v0.8.0) (2025-12-24)

* add configurable batch_size for embedding API calls ([#114](https://github.com/NevaMind-AI/memU/issues/114)) ([060067a](https://github.com/NevaMind-AI/memU/commit/060067a5ebe8ad36c4ca4ad2cc6033303c3f1a36))

* add conversation created at ([#120](https://github.com/NevaMind-AI/memU/issues/120)) ([825df56](https://github.com/NevaMind-AI/memU/commit/825df5640037fa2345c3153c3df89174059551b3))

* add workflow implementation and postgres store ([#122](https://github.com/NevaMind-AI/memU/issues/122)) ([a175811](https://github.com/NevaMind-AI/memU/commit/a1758110f859f3725960d308fa0344a1056be52c))

* example 3 output ([#117](https://github.com/NevaMind-AI/memU/issues/117)) ([65ef7c6](https://github.com/NevaMind-AI/memU/commit/65ef7c6a497047f0f86938cf77ee4602a630216b))

* postgres model definitions & database initialization ([#124](https://github.com/NevaMind-AI/memU/issues/124)) ([7d5e0cb](https://github.com/NevaMind-AI/memU/commit/7d5e0cb02837a6e2071d3c3344ef6dad613f9a43))

* Add memU-experiment link to README ([#119](https://github.com/NevaMind-AI/memU/issues/119)) ([2d908e1](https://github.com/NevaMind-AI/memU/commit/2d908e17ee2e15b95d4eb2f35dd09f924d57f8cf))

* clearer introduction and new agent examples ([#115](https://github.com/NevaMind-AI/memU/issues/115)) ([da27875](https://github.com/NevaMind-AI/memU/commit/da2787536d91490f7a96a0c7379abd1ad1c6d9ac))

## [0.7.0](https://github.com/NevaMind-AI/memU/compare/v0.6.0...v0.7.0) (2025-12-05)

* add user model and user context store ([#113](https://github.com/NevaMind-AI/memU/issues/113)) ([7c37fb1](https://github.com/NevaMind-AI/memU/commit/7c37fb166b0a85bf7c89d0b109cbaa882fa80064))

* add valcano model support ([#110](https://github.com/NevaMind-AI/memU/issues/110)) ([704c302](https://github.com/NevaMind-AI/memU/commit/704c3024946e8d4a1d1b13ffef33126bb68bd9c4))

* resource caption miss problem ([#111](https://github.com/NevaMind-AI/memU/issues/111)) ([85586f5](https://github.com/NevaMind-AI/memU/commit/85586f52d6bd6355ae440ad06d8cc6779c689ce8))

* fix example file path ([#105](https://github.com/NevaMind-AI/memU/issues/105)) ([21aad6a](https://github.com/NevaMind-AI/memU/commit/21aad6a7f070e7666ac6a41c91980a4fa9696918))

* fix readme test case ([#107](https://github.com/NevaMind-AI/memU/issues/107)) ([228306c](https://github.com/NevaMind-AI/memU/commit/228306c897402c633f57c7aa31e8c6cd4e995d5d))

* highlight OpenAI key ([#106](https://github.com/NevaMind-AI/memU/issues/106)) ([5b6ce54](https://github.com/NevaMind-AI/memU/commit/5b6ce54def5aa7743a85bec629da65bfa9d8333b))

* highlight readme openai key ([#103](https://github.com/NevaMind-AI/memU/issues/103)) ([fc4154a](https://github.com/NevaMind-AI/memU/commit/fc4154a707220ced4359e7296218451c43cf0681))

## [0.6.0](https://github.com/NevaMind-AI/memU/compare/v0.5.0...v0.6.0) (2025-11-20)

* retrieve args change conversation_history to queries ([#98](https://github.com/NevaMind-AI/memU/issues/98)) ([6370c6e](https://github.com/NevaMind-AI/memU/commit/6370c6e968c9d0922120bf2a41e8b4206bab87cb))

## [0.5.0](https://github.com/NevaMind-AI/memU/compare/v0.4.0...v0.5.0) (2025-11-18)

* add usecase examples ([#94](https://github.com/NevaMind-AI/memU/issues/94)) ([47b5b39](https://github.com/NevaMind-AI/memU/commit/47b5b390e065ccac1cd2173fa2d6c41549e01063))

## [0.4.0](https://github.com/NevaMind-AI/memU/compare/v0.3.0...v0.4.0) (2025-11-18)

* add non-RAG retrieve solution ([#84](https://github.com/NevaMind-AI/memU/issues/84)) ([fb96e54](https://github.com/NevaMind-AI/memU/commit/fb96e5405f1c0e3477929b7d9874e624dd0453cb))

* correct binary name after making a release ([#91](https://github.com/NevaMind-AI/memU/issues/91)) ([0fa721a](https://github.com/NevaMind-AI/memU/commit/0fa721aaae294c6f230221af11084a0a6c1f478d))

* fix several words in README ([#89](https://github.com/NevaMind-AI/memU/issues/89)) ([1e3baf9](https://github.com/NevaMind-AI/memU/commit/1e3baf92d5a08ec51a7eda3249bbd4b40530f56c))

* revise README for clarity and roadmap inclusion ([#86](https://github.com/NevaMind-AI/memU/issues/86)) ([2235b09](https://github.com/NevaMind-AI/memU/commit/2235b099acc7e92ac52b2613fa731f85259d58fd))

* update images and refine punctuation in README ([#88](https://github.com/NevaMind-AI/memU/issues/88)) ([cc375e8](https://github.com/NevaMind-AI/memU/commit/cc375e89a9b49bda0b7057eee696d74c4c1d9cee))

## [0.3.0](https://github.com/NevaMind-AI/memU/compare/v0.2.2...v0.3.0) (2025-11-17)

* initialize the memorize and retrieve workflows with the new 3-layer architecture ([#81](https://github.com/NevaMind-AI/memU/issues/81)) ([4a2e86c](https://github.com/NevaMind-AI/memU/commit/4a2e86c0e8bc3e50c82c4fde33d07ad741c8a65e))

* add German translation for README ([f6d6ab1](https://github.com/NevaMind-AI/memU/commit/f6d6ab1a51b76bd4312542422aebac89410b8da9))

* add German translation for README ([76c3fc4](https://github.com/NevaMind-AI/memU/commit/76c3fc4227a8e349fbcf1e5bfec29d68e984ff7a))

- Python 3.11+ - Git - [uv](https://github.com/astral-sh/uv) (Python package manager)

- Git - [uv](https://github.com/astral-sh/uv) (Python package manager) - A code editor (VS Code recommended)

- [uv](https://github.com/astral-sh/uv) (Python package manager)

# 1. Fork the repository on GitHub # 2. Clone your fork locally git clone https://github.com/YOUR_USERNAME/MemU.git

# 2. Clone your fork locally git clone https://github.com/YOUR_USERNAME/MemU.git cd MemU

git clone https://github.com/YOUR_USERNAME/MemU.git

# 3. Install uv if you haven't already curl -LsSf https://astral.sh/uv/install.sh | sh

curl -LsSf https://astral.sh/uv/install.sh | sh

curl -LsSf https://astral.sh/uv/install.sh | sh

| Channel | Best For | |---------|----------| | 💬 [Discord](https://discord.gg/memu) | Real-time chat, quick questions |

|---------|----------| | 💬 [Discord](https://discord.gg/memu) | Real-time chat, quick questions | | 🗣<U+FE0F> [GitHub Discussions](https://github.com/NevaMind-AI/MemU/discussions) | Feature discussions, Q&A |

| 💬 [Discord](https://discord.gg/memu) | Real-time chat, quick questions | | 🗣<U+FE0F> [GitHub Discussions](https://github.com/NevaMind-AI/MemU/discussions) | Feature discussions, Q&A | | 🐛 [GitHub Issues](https://github.com/NevaMind-AI/MemU/issue

| 🗣<U+FE0F> [GitHub Discussions](https://github.com/NevaMind-AI/MemU/discussions) | Feature discussions, Q&A | | 🐛 [GitHub Issues](https://github.com/NevaMind-AI/MemU/issues) | Bug reports, feature requests | | 📧 [Email](mailto:contact@nevamind.ai

| 🐛 [GitHub Issues](https://github.com/NevaMind-AI/MemU/issues) | Bug reports, feature requests |

- README.md contributors section - Release notes for significant contributions - Our [Contributors](https://github.com/NevaMind-AI/MemU/graphs/contributors) page

- Our [Contributors](https://github.com/NevaMind-AI/MemU/graphs/contributors) page

uv tool install "git+https://github.com/NevaMind-AI/memU"

curl -LsSf https://astral.sh/uv/install.sh | sh                 # macOS / Linux

curl -LsSf https://astral.sh/uv/install.sh | sh                 # macOS / Linux

powershell -c "irm https://astral.sh/uv/install.ps1 | iex"      # Windows

pip install "git+https://github.com/NevaMind-AI/memU"

- the SHA (from Step 2), - its **subject line and date**, and - the link to inspect it: `https://github.com/NevaMind-AI/memU/commit/<sha>`.

