anycap-ai/anycap

metadata:   version: 0.6.5   website: https://anycap.ai

version: 0.6.5   website: https://anycap.ai license: MIT

website: https://anycap.ai

anycap crawl https://example.com

- Google's [Search Essentials](https://developers.google.com/search/docs/essentials) say meeting technical requirements does not guarantee crawling, indexing, or serving. A live URL test and a clear manual-action report do not establish tha

- A [sitemap](https://developers.google.com/search/docs/crawling-indexing/sitemaps/build-sitemap) helps discovery but does not guarantee indexing. Use `<lastmod>` only for significant, real changes; do not repeatedly resubmit an unchanged s

- [Recrawl requests](https://developers.google.com/search/docs/crawling-indexing/ask-google-to-recrawl) can take days to weeks and do not guarantee inclusion. Repeating the request does not make Google crawl faster.

- Follow [people-first content guidance](https://developers.google.com/search/docs/fundamentals/creating-helpful-content). There is no preferred word count; changing a date without meaningful changes is not a freshness strategy. “E-E-A-T” i

- [Scaled content abuse](https://developers.google.com/search/docs/essentials/spam-policies) can apply regardless of whether text is produced by humans or AI. Do not mass-publish keyword variants, doorway pages, or lightly rewritten pages.

- Google [retired the FAQ rich result feature in May 2026](https://developers.google.com/search/updates) and removed its documentation in June 2026. A useful FAQ may still help readers, but `FAQPage` markup is not a Google Search enhancemen

- Google's [generative AI Search guidance](https://developers.google.com/search/docs/fundamentals/ai-optimization-guide) applies core SEO to AI Overviews and AI Mode. Google Search does not use `llms.txt` as a ranking or visibility signal, 

- For international pages, follow [localized-version guidance](https://developers.google.com/search/docs/specialty/international/localized-versions): localize the main content, make alternate references reciprocal, and use a suitable canoni

- Prefer relevant editorial mentions and user-serving internal links. Do not recommend paid link schemes, bulk exchanges, or low-quality directory volume. Qualify paid placements with [appropriate link attributes](https://developers.google.

metadata:   version: 0.6.5   website: https://anycap.ai

version: 0.6.5   website: https://anycap.ai   compatibility: Requires anycap CLI binary and internet access. Best for AnyCap website content, especially blog, learn, guide, glossary, and landing-page style articles authored from structured 

website: https://anycap.ai

metadata:   version: 0.6.5   website: https://anycap.ai

version: 0.6.5   website: https://anycap.ai license: MIT

website: https://anycap.ai

Read the machine-readable install guide at https://anycap.ai/install.txt for installation tasks. Do not fetch the homepage for install automation. Prefer the **binary install** (install script or GitHub Releases) over npm -- fewer dependenc

[Credential-related source omitted]

[Credential-related source omitted]

[Credential-related source omitted]

# Instead of constructing a JSON URL array: #   --param images='["https://example.com/photo.jpg"]'

#   --param images='["https://example.com/photo.jpg"]'

# Blocking mode -- opens browser, waits for Done click anycap annotate photo.png -o annotated.png anycap annotate https://localhost:3000

anycap annotate photo.png -o annotated.png anycap annotate https://localhost:3000 anycap annotate output.mp4

anycap annotate https://localhost:3000

# Crawl a web page to Markdown (1 credit) anycap crawl https://example.com | jq -r '.data.markdown'

anycap crawl https://example.com | jq -r '.data.markdown'

[Credential-related source omitted]

[Credential-related source omitted]

[Credential-related source omitted]

[Credential-related source omitted]

# Analyze a remote image by URL anycap actions image-read --url https://example.com/photo.jpg | jq -r '.content'

anycap actions image-read --url https://example.com/photo.jpg | jq -r '.content'

# Crawl a web page and get Markdown content anycap crawl https://example.com | jq -r '.data.markdown'

anycap crawl https://example.com | jq -r '.data.markdown'

This project uses [AnyCap](https://anycap.ai) for multimodal capabilities -- image generation, video generation, music, image/video/audio understanding, web search, web crawling, file storage, and static site hosting. When a task requires a