- the link to inspect it: `https://github.com/NevaMind-AI/memU/commit/<sha>`.

curl -s https://api.github.com/repos/NevaMind-AI/memU/commits/<sha>

Apache License                            Version 2.0, January 2004                         http://www.apache.org/licenses/

http://www.apache.org/licenses/

http://www.apache.org/licenses/LICENSE-2.0

[Credential-related source omitted]

Executable file

[![PyPI version](https://badge.fury.io/py/memu-cli.svg)](https://badge.fury.io/py/memu-cli)

[![License: Apache 2.0](https://img.shields.io/badge/License-Apache%202.0-blue.svg)](https://opensource.org/licenses/Apache-2.0)

[![Python 3.11+](https://img.shields.io/badge/python-3.11+-blue.svg)](https://www.python.org/downloads/)

[![Discord](https://img.shields.io/badge/Discord-Join%20Chat-5865F2?logo=discord&logoColor=white)](https://discord.com/invite/hQZntfGsbJ)

[![Twitter](https://img.shields.io/badge/Twitter-Follow-1DA1F2?logo=x&logoColor=white)](https://x.com/memU_ai)

<a href="https://trendshift.io/repositories/17374" target="_blank"><img src="https://trendshift.io/api/badge/repositories/17374" alt="NevaMind-AI%2FmemU | Trendshift" style="width: 250px; height: 55px;" width="250" height="55"/></a>

**Cross-device · Free · Unlimited · [View online](https://memu.so)**

Get your API key from [memu.so](https://memu.so), then send this message to your agent:

> Read [https://memu.pro/SKILL.md](https://memu.pro/SKILL.md), follow its instructions to install and configure memU, API Key is memu_•••••••••(get Api Key from memu.so).

> Read [https://raw.githubusercontent.com/NevaMind-AI/MemU/main/SKILL.md](https://raw.githubusercontent.com/NevaMind-AI/MemU/main/SKILL.md) and follow it to install memU.

> Read [https://memu.pro/SKILL.md](https://memu.pro/SKILL.md) and follow its instructions to uninstall memU.

With memU Cloud, sign in at [memu.so](https://memu.so) to view your memory files. With a local installation, memory lives in the shared store configured by `MEMU_DB` in `~/.memu/config.env` — typically `~/.memu/memu.sqlite3` for local SQLit

[Credential-related source omitted]

<sub>Partnership Community: <a href="https://linux.do">LINUX DO</a></sub>

[Credential-related source omitted]

[Credential-related source omitted]

[Credential-related source omitted]

[Credential-related source omitted]

MEMU_CLOUD_BASE_URL=https://api.memu.so/api/v4/memory/

The base URL has the production value above as its default and remains overridable for compatible deployments. Users obtain a memU API key by registering at [memu.so](https://memu.so). `MEMU_BASE_URL` and `MEMU_API_KEY`

overridable for compatible deployments. Users obtain a memU API key by registering at [memu.so](https://memu.so). `MEMU_BASE_URL` and `MEMU_API_KEY` keep their existing local-embedding meaning.

[Credential-related source omitted]

[Credential-related source omitted]

[Credential-related source omitted]

A single module fetches `https://memu.pro/sdk/instructions/<name>.txt` for the

The base URL defaults to `https://memu.pro/sdk/instructions` and is overridable

- **`fetch(name)` — server only, no cache.** Used for the retrieval skill

(`retrieval-skill`), served as a full `SKILL.md` document. Its durable copy is   not a cache but the file already installed on disk, so there is nothing extra to   cache. `install-instruction` uses `fetch(...) or embedded` (an explicit, one

not a cache but the file already installed on disk, so there is nothing extra to   cache. `install-instruction` uses `fetch(...) or embedded` (an explicit, one-off   command; the embedded floor is correct when the server is down mid-install

cache. `install-instruction` uses `fetch(...) or embedded` (an explicit, one-off

command; the embedded floor is correct when the server is down mid-install). The   scheduled refresh (below) uses `fetch(...)` and **skips the write entirely on   `None`**, so a transient outage leaves the already-installed — and newer — co

scheduled refresh (below) uses `fetch(...)` and **skips the write entirely on

[Credential-related source omitted]

[Credential-related source omitted]

[Credential-related source omitted]

[Credential-related source omitted]

[Credential-related source omitted]

[Credential-related source omitted]

[Credential-related source omitted]

[Credential-related source omitted]

[Credential-related source omitted]

[Credential-related source omitted]

[Credential-related source omitted]

[Credential-related source omitted]

[Credential-related source omitted]

[Credential-related source omitted]

CLI for [memU](https://github.com/NevaMind-AI/MemU) — personal memory as files. Persist agent-prepared memory and skill documents, then retrieve compact, ranked context instead of restuffing every prompt. Embedding-only: no LLM call happens

The only prerequisite is [uv](https://docs.astral.sh/uv/) — it fetches both a Python 3.13 runtime and the memU engine automatically, so nothing else needs to be preinstalled:

curl -LsSf https://astral.sh/uv/install.sh | sh    # macOS / Linux

curl -LsSf https://astral.sh/uv/install.sh | sh    # macOS / Linux

# Windows: powershell -c "irm https://astral.sh/uv/install.ps1 | iex"

[Credential-related source omitted]

[Credential-related source omitted]

[Credential-related source omitted]

[Credential-related source omitted]

instead. Register at [memu.so](https://memu.so) to obtain a memU API key. The

production API base defaults to `https://api.memu.so/api/v4/memory/` and can be

This npm package is a thin launcher (a few kB, no dependencies). The engine is the PyPI package [`memu-cli`](https://pypi.org/project/memu-cli/) — the memU engine itself, with prebuilt wheels for Linux (x86_64/aarch64), macOS (Intel/Apple S

See the [main README](https://github.com/NevaMind-AI/MemU#readme) for the memory model, library API, and self-hosting options.

#!/usr/bin/env node

"memu-cli: no Python runner found. The memU engine is the PyPI package `memu-cli` (Python >= 3.13).",     "Install one of:",     "  - uv    (https://docs.astral.sh/uv/)  -> memu-cli will use `uvx` automatically",

"Install one of:",     "  - uv    (https://docs.astral.sh/uv/)  -> memu-cli will use `uvx` automatically",     "  - pipx  (https://pipx.pypa.io/)       -> memu-cli will use `pipx run` automatically",

"  - uv    (https://docs.astral.sh/uv/)  -> memu-cli will use `uvx` automatically",

"  - pipx  (https://pipx.pypa.io/)       -> memu-cli will use `pipx run` automatically",

Executable file

"repository": {     "type": "git",     "url": "git+https://github.com/NevaMind-AI/MemU.git",

"type": "git",     "url": "git+https://github.com/NevaMind-AI/MemU.git",     "directory": "npm"

"url": "git+https://github.com/NevaMind-AI/MemU.git",

"directory": "npm"   },   "homepage": "https://github.com/NevaMind-AI/MemU#readme",

},   "homepage": "https://github.com/NevaMind-AI/MemU#readme",   "bugs": {

"homepage": "https://github.com/NevaMind-AI/MemU#readme",

"bugs": {     "url": "https://github.com/NevaMind-AI/MemU/issues"   }

"url": "https://github.com/NevaMind-AI/MemU/issues"

[project.urls] "Homepage" = "https://github.com/NevaMind-AI/MemU"

"Homepage" = "https://github.com/NevaMind-AI/MemU"

"Bug Tracker" = "https://github.com/NevaMind-AI/MemU/issues"

"Documentation" = "https://github.com/NevaMind-AI/MemU#readme"

#!/usr/bin/env python

[Credential-related source omitted]

Executable file

Executable file

Executable file

Executable file

Executable file

Executable file

Executable file

Executable file

Executable file

Executable file

Executable file

Executable file

[Credential-related source omitted]

description="Identifier for the embedding provider implementation (used by HTTP client backend).",     )     base_url: str = Field(default="https://api.openai.com/v1")

[Credential-related source omitted]

base_url: str = Field(default="https://api.openai.com/v1")

[Credential-related source omitted]

[Credential-related source omitted]

[Credential-related source omitted]

[Credential-related source omitted]

if self.base_url == "https://api.openai.com/v1":

[Credential-related source omitted]

[Credential-related source omitted]