# Single image anycap actions image-read --url https://example.com/photo.jpg

anycap actions image-read --url https://example.com/photo.jpg

# Multiple images (up to 10) anycap actions image-read \   --url https://example.com/before.jpg \

anycap actions image-read    --url https://example.com/before.jpg

--url https://example.com/before.jpg \

--url https://example.com/after.jpg \

# Mix URLs and local files anycap actions image-read \   --url https://example.com/reference.jpg \

anycap actions image-read    --url https://example.com/reference.jpg

--url https://example.com/reference.jpg \

anycap actions video-read --url https://example.com/clip.mp4

anycap actions video-read --url https://www.youtube.com/watch?v=dQw4w9WgXcQ --instruction "Summarize this video"

anycap actions audio-read --url https://example.com/recording.wav

anycap actions audio-read --url https://www.youtube.com/watch?v=dQw4w9WgXcQ --instruction "Transcribe the lyrics"

# Pipe content into another tool or file anycap actions image-read --url https://example.com/chart.png \

anycap actions image-read --url https://example.com/chart.png \

|------|-------------------|---------------------|-----------------|----------| | Image | File extension (.png, .jpg, .webp, ...) | Image with annotation overlay | Yes (original + annotations composited) | Yes | | URL | `http://` or `https:

| Image | File extension (.png, .jpg, .webp, ...) | Image with annotation overlay | Yes (original + annotations composited) | Yes | | URL | `http://` or `https://` prefix | Live iframe with annotation overlay + Browse mode | No (cross-origi

| URL | `http://` or `https://` prefix | Live iframe with annotation overlay + Browse mode | No (cross-origin) | Yes |

anycap annotate photo.png anycap annotate https://localhost:3000

anycap annotate https://localhost:3000

"status": "started",   "session": "ann_a1b2c3d4",   "url": "http://127.0.0.1:54321",

"session": "ann_a1b2c3d4",   "url": "http://127.0.0.1:54321",   "poll_command": "anycap annotate poll --session ann_a1b2c3d4",

"url": "http://127.0.0.1:54321",

[Credential-related source omitted]

| Flag | Description | |------|-------------| | `--endpoint <url>` | Override the server endpoint (default: `https://api.anycap.ai`) |

|------|-------------| | `--endpoint <url>` | Override the server endpoint (default: `https://api.anycap.ai`) | | `--verbose` | Enable verbose output (debug logs to stderr) |

| `--endpoint <url>` | Override the server endpoint (default: `https://api.anycap.ai`) |

[Credential-related source omitted]

[Credential-related source omitted]

[Credential-related source omitted]

[Credential-related source omitted]

[Credential-related source omitted]

[Credential-related source omitted]

| Key | Type | Default | Env Override | Description | |-----|------|---------|-------------|-------------| | `endpoint` | string | `https://api.anycap.ai` | `ANYCAP_API_ENDPOINT` | Server endpoint URL |

|-----|------|---------|-------------|-------------| | `endpoint` | string | `https://api.anycap.ai` | `ANYCAP_API_ENDPOINT` | Server endpoint URL | | `auto_update` | bool | `true` | `ANYCAP_NO_UPDATE` (any value to disable) | Auto-update C

| `endpoint` | string | `https://api.anycap.ai` | `ANYCAP_API_ENDPOINT` | Server endpoint URL |

# Set a value anycap config set endpoint https://api.anycap.ai

anycap config set endpoint https://api.anycap.ai

# ~/.anycap/config.toml endpoint = "https://api.anycap.ai"

endpoint = "https://api.anycap.ai"

[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]

# Crawl a page (returns title + markdown + url) anycap crawl https://go.dev

anycap crawl https://go.dev

# Extract just the markdown content anycap crawl https://docs.go.dev/ref/spec | jq -r '.data.markdown'

anycap crawl https://docs.go.dev/ref/spec | jq -r '.data.markdown'