Executable file

[Credential-related source omitted]

[Credential-related source omitted]

[Credential-related source omitted]

[Credential-related source omitted]

[Credential-related source omitted]

Executable file

DEFAULT_CLOUD_BASE_URL = "https://api.memu.so/api/v4/memory/"

[Credential-related source omitted]

[Credential-related source omitted]

[Credential-related source omitted]

[Credential-related source omitted]

[Credential-related source omitted]

[Credential-related source omitted]

[Credential-related source omitted]

[Credential-related source omitted]

self.timeout = timeout or httpx.Timeout(30.0, connect=5.0)

[Credential-related source omitted]

request_target = endpoint or self.base_url.rstrip("/")         async with httpx.AsyncClient(**client_kwargs) as client:

async with httpx.AsyncClient(**client_kwargs) as client:

Executable file

[Credential-related source omitted]

[Credential-related source omitted]

[Credential-related source omitted]

Executable file

Executable file

Executable file

Executable file

Executable file

Executable file

Executable file

Executable file

Executable file

Executable file

Executable file

Executable file

Executable file

Executable file

Executable file

Executable file

Executable file

Executable file

Executable file

Executable file

Executable file

Executable file

Executable file

Executable file

Executable file

Executable file

Executable file

Executable file

Executable file

Executable file

Executable file

Executable file

Executable file

Executable file

Executable file

Executable file

Executable file

Executable file

Executable file

Executable file

Executable file

Executable file

Executable file

Executable file

Executable file

Executable file

[Credential-related source omitted]

[Credential-related source omitted]

Executable file

Executable file

Jina exposes an OpenAI-compatible ``/embeddings`` surface (bearer auth,     ``{"model", "input"}`` payload, ``data[].embedding`` response) at     ``https://api.jina.ai/v1``. See https://jina.ai/embeddings/.

``{"model", "input"}`` payload, ``data[].embedding`` response) at     ``https://api.jina.ai/v1``. See https://jina.ai/embeddings/.     """

``https://api.jina.ai/v1``. See https://jina.ai/embeddings/.

Executable file

Executable file

OpenRouter serves embeddings at ``/api/v1/embeddings`` relative to     ``https://openrouter.ai``.

``https://openrouter.ai``.

Executable file

Voyage exposes an OpenAI-compatible ``/embeddings`` surface (bearer auth,     ``{"model", "input"}`` payload, ``data[].embedding`` response) at     ``https://api.voyageai.com/v1``. See https://docs.voyageai.com/.

``{"model", "input"}`` payload, ``data[].embedding`` response) at     ``https://api.voyageai.com/v1``. See https://docs.voyageai.com/.     """

``https://api.voyageai.com/v1``. See https://docs.voyageai.com/.

Executable file

Executable file

EMBEDDING_PROVIDER_ENDPOINTS: dict[str, tuple[str, str]] = {     "jina": ("https://api.jina.ai/v1", "JINA_API_KEY"),

[Credential-related source omitted]

[Credential-related source omitted]

[Credential-related source omitted]

[Credential-related source omitted]

[Credential-related source omitted]

[Credential-related source omitted]

[Credential-related source omitted]

[Credential-related source omitted]

EMBEDDING_SDK_BASE_URLS: dict[str, str] = {     "openrouter": "https://openrouter.ai/api/v1",

"openrouter": "https://openrouter.ai/api/v1",

Executable file

[Credential-related source omitted]

[Credential-related source omitted]

Executable file

httpx gives scheme-specific env-proxy mounts (``HTTP_PROXY`` mounts on     ``http://``) priority over a generic ``all://`` unmount, so the bypass must

``http://``) priority over a generic ``all://`` unmount, so the bypass must

[Credential-related source omitted]

# Ensure base_url ends with "/" so httpx doesn't discard the path         # component when joining with endpoint paths.         # See: https://github.com/NevaMind-AI/memU/issues/328

# See: https://github.com/NevaMind-AI/memU/issues/328

[Credential-related source omitted]

async with httpx.AsyncClient(

Example:             >>> client = HTTPEmbeddingClient(             ...     base_url="https://ark.cn-beijing.volces.com",

[Credential-related source omitted]

...     base_url="https://ark.cn-beijing.volces.com",

[Credential-related source omitted]

>>> embeddings = await client.embed_multimodal([             ...     ("text", "What is in the image and video?"),             ...     ("image_url", "https://example.com/image.png"),

...     ("text", "What is in the image and video?"),             ...     ("image_url", "https://example.com/image.png"),             ...     ("video_url", "https://example.com/video.mp4"),

...     ("image_url", "https://example.com/image.png"),

...     ("video_url", "https://example.com/video.mp4"),

endpoint = self.backend.multimodal_embedding_endpoint.lstrip("/")         async with httpx.AsyncClient(

async with httpx.AsyncClient(

[Credential-related source omitted]

Executable file

[Credential-related source omitted]

[Credential-related source omitted]

[Credential-related source omitted]

[Credential-related source omitted]

Executable file

[Credential-related source omitted]

[Credential-related source omitted]

[Credential-related source omitted]

[Credential-related source omitted]

[Credential-related source omitted]

[Credential-related source omitted]

[Credential-related source omitted]

[Credential-related source omitted]

[Credential-related source omitted]

[Credential-related source omitted]

[Credential-related source omitted]

Executable file

DEFAULT_EVENTS_URL = "https://api.memu.so/api/memu/analytics/events"

[Credential-related source omitted]

[Credential-related source omitted]

[Credential-related source omitted]

[Credential-related source omitted]

body = json.dumps(event, ensure_ascii=False, default=str).encode("utf-8")     request = urllib.request.Request(url, data=body, headers=_headers(), method="POST")  # noqa: S310

request = urllib.request.Request(url, data=body, headers=_headers(), method="POST")  # noqa: S310

try:         with urllib.request.urlopen(request, timeout=_TIMEOUT_SECONDS, **trust.urlopen_kwargs()) as response:  # noqa: S310             return ACCEPTED if 200 <= getattr(response, "status", 200) < 300 else RETRY

with urllib.request.urlopen(request, timeout=_TIMEOUT_SECONDS, **trust.urlopen_kwargs()) as response:  # noqa: S310

Executable file

Executable file

Executable file

Executable file

Executable file

Executable file

Executable file

Executable file

Executable file

Executable file

[Credential-related source omitted]

Executable file

> Prior art: [jshchnz/claude-code-scheduler](https://github.com/jshchnz/claude-code-scheduler),

[Credential-related source omitted]

**MemU Cloud.** Ask the user for their memU API key. If they do not have one, direct them to [memu.so](https://memu.so) to register and create one, then wait

direct them to [memu.so](https://memu.so) to register and create one, then wait

It reports where the file is and what protection it has; tell the user the key is stored there in plaintext. The production endpoint defaults to `https://api.memu.so/api/v4/memory/` — pass `--cloud-base-url` only for a

is stored there in plaintext. The production endpoint defaults to `https://api.memu.so/api/v4/memory/` — pass `--cloud-base-url` only for a non-default one, and never `--embed-api-key`, which is the *embedding

`https://api.memu.so/api/v4/memory/` — pass `--cloud-base-url` only for a

memu-claude-code config --local --db /absolute/path/memu.sqlite3 --embed-provider openai --embed-base-url http://localhost:11434/v1 --embed-model nomic-embed-text --embed-api-key local

memu-claude-code config --local --embed-base-url http://127.0.0.1:11434/v1

official install script (it lands in `~/.local/bin`, needs no elevation    and no node):    - Windows: `irm https://claude.ai/install.ps1 | iex`

and no node):    - Windows: `irm https://claude.ai/install.ps1 | iex`    - macOS / Linux: `curl -fsSL https://claude.ai/install.sh | bash`

- Windows: `irm https://claude.ai/install.ps1 | iex`

- macOS / Linux: `curl -fsSL https://claude.ai/install.sh | bash`

- macOS / Linux: `curl -fsSL https://claude.ai/install.sh | bash`

[Credential-related source omitted]

OAuth exchange fails even though the browser half looks complete.       Fix it where it lives, then rerun: in that terminal window,       `set HTTPS_PROXY=http://127.0.0.1:<port>` (and `HTTP_PROXY`

Fix it where it lives, then rerun: in that terminal window,       `set HTTPS_PROXY=http://127.0.0.1:<port>` (and `HTTP_PROXY`       likewise), then `claude setup-token` again. The scheduled run needs

`set HTTPS_PROXY=http://127.0.0.1:<port>` (and `HTTP_PROXY`

[Credential-related source omitted]

Executable file

Executable file

"  Install a standalone claude:\n"         "    winget install Anthropic.ClaudeCode\n"         "    # or:  irm https://claude.ai/install.ps1 | iex\n"

"    winget install Anthropic.ClaudeCode\n"         "    # or:  irm https://claude.ai/install.ps1 | iex\n"         "    # or:  npm install -g @anthropic-ai/claude-code"

"    # or:  irm https://claude.ai/install.ps1 | iex\n"

[Credential-related source omitted]

Executable file

[Credential-related source omitted]

Executable file

Executable file

Executable file

**MemU Cloud.** Ask the user for their memU API key. If they do not have one, direct them to [memu.so](https://memu.so) to register and create one, then wait

direct them to [memu.so](https://memu.so) to register and create one, then wait

It reports where the file is and what protection it has; tell the user the key is stored there in plaintext. The production endpoint defaults to `https://api.memu.so/api/v4/memory/` — pass `--cloud-base-url` only for a

is stored there in plaintext. The production endpoint defaults to `https://api.memu.so/api/v4/memory/` — pass `--cloud-base-url` only for a non-default one, and never `--embed-api-key`, which is the *embedding

`https://api.memu.so/api/v4/memory/` — pass `--cloud-base-url` only for a

memu-codex config --local --db /absolute/path/memu.sqlite3 --embed-provider openai --embed-base-url http://localhost:11434/v1 --embed-model nomic-embed-text --embed-api-key local

memu-codex config --local --embed-base-url http://127.0.0.1:11434/v1

irm https://chatgpt.com/codex/install.ps1 | iex

curl -fsSL https://chatgpt.com/codex/install.sh | sh

curl -fsSL https://chatgpt.com/codex/install.sh | sh

Executable file

Executable file

install_hint=(         "Install the standalone Codex CLI using the official native installer:\n"         "  Windows (PowerShell): irm https://chatgpt.com/codex/install.ps1 | iex\n"

"Install the standalone Codex CLI using the official native installer:\n"         "  Windows (PowerShell): irm https://chatgpt.com/codex/install.ps1 | iex\n"         "  macOS/Linux: curl -fsSL https://chatgpt.com/codex/install.sh | sh\n"

"  Windows (PowerShell): irm https://chatgpt.com/codex/install.ps1 | iex\n"         "  macOS/Linux: curl -fsSL https://chatgpt.com/codex/install.sh | sh\n"         "Refresh PATH, verify `codex --version`, then retry `memu-codex install-prom

"  macOS/Linux: curl -fsSL https://chatgpt.com/codex/install.sh | sh\n"

"  macOS/Linux: curl -fsSL https://chatgpt.com/codex/install.sh | sh\n"

Executable file

Executable file

[Credential-related source omitted]

Executable file

[Credential-related source omitted]

Executable file

Executable file

[Credential-related source omitted]

[Credential-related source omitted]

Executable file

[Credential-related source omitted]

Executable file

Executable file

Executable file

Executable file

Executable file

[Credential-related source omitted]

[Credential-related source omitted]

[Credential-related source omitted]

[Credential-related source omitted]

[Credential-related source omitted]

[Credential-related source omitted]

[Credential-related source omitted]

[Credential-related source omitted]

[Credential-related source omitted]

[Credential-related source omitted]

[Credential-related source omitted]

[Credential-related source omitted]

[Credential-related source omitted]

[Credential-related source omitted]

[Credential-related source omitted]

[Credential-related source omitted]

[Credential-related source omitted]

Executable file

Executable file

[Credential-related source omitted]

[Credential-related source omitted]

[Credential-related source omitted]

[Credential-related source omitted]

[Credential-related source omitted]

[Credential-related source omitted]

[Credential-related source omitted]

**MemU Cloud.** Ask the user for their memU API key. If they do not have one, direct them to [memu.so](https://memu.so) to register and create one, then wait

direct them to [memu.so](https://memu.so) to register and create one, then wait

It reports where the file is and what protection it has; tell the user the key is stored there in plaintext. The production endpoint defaults to `https://api.memu.so/api/v4/memory/` — pass `--cloud-base-url` only for a

is stored there in plaintext. The production endpoint defaults to `https://api.memu.so/api/v4/memory/` — pass `--cloud-base-url` only for a non-default one, and never `--embed-api-key`, which is the *embedding

`https://api.memu.so/api/v4/memory/` — pass `--cloud-base-url` only for a

memu-cursor config --local --db /absolute/path/memu.sqlite3 --embed-provider openai --embed-base-url http://localhost:11434/v1 --embed-model nomic-embed-text --embed-api-key local

memu-cursor config --local --embed-base-url http://127.0.0.1:11434/v1

1. **`cursor-agent` resolves on `PATH`.** If it does not, install it with the    user via Cursor's official installer —    `curl https://cursor.com/install -fsSL | bash` on macOS / Linux / WSL, or

user via Cursor's official installer —    `curl https://cursor.com/install -fsSL | bash` on macOS / Linux / WSL, or    `irm 'https://cursor.com/install?win32=true' | iex` on native Windows

`curl https://cursor.com/install -fsSL | bash` on macOS / Linux / WSL, or

`curl https://cursor.com/install -fsSL | bash` on macOS / Linux / WSL, or

`irm 'https://cursor.com/install?win32=true' | iex` on native Windows

[Credential-related source omitted]

Executable file

Executable file

install_hint=(         "  Install the standalone Cursor Agent CLI:\n"         "    irm 'https://cursor.com/install?win32=true' | iex\n"

"  Install the standalone Cursor Agent CLI:\n"         "    irm 'https://cursor.com/install?win32=true' | iex\n"         "    # macOS/Linux/WSL:  curl https://cursor.com/install -fsSL | bash\n"

"    irm 'https://cursor.com/install?win32=true' | iex\n"         "    # macOS/Linux/WSL:  curl https://cursor.com/install -fsSL | bash\n"         "  Then re-run from a NEW terminal - this shell's PATH may predate the install."

"    # macOS/Linux/WSL:  curl https://cursor.com/install -fsSL | bash\n"

"    # macOS/Linux/WSL:  curl https://cursor.com/install -fsSL | bash\n"

Executable file

**MemU Cloud.** Ask the user for their memU API key. If they do not have one, direct them to [memu.so](https://memu.so) to register and create one, then wait

direct them to [memu.so](https://memu.so) to register and create one, then wait

It reports where the file is and what protection it has; tell the user the key is stored there in plaintext. The production endpoint defaults to `https://api.memu.so/api/v4/memory/` — pass `--cloud-base-url` only for a

is stored there in plaintext. The production endpoint defaults to `https://api.memu.so/api/v4/memory/` — pass `--cloud-base-url` only for a non-default one, and never `--embed-api-key`, which is the *embedding

`https://api.memu.so/api/v4/memory/` — pass `--cloud-base-url` only for a

memu-agent config --local --db /absolute/path/memu.sqlite3 --embed-provider openai --embed-base-url http://localhost:11434/v1 --embed-model nomic-embed-text --embed-api-key local

memu-agent config --local --embed-base-url http://127.0.0.1:11434/v1

Executable file

Executable file

Executable file

[Credential-related source omitted]

Executable file

**MemU Cloud.** Ask the user for their memU API key. If they do not have one, direct them to [memu.so](https://memu.so) to register and create one, then wait

direct them to [memu.so](https://memu.so) to register and create one, then wait

It reports where the file is and what protection it has; tell the user the key is stored there in plaintext. The production endpoint defaults to `https://api.memu.so/api/v4/memory/` — pass `--cloud-base-url` only for a

is stored there in plaintext. The production endpoint defaults to `https://api.memu.so/api/v4/memory/` — pass `--cloud-base-url` only for a non-default one, and never `--embed-api-key`, which is the *embedding

`https://api.memu.so/api/v4/memory/` — pass `--cloud-base-url` only for a

memu-hermes config --local --db /absolute/path/memu.sqlite3 --embed-provider openai --embed-base-url http://localhost:11434/v1 --embed-model nomic-embed-text --embed-api-key local

memu-hermes config --local --embed-base-url http://127.0.0.1:11434/v1

rm -r ~/.hermes/skills/memu-retrieve

Executable file

Executable file

Executable file

[Credential-related source omitted]

[Credential-related source omitted]

Executable file

Executable file

[Credential-related source omitted]

[Credential-related source omitted]

[Credential-related source omitted]

f"hint: the embedding target is this machine and a proxy is configured ({listing}, from {source}). "         "This memU bypasses proxies for loopback targets, so the proxy is likely not the cause — check the "         f"embedding server its

"This memU bypasses proxies for loopback targets, so the proxy is likely not the cause — check the "         f"embedding server itself (is it running? does `curl {base_url}` answer?). On older memU releases "         "the proxy *would* hija

f"embedding server itself (is it running? does `curl {base_url}` answer?). On older memU releases "

[Credential-related source omitted]

[Credential-related source omitted]

Executable file

skill_text = templates.fetch(templates.RETRIEVAL_SKILL)

skill_text = templates.fetch(templates.RETRIEVAL_SKILL)

[Credential-related source omitted]

**MemU Cloud.** Ask the user for their memU API key. If they do not have one, direct them to [memu.so](https://memu.so) to register and create one, then wait

direct them to [memu.so](https://memu.so) to register and create one, then wait

It reports where the file is and what protection it has; tell the user the key is stored there in plaintext. The production endpoint defaults to `https://api.memu.so/api/v4/memory/` — pass `--cloud-base-url` only for a

is stored there in plaintext. The production endpoint defaults to `https://api.memu.so/api/v4/memory/` — pass `--cloud-base-url` only for a non-default one, and never `--embed-api-key`, which is the *embedding

`https://api.memu.so/api/v4/memory/` — pass `--cloud-base-url` only for a

memu-openclaw config --local --db /absolute/path/memu.sqlite3 --embed-provider openai --embed-base-url http://localhost:11434/v1 --embed-model nomic-embed-text --embed-api-key local

memu-openclaw config --local --embed-base-url http://127.0.0.1:11434/v1

Executable file

Executable file

Executable file

Executable file

[Credential-related source omitted]

[Credential-related source omitted]

[Credential-related source omitted]

[Credential-related source omitted]

[Credential-related source omitted]

[Credential-related source omitted]

[Credential-related source omitted]

Executable file

Executable file

Executable file

Executable file

Executable file

Executable file

Executable file

Executable file

better mining prompt cannot reach an install until that install upgrades. This module lets the SDK *try* the server's current copy at ``https://memu.pro/sdk/instructions/<name>.txt`` and use it when it is reachable

module lets the SDK *try* the server's current copy at ``https://memu.pro/sdk/instructions/<name>.txt`` and use it when it is reachable and well-formed, falling back otherwise.

``https://memu.pro/sdk/instructions/<name>.txt`` and use it when it is reachable

DEFAULT_BASE_URL = "https://memu.pro/sdk/instructions"

[Credential-related source omitted]

try:         with urllib.request.urlopen(url, timeout=_TIMEOUT_SECONDS, **trust.urlopen_kwargs()) as resp:  # noqa: S310

with urllib.request.urlopen(url, timeout=_TIMEOUT_SECONDS, **trust.urlopen_kwargs()) as resp:  # noqa: S310

def fetch(name: str) -> str | None:

DEFAULT_DOCS_BASE_URL = "https://memu.pro/sdk/docs"

[Credential-related source omitted]

**MemU Cloud.** Ask the user for their memU API key. If they do not have one, direct them to [memu.so](https://memu.so) to register and create one, then wait

direct them to [memu.so](https://memu.so) to register and create one, then wait

It reports where the file is and what protection it has; tell the user the key is stored there in plaintext. The production endpoint defaults to `https://api.memu.so/api/v4/memory/` — pass `--cloud-base-url` only for a

is stored there in plaintext. The production endpoint defaults to `https://api.memu.so/api/v4/memory/` — pass `--cloud-base-url` only for a non-default one, and never `--embed-api-key`, which is the *embedding

`https://api.memu.so/api/v4/memory/` — pass `--cloud-base-url` only for a

memu-workbuddy config --local --db /absolute/path/memu.sqlite3 --embed-provider openai --embed-base-url http://localhost:11434/v1 --embed-model nomic-embed-text --embed-api-key local

memu-workbuddy config --local --embed-base-url http://127.0.0.1:11434/v1

Executable file

Executable file

Executable file

Executable file

Executable file

Executable file

Executable file

Executable file

Executable file

Executable file

Executable file

Executable file

Executable file

Executable file

Executable file

Executable file

def _client(handler: Handler, *, max_attempts: int = 3) -> CloudMemoryClient:     return CloudMemoryClient(         base_url="https://cloud.example/api/v4/memory/",

[Credential-related source omitted]

base_url="https://cloud.example/api/v4/memory/",

[Credential-related source omitted]

[Credential-related source omitted]

max_attempts=max_attempts,         transport=httpx.MockTransport(handler),     )

transport=httpx.MockTransport(handler),

def handler(request: httpx.Request) -> httpx.Response:         seen.append(request)         return httpx.Response(200, json=payload)

return httpx.Response(200, json=payload)

def handler(request: httpx.Request) -> httpx.Response:         seen.append(request)         return httpx.Response(200, json=page)

return httpx.Response(200, json=page)

"agent_id": "a1",         }         return httpx.Response(200, json=response_payload)

return httpx.Response(200, json=response_payload)

def handler(request: httpx.Request) -> httpx.Response:         paths.append(request.url.path)         return httpx.Response(200, json={"categories": []})

return httpx.Response(200, json={"categories": []})

"resource": resources,         }         return httpx.Response(200, json={"recall_files": recall_files, "resources": []})

return httpx.Response(200, json={"recall_files": recall_files, "resources": []})

"agent_name": "Agent",         }         return httpx.Response(200, json={"recall_files": [], "resources": []})

return httpx.Response(200, json={"recall_files": [], "resources": []})

) -> None:     def handler(request: httpx.Request) -> httpx.Response:         return httpx.Response(

def handler(request: httpx.Request) -> httpx.Response:         return httpx.Response(             status,

return httpx.Response(

calls += 1         if calls == 1:             return httpx.Response(503, json={"message": "try again"})

if calls == 1:             return httpx.Response(503, json={"message": "try again"})         return httpx.Response(200, json={"categories": []})

return httpx.Response(503, json={"message": "try again"})

return httpx.Response(200, json={"categories": []})

nonlocal calls         calls += 1         return httpx.Response(401, json={"message": "bad key"})

return httpx.Response(401, json={"message": "bad key"})

nonlocal calls         calls += 1         raise httpx.ConnectError("offline", request=request)

raise httpx.ConnectError("offline", request=request)

async def test_invalid_success_response_is_not_silently_accepted() -> None:     def handler(request: httpx.Request) -> httpx.Response:         return httpx.Response(200, json=["unexpected"])

return httpx.Response(200, json=["unexpected"])

[Credential-related source omitted]

[Credential-related source omitted]

[Credential-related source omitted]

def test_cloud_factory_accepts_custom_base_url(config_file: pathlib.Path) -> None:     custom_base_url = "https://cloud.example/api/v4/memory/"

custom_base_url = "https://cloud.example/api/v4/memory/"

[Credential-related source omitted]

[Credential-related source omitted]

[Credential-related source omitted]

[Credential-related source omitted]

Executable file

Executable file

Executable file

Executable file

[Credential-related source omitted]

Executable file

Executable file

[Credential-related source omitted]

Executable file

Executable file

Executable file

[Credential-related source omitted]

_write(config, "# the store\nMEMU_DB=/old\n# the endpoint\nMEMU_BASE_URL=http://localhost:11434/v1\n")

assert config.read_text(encoding="utf-8") == (         "# the store\nMEMU_DB=/new\n# the endpoint\nMEMU_BASE_URL=http://localhost:11434/v1\n"

"# the store\nMEMU_DB=/new\n# the endpoint\nMEMU_BASE_URL=http://localhost:11434/v1\n"

[Credential-related source omitted]

[Credential-related source omitted]

[Credential-related source omitted]

[Credential-related source omitted]

[Credential-related source omitted]

[Credential-related source omitted]

[Credential-related source omitted]

[Credential-related source omitted]

[Credential-related source omitted]

[Credential-related source omitted]

[Credential-related source omitted]

[Credential-related source omitted]

_write(config, "MEMU_MEMORY_MODE=local\nMEMU_DB=/srv/db\nMEMU_BASE_URL=http://localhost:11434/v1\n")

assert run(SPEC, ["config", "--local", "--embed-base-url", "http://127.0.0.1:11434/v1"]) == 0

assert config_file.read()["MEMU_BASE_URL"] == "http://127.0.0.1:11434/v1"

def test_config_persists_a_non_default_endpoint(config: pathlib.Path) -> None:     assert run(SPEC, ["config", "--cloud", "--cloud-api-key", "sk-1", "--cloud-base-url", "https://staging/api/"]) == 0

assert run(SPEC, ["config", "--cloud", "--cloud-api-key", "sk-1", "--cloud-base-url", "https://staging/api/"]) == 0

assert config_file.read()["MEMU_CLOUD_BASE_URL"] == "https://staging/api/"

[Credential-related source omitted]

[Credential-related source omitted]

[Credential-related source omitted]

[Credential-related source omitted]

Executable file

Executable file

Executable file

Executable file

PROXY = "http://proxy.corp:8080"

LOOPBACK = "http://localhost:11434/v1"

[Credential-related source omitted]

def test_non_loopback_local_address_suggests_no_proxy(monkeypatch: pytest.MonkeyPatch) -> None:     monkeypatch.setenv("HTTP_PROXY", PROXY)     hint = _proxy_hint("http://host.docker.internal:11434/v1")

monkeypatch.setenv("HTTP_PROXY", PROXY)     hint = _proxy_hint("http://host.docker.internal:11434/v1")     assert hint is not None

hint = _proxy_hint("http://host.docker.internal:11434/v1")

Executable file

[Credential-related source omitted]

[Credential-related source omitted]

[Credential-related source omitted]

[Credential-related source omitted]

[Credential-related source omitted]

[Credential-related source omitted]

[Credential-related source omitted]

[Credential-related source omitted]

[Credential-related source omitted]

[Credential-related source omitted]

[Credential-related source omitted]

[Credential-related source omitted]

[Credential-related source omitted]

[Credential-related source omitted]

def raise_for_status(self):         if self.status_code >= 400:             request = httpx.Request("POST", "https://x/v1/embeddings")

if self.status_code >= 400:             request = httpx.Request("POST", "https://x/v1/embeddings")             raise httpx.HTTPStatusError(

request = httpx.Request("POST", "https://x/v1/embeddings")

raise httpx.HTTPStatusError(

str(self.status_code),                 request=request,                 response=httpx.Response(self.status_code, request=request),

request=request,                 response=httpx.Response(self.status_code, request=request),             )

response=httpx.Response(self.status_code, request=request),

[Credential-related source omitted]

[Credential-related source omitted]

[Credential-related source omitted]

async def test_embed_retries_transport_errors(monkeypatch):     client, attempts = _client_over([httpx.ConnectError("boom"), _StubResponse(200)], monkeypatch)

client, attempts = _client_over([httpx.ConnectError("boom"), _StubResponse(200)], monkeypatch)

[Credential-related source omitted]

[Credential-related source omitted]

def test_embedding_config_provider_defaults():     jina = EmbeddingConfig(provider="jina")     assert jina.base_url == "https://api.jina.ai/v1"

[Credential-related source omitted]

assert jina.base_url == "https://api.jina.ai/v1"

[Credential-related source omitted]

voyage = EmbeddingConfig(provider="voyage")     assert voyage.base_url == "https://api.voyageai.com/v1"

assert voyage.base_url == "https://api.voyageai.com/v1"

[Credential-related source omitted]

[Credential-related source omitted]

[Credential-related source omitted]

assert explicit.base_url == "https://proxy/v1"

[Credential-related source omitted]

Executable file

def do_POST(self):             payload = json.loads(self.rfile.read(int(self.headers["Content-Length"])))             requests.append((self.path, payload, self.headers["Authorization"]))

payload = json.loads(self.rfile.read(int(self.headers["Content-Length"])))             requests.append((self.path, payload, self.headers["Authorization"]))             self.send_response(200)  # Measure the actual URL; accept every path.

requests.append((self.path, payload, self.headers["Authorization"]))

thread.start()         try:             yield f"http://127.0.0.1:{server.server_port}", requests

try:             yield f"http://127.0.0.1:{server.server_port}", requests         finally:

yield f"http://127.0.0.1:{server.server_port}", requests

("options", "base_url", "path"),     [         ({}, "https://openrouter.ai/api/v1", "/api/v1/embeddings"),

[         ({}, "https://openrouter.ai/api/v1", "/api/v1/embeddings"),         ({"client_backend": "sdk"}, "https://openrouter.ai/api/v1", "/api/v1/embeddings"),

({}, "https://openrouter.ai/api/v1", "/api/v1/embeddings"),         ({"client_backend": "sdk"}, "https://openrouter.ai/api/v1", "/api/v1/embeddings"),         ({"client_backend": "httpx"}, "https://openrouter.ai", "/api/v1/embeddings"),

({"client_backend": "sdk"}, "https://openrouter.ai/api/v1", "/api/v1/embeddings"),         ({"client_backend": "httpx"}, "https://openrouter.ai", "/api/v1/embeddings"),         ({"base_url": "https://openrouter.ai"}, "https://openrouter.ai"

({"client_backend": "httpx"}, "https://openrouter.ai", "/api/v1/embeddings"),

({"base_url": "https://openrouter.ai"}, "https://openrouter.ai", "/embeddings"),

({"base_url": "https://proxy.example/custom/v1/"}, "https://proxy.example/custom/v1/", "/custom/v1/embeddings"),

({"base_url": "https://openrouter.ai/api/v1"}, "https://openrouter.ai/api/v1", "/api/v1/embeddings"),         (             {"client_backend": "httpx", "base_url": "https://proxy.example/prefix"},

(             {"client_backend": "httpx", "base_url": "https://proxy.example/prefix"},             "https://proxy.example/prefix",

{"client_backend": "httpx", "base_url": "https://proxy.example/prefix"},

"https://proxy.example/prefix",

{                 "client_backend": "httpx",                 "base_url": "https://proxy.example/v1",

"client_backend": "httpx",                 "base_url": "https://proxy.example/v1",                 "endpoint_overrides": {"embeddings": "/vectors"},

"base_url": "https://proxy.example/v1",

"endpoint_overrides": {"embeddings": "/vectors"},             },             "https://proxy.example/v1",

},             "https://proxy.example/v1",             "/v1/vectors",

"https://proxy.example/v1",

[Credential-related source omitted]

[Credential-related source omitted]

cfg = EmbeddingConfig(**embedding_profile())     assert cfg.client_backend == "sdk"     assert cfg.base_url == "https://openrouter.ai/api/v1"

[Credential-related source omitted]

assert cfg.base_url == "https://openrouter.ai/api/v1"

[Credential-related source omitted]

Executable file

PROXY = "http://proxy.corp:8080"

[Credential-related source omitted]

"url",     [         "http://localhost:11434/v1",

[         "http://localhost:11434/v1",         "http://LOCALHOST:11434/v1",

"http://localhost:11434/v1",

"http://LOCALHOST:11434/v1",

"http://ollama.localhost/v1",

"http://127.0.0.1:11434/v1",

"http://127.5.5.5/v1",

"http://[::1]:11434/v1",

"url",     [         "https://api.openai.com/v1",

[         "https://api.openai.com/v1",         "http://192.168.1.23:11434/v1",

"https://api.openai.com/v1",

"http://192.168.1.23:11434/v1",

"http://host.docker.internal:11434/v1",

"http://localhost.evil.com/v1",

def test_ambient_proxy_is_ignored_for_loopback(monkeypatch: pytest.MonkeyPatch) -> None:     monkeypatch.setenv("HTTP_PROXY", PROXY)     assert _load_proxy("http://localhost:11434/v1") is None

monkeypatch.setenv("HTTP_PROXY", PROXY)     assert _load_proxy("http://localhost:11434/v1") is None     assert _load_proxy("https://api.openai.com/v1") == PROXY

assert _load_proxy("http://localhost:11434/v1") is None

assert _load_proxy("https://api.openai.com/v1") == PROXY

monkeypatch.setenv("MEMU_HTTP_PROXY", PROXY)     assert _load_proxy("http://localhost:11434/v1") == PROXY

assert _load_proxy("http://localhost:11434/v1") == PROXY

[Credential-related source omitted]

[Credential-related source omitted]

assert proxy_bypass_mounts("http://localhost:11434/v1") == {"all://localhost": None}

assert proxy_bypass_mounts("http://127.0.0.1:11434/v1") == {"all://127.0.0.1": None}

assert proxy_bypass_mounts("http://[::1]:11434/v1") == {"all://[::1]": None}

assert proxy_bypass_mounts("https://api.openai.com/v1") is None

[Credential-related source omitted]

[Credential-related source omitted]

[Credential-related source omitted]

[Credential-related source omitted]

[Credential-related source omitted]

[Credential-related source omitted]

def _resolved_transport(client: OpenAIEmbeddingSDKClient, url: str) -> object:     inner = client.client._client     return inner._transport_for_url(httpx.URL(url))

return inner._transport_for_url(httpx.URL(url))

[Credential-related source omitted]

[Credential-related source omitted]

[Credential-related source omitted]

[Credential-related source omitted]

assert _resolved_transport(local, "http://localhost:11434/v1/embeddings") is local.client._client._transport

[Credential-related source omitted]

[Credential-related source omitted]

assert _resolved_transport(remote, "https://api.openai.com/v1/embeddings") is not remote.client._client._transport

[Credential-related source omitted]

[Credential-related source omitted]

[Credential-related source omitted]

assert (         _resolved_transport(opted_in, "http://localhost:11434/v1/embeddings") is not opted_in.client._client._transport     ), "MEMU_HTTP_PROXY alone must actually reach the SDK transport"

_resolved_transport(opted_in, "http://localhost:11434/v1/embeddings") is not opted_in.client._client._transport

server, port = await _json_server({"data": [{"embedding": [1.0, 2.0]}], "usage": {"total_tokens": 1}})     monkeypatch.setenv("HTTP_PROXY", "http://127.0.0.1:9")  # nothing listens there

monkeypatch.setenv("HTTP_PROXY", "http://127.0.0.1:9")  # nothing listens there

[Credential-related source omitted]

[Credential-related source omitted]

[Credential-related source omitted]

"usage": {"prompt_tokens": 1, "total_tokens": 1},     })     monkeypatch.setenv("HTTP_PROXY", "http://127.0.0.1:9")  # nothing listens there

monkeypatch.setenv("HTTP_PROXY", "http://127.0.0.1:9")  # nothing listens there

[Credential-related source omitted]

[Credential-related source omitted]

[Credential-related source omitted]

Executable file

[Credential-related source omitted]

PROXY = "http://proxy.corp:8080"

[Credential-related source omitted]

[Credential-related source omitted]

[Credential-related source omitted]

[Credential-related source omitted]

[Credential-related source omitted]

[Credential-related source omitted]

assert _load_proxy("http://localhost:11434/v1") == PROXY

Executable file

spool = tmp_path / "events.jsonl"     monkeypatch.setenv("MEMU_EVENTS_BASE_URL", "https://example.invalid/events")

monkeypatch.setenv("MEMU_EVENTS_BASE_URL", "https://example.invalid/events")

[Credential-related source omitted]

[Credential-related source omitted]

) -> None:     events.record(events.CLI_INSTALL_SUCCEEDED, host="codex")     error = urllib.error.HTTPError("https://example.invalid/events", status, "nope", {}, None)  # type: ignore[arg-type]

events.record(events.CLI_INSTALL_SUCCEEDED, host="codex")     error = urllib.error.HTTPError("https://example.invalid/events", status, "nope", {}, None)  # type: ignore[arg-type]     monkeypatch.setattr(events.urllib.request, "urlopen", _Po

error = urllib.error.HTTPError("https://example.invalid/events", status, "nope", {}, None)  # type: ignore[arg-type]

) -> None:     events.record(events.CLI_INSTALL_SUCCEEDED, host="codex")     error = urllib.error.HTTPError("https://example.invalid/events", status, "nope", {}, None)  # type: ignore[arg-type]

events.record(events.CLI_INSTALL_SUCCEEDED, host="codex")     error = urllib.error.HTTPError("https://example.invalid/events", status, "nope", {}, None)  # type: ignore[arg-type]     monkeypatch.setattr(events.urllib.request, "urlopen", _Po

error = urllib.error.HTTPError("https://example.invalid/events", status, "nope", {}, None)  # type: ignore[arg-type]

error = urllib.error.HTTPError("https://example.invalid/events", 422, "Unprocessable", {}, None)  # type: ignore[arg-type]

Executable file

Executable file

Executable file

Executable file

Executable file

[Credential-related source omitted]

[Credential-related source omitted]

Executable file

def _serve(monkeypatch: pytest.MonkeyPatch, body: bytes, status: int = 200) -> None:     monkeypatch.setenv("MEMU_TEMPLATE_BASE_URL", "https://example.test/inst")     monkeypatch.setattr("urllib.request.urlopen", lambda url, timeout=None: _

monkeypatch.setenv("MEMU_TEMPLATE_BASE_URL", "https://example.test/inst")

monkeypatch.setattr("urllib.request.urlopen", lambda url, timeout=None: _FakeResponse(body, status))

def _server_down(monkeypatch: pytest.MonkeyPatch) -> None:     monkeypatch.setenv("MEMU_TEMPLATE_BASE_URL", "https://example.test/inst")

monkeypatch.setenv("MEMU_TEMPLATE_BASE_URL", "https://example.test/inst")

monkeypatch.setattr("urllib.request.urlopen", _boom)

assert templates.fetch(templates.MEMORY_JOB) == body

assert templates.fetch(templates.MEMORY_JOB) is None

assert templates.fetch(templates.MEMORY_JOB) is None

def test_job_cooldown_survives_reload_and_expires(monkeypatch: pytest.MonkeyPatch, response: str | None) -> None:     cache = templates._cache_dir()     monkeypatch.setenv("MEMU_TEMPLATE_BASE_URL", "https://example.test/inst")

cache = templates._cache_dir()     monkeypatch.setenv("MEMU_TEMPLATE_BASE_URL", "https://example.test/inst")     now = 100_000.0

monkeypatch.setenv("MEMU_TEMPLATE_BASE_URL", "https://example.test/inst")

assert templates.resolve(templates.MEMORY_JOB, embedded) == expected     assert len(calls) == 2     monkeypatch.setenv("MEMU_TEMPLATE_BASE_URL", "https://other.test/inst")

assert len(calls) == 2     monkeypatch.setenv("MEMU_TEMPLATE_BASE_URL", "https://other.test/inst")     assert templates.resolve(templates.MEMORY_JOB, embedded) == expected

monkeypatch.setenv("MEMU_TEMPLATE_BASE_URL", "https://other.test/inst")

monkeypatch.setattr(templates, "_get", get)     for source in ("a", "b", "a"):         base = f"https://{source}.test"

for source in ("a", "b", "a"):         base = f"https://{source}.test"         monkeypatch.setenv("MEMU_TEMPLATE_BASE_URL", base)

base = f"https://{source}.test"

def test_same_url_updates_content_only_after_expiry(monkeypatch: pytest.MonkeyPatch) -> None:     monkeypatch.setenv("MEMU_TEMPLATE_BASE_URL", "https://example.test")

monkeypatch.setenv("MEMU_TEMPLATE_BASE_URL", "https://example.test")

Executable file

Executable file

Executable file

Executable file

Executable file

Executable file

[Credential-related source omitted]

[Credential-related source omitted]

Executable file

Executable file

Executable file

Executable file

def exec(self, stmt: Any) -> _StubSession:

Executable file

Executable file

def test_remote_doc_without_naming_contract_is_rejected(monkeypatch: pytest.MonkeyPatch) -> None:     monkeypatch.setenv("MEMU_DOCS_BASE_URL", "https://example.test/docs")

monkeypatch.setenv("MEMU_DOCS_BASE_URL", "https://example.test/docs")

"Current {{task_name}}; former {{former_task_names}}; all {{all_task_names}}.\n"     )     monkeypatch.setenv("MEMU_DOCS_BASE_URL", "https://example.test/docs")

)     monkeypatch.setenv("MEMU_DOCS_BASE_URL", "https://example.test/docs")     monkeypatch.setattr(templates, "_get", lambda url: source)

monkeypatch.setenv("MEMU_DOCS_BASE_URL", "https://example.test/docs")

cache.write_text(old, encoding="utf-8")     monkeypatch.setattr(templates, "_docs_cache_dir", lambda _: tmp_path)     monkeypatch.setenv("MEMU_DOCS_BASE_URL", "https://example.test/docs")

monkeypatch.setattr(templates, "_docs_cache_dir", lambda _: tmp_path)     monkeypatch.setenv("MEMU_DOCS_BASE_URL", "https://example.test/docs")     monkeypatch.setattr(templates, "_get", lambda _: old)

monkeypatch.setenv("MEMU_DOCS_BASE_URL", "https://example.test/docs")

Executable file

assert events._post("https://example.test/events", {"event_name": "x"}) == events.ACCEPTED

templates._get("https://example.test/inst/memory-job.txt")

Executable file

name = "alembic" version = "1.17.2" source = { registry = "https://pypi.org/simple" }

version = "1.17.2" source = { registry = "https://pypi.org/simple" } dependencies = [

source = { registry = "https://pypi.org/simple" }

{ name = "typing-extensions" }, ] sdist = { url = "https://files.pythonhosted.org/packages/02/a6/74c8cadc2882977d80ad756a13857857dbcf9bd405bc80b662eb10651282/alembic-1.17.2.tar.gz", hash = "sha256:bbe9751705c5e0f14877f02d46c53d10885e377e3d9

] sdist = { url = "https://files.pythonhosted.org/packages/02/a6/74c8cadc2882977d80ad756a13857857dbcf9bd405bc80b662eb10651282/alembic-1.17.2.tar.gz", hash = "sha256:bbe9751705c5e0f14877f02d46c53d10885e377e3d90eda810a016f9baa19e8e", size = 1

sdist = { url = "https://files.pythonhosted.org/packages/02/a6/74c8cadc2882977d80ad756a13857857dbcf9bd405bc80b662eb10651282/alembic-1.17.2.tar.gz", hash = "sha256:bbe9751705c5e0f14877f02d46c53d10885e377e3d90eda810a016f9baa19e8e", size = 198

wheels = [     { url = "https://files.pythonhosted.org/packages/ba/88/6237e97e3385b57b5f1528647addea5cc03d4d65d5979ab24327d41fb00d/alembic-1.17.2-py3-none-any.whl", hash = "sha256:f483dd1fe93f6c5d49217055e4d15b905b425b6af906746abb35b69c1996

{ url = "https://files.pythonhosted.org/packages/ba/88/6237e97e3385b57b5f1528647addea5cc03d4d65d5979ab24327d41fb00d/alembic-1.17.2-py3-none-any.whl", hash = "sha256:f483dd1fe93f6c5d49217055e4d15b905b425b6af906746abb35b69c1996c4e6", size = 2

name = "annotated-types" version = "0.7.0" source = { registry = "https://pypi.org/simple" }

version = "0.7.0" source = { registry = "https://pypi.org/simple" } sdist = { url = "https://files.pythonhosted.org/packages/ee/67/531ea369ba64dcff5ec9c3402f9f51bf748cec26dde048a2f973a4eea7f5/annotated_types-0.7.0.tar.gz", hash = "sha256:af

source = { registry = "https://pypi.org/simple" }

sdist = { url = "https://files.pythonhosted.org/packages/ee/67/531ea369ba64dcff5ec9c3402f9f51bf748cec26dde048a2f973a4eea7f5/annotated_types-0.7.0.tar.gz", hash = "sha256:aff07c09a53a08bc8cfccb9c85b05f1aa9a2a6f23728d790723543408344ce89", siz

wheels = [     { url = "https://files.pythonhosted.org/packages/78/b6/6307fbef88d9b5ee7421e68d78a9f162e0da4900bc5f5793f6d3d0e34fb8/annotated_types-0.7.0-py3-none-any.whl", hash = "sha256:1f02e8b43a8fbbc3f3e0d4f0f4bfc8131bcb4eebe8849b8e5c773

{ url = "https://files.pythonhosted.org/packages/78/b6/6307fbef88d9b5ee7421e68d78a9f162e0da4900bc5f5793f6d3d0e34fb8/annotated_types-0.7.0-py3-none-any.whl", hash = "sha256:1f02e8b43a8fbbc3f3e0d4f0f4bfc8131bcb4eebe8849b8e5c773f3a1c582a53", s

name = "anyio" version = "4.14.2" source = { registry = "https://pypi.org/simple" }

version = "4.14.2" source = { registry = "https://pypi.org/simple" } dependencies = [

source = { registry = "https://pypi.org/simple" }

{ name = "typing-extensions", marker = "python_full_version < '3.13'" }, ] sdist = { url = "https://files.pythonhosted.org/packages/61/cc/a381afa6efea9f496eff839d4a6a1aed3bfafc7b3ab4b0d1b243a12573dd/anyio-4.14.2.tar.gz", hash = "sha256:cfa1

] sdist = { url = "https://files.pythonhosted.org/packages/61/cc/a381afa6efea9f496eff839d4a6a1aed3bfafc7b3ab4b0d1b243a12573dd/anyio-4.14.2.tar.gz", hash = "sha256:cfa139f3ed1a23ee8f88a145ddb5ac7605b8bbfd8592baacd7ce3d8bb4313c7f", size = 260

sdist = { url = "https://files.pythonhosted.org/packages/61/cc/a381afa6efea9f496eff839d4a6a1aed3bfafc7b3ab4b0d1b243a12573dd/anyio-4.14.2.tar.gz", hash = "sha256:cfa139f3ed1a23ee8f88a145ddb5ac7605b8bbfd8592baacd7ce3d8bb4313c7f", size = 26017

wheels = [     { url = "https://files.pythonhosted.org/packages/da/35/f2287558c17e29fafc8ef3daf819bb9834061cfa43bff8014f7df7f63bdc/anyio-4.14.2-py3-none-any.whl", hash = "sha256:9f505dda5ac9f0c8309b5e8bd445a8c2bf7246f3ce950121e45ea15bc41d14

{ url = "https://files.pythonhosted.org/packages/da/35/f2287558c17e29fafc8ef3daf819bb9834061cfa43bff8014f7df7f63bdc/anyio-4.14.2-py3-none-any.whl", hash = "sha256:9f505dda5ac9f0c8309b5e8bd445a8c2bf7246f3ce950121e45ea15bc41d1494", size = 125

name = "certifi" version = "2025.10.5" source = { registry = "https://pypi.org/simple" }

version = "2025.10.5" source = { registry = "https://pypi.org/simple" } sdist = { url = "https://files.pythonhosted.org/packages/4c/5b/b6ce21586237c77ce67d01dc5507039d444b630dd76611bbca2d8e5dcd91/certifi-2025.10.5.tar.gz", hash = "sha256:47

source = { registry = "https://pypi.org/simple" }

sdist = { url = "https://files.pythonhosted.org/packages/4c/5b/b6ce21586237c77ce67d01dc5507039d444b630dd76611bbca2d8e5dcd91/certifi-2025.10.5.tar.gz", hash = "sha256:47c09d31ccf2acf0be3f701ea53595ee7e0b8fa08801c6624be771df09ae7b43", size = 

wheels = [     { url = "https://files.pythonhosted.org/packages/e4/37/af0d2ef3967ac0d6113837b44a4f0bfe1328c2b9763bd5b1744520e5cfed/certifi-2025.10.5-py3-none-any.whl", hash = "sha256:0f212c2744a9bb6de0c56639a6f68afe01ecd92d91f14ae897c4fe7bb

{ url = "https://files.pythonhosted.org/packages/e4/37/af0d2ef3967ac0d6113837b44a4f0bfe1328c2b9763bd5b1744520e5cfed/certifi-2025.10.5-py3-none-any.whl", hash = "sha256:0f212c2744a9bb6de0c56639a6f68afe01ecd92d91f14ae897c4fe7bbeeef0de", size 

name = "cfgv" version = "3.4.0" source = { registry = "https://pypi.org/simple" }

version = "3.4.0" source = { registry = "https://pypi.org/simple" } sdist = { url = "https://files.pythonhosted.org/packages/11/74/539e56497d9bd1d484fd863dd69cbbfa653cd2aa27abfe35653494d85e94/cfgv-3.4.0.tar.gz", hash = "sha256:e52591d4c5f5d

source = { registry = "https://pypi.org/simple" }

sdist = { url = "https://files.pythonhosted.org/packages/11/74/539e56497d9bd1d484fd863dd69cbbfa653cd2aa27abfe35653494d85e94/cfgv-3.4.0.tar.gz", hash = "sha256:e52591d4c5f5dead8e0f673fb16db7949d2cfb3f7da4582893288f0ded8fe560", size = 7114, u

wheels = [     { url = "https://files.pythonhosted.org/packages/c5/55/51844dd50c4fc7a33b653bfaba4c2456f06955289ca770a5dbd5fd267374/cfgv-3.4.0-py2.py3-none-any.whl", hash = "sha256:b7265b1f29fd3316bfcd2b330d63d024f2bfd8bcb8b0272f8e19a504856c

{ url = "https://files.pythonhosted.org/packages/c5/55/51844dd50c4fc7a33b653bfaba4c2456f06955289ca770a5dbd5fd267374/cfgv-3.4.0-py2.py3-none-any.whl", hash = "sha256:b7265b1f29fd3316bfcd2b330d63d024f2bfd8bcb8b0272f8e19a504856c48f9", size = 7

name = "click" version = "8.4.2" source = { registry = "https://pypi.org/simple" }

version = "8.4.2" source = { registry = "https://pypi.org/simple" } dependencies = [

source = { registry = "https://pypi.org/simple" }

{ name = "colorama", marker = "sys_platform == 'win32'" }, ] sdist = { url = "https://files.pythonhosted.org/packages/76/d4/81420972a676e8ffea40450d8c8c92943e7218a78fe9b64359836cc9876b/click-8.4.2.tar.gz", hash = "sha256:9a6cea6e60b17ebe0a4

] sdist = { url = "https://files.pythonhosted.org/packages/76/d4/81420972a676e8ffea40450d8c8c92943e7218a78fe9b64359836cc9876b/click-8.4.2.tar.gz", hash = "sha256:9a6cea6e60b17ebe0a44c5cc636d94f09bd66142c1cd7d8b4cd731c4917a15f6", size = 3380