# Get the page title anycap crawl https://go.dev | jq -r '.data.title'

anycap crawl https://go.dev | jq -r '.data.title'

# Crawl documentation anycap crawl https://docs.python.org/3/library/asyncio.html | jq -r '.data.markdown'

anycap crawl https://docs.python.org/3/library/asyncio.html | jq -r '.data.markdown'

"status": "success",   "data": {     "url": "https://go.dev",

"data": {     "url": "https://go.dev",     "title": "The Go Programming Language",

"url": "https://go.dev",

"status": "started",   "session": "drw_a1b2c3d4",   "url": "http://127.0.0.1:18400",

"session": "drw_a1b2c3d4",   "url": "http://127.0.0.1:18400",   "poll_command": "anycap draw poll --session drw_a1b2c3d4",

"url": "http://127.0.0.1:18400",

anycap drive rm <node-id>

anycap drive rm --src-path /results/old-data.csv

{   "status": "success",   "url": "https://drive.anycap.dev/s/abc123",

"status": "success",   "url": "https://drive.anycap.dev/s/abc123",   "expires_at": "2026-04-06T14:00:00Z",

"url": "https://drive.anycap.dev/s/abc123",

anycap image generate    --prompt "remove the background"    --model <model-id>    --mode image-to-image    --param images=https://example.com/photo.jpg

--model <model-id> \   --mode image-to-image \   --param images=https://example.com/photo.jpg \

--mode image-to-image \   --param images=https://example.com/photo.jpg \   -o no-bg.png

--param images=https://example.com/photo.jpg \

anycap image generate    --prompt "a portrait in the style of the reference images"    --model <model-id>    --mode image-to-image    --param images='["./local-ref.png","https://example.com/style-ref.jpg"]'

--model <model-id> \   --mode image-to-image \   --param images='["./local-ref.png","https://example.com/style-ref.jpg"]' \

--mode image-to-image \   --param images='["./local-ref.png","https://example.com/style-ref.jpg"]' \   -o portrait-styled.png

--param images='["./local-ref.png","https://example.com/style-ref.jpg"]' \

"credits_used": 5,   "outputs": [     {"local_path": "/absolute/path/to/lofi-drive.mp3", "url": "https://..."},

"outputs": [     {"local_path": "/absolute/path/to/lofi-drive.mp3", "url": "https://..."},     {"local_path": "/absolute/path/to/lofi-drive_2.mp3", "url": "https://..."}

{"local_path": "/absolute/path/to/lofi-drive.mp3", "url": "https://..."},

{"local_path": "/absolute/path/to/lofi-drive_2.mp3", "url": "https://..."}

"page_id": "pg_aBcDeFg",   "page_name": "my-docs-a1b2c3",   "page_url": "https://page-my-docs-a1b2c3.anycap.dev",

"page_name": "my-docs-a1b2c3",   "page_url": "https://page-my-docs-a1b2c3.anycap.dev",   "version": 1,

"page_url": "https://page-my-docs-a1b2c3.anycap.dev",

{         "title": "The Go Programming Language",         "url": "https://go.dev/",

"title": "The Go Programming Language",         "url": "https://go.dev/",         "description": "An open-source programming language...",

"url": "https://go.dev/",

"queries": ["Go 1.25 changes", "Go 1.25 release notes"],       "sources": [         {"index": 1, "title": "go.dev", "uri": "https://go.dev/doc/go1.25"},

"sources": [         {"index": 1, "title": "go.dev", "uri": "https://go.dev/doc/go1.25"},         {"index": 2, "title": "github.com", "uri": "https://github.com/golang/go/milestone/..."}

{"index": 1, "title": "go.dev", "uri": "https://go.dev/doc/go1.25"},

{"index": 2, "title": "github.com", "uri": "https://github.com/golang/go/milestone/..."}

[Credential-related source omitted]

[Credential-related source omitted]

[Credential-related source omitted]

anycap social get --url "https://www.instagram.com/p/<shortcode>/"

anycap social get --url "https://www.instagram.com/reel/<shortcode>/"

anycap social get --url "https://x.com/<username>/status/<post-id>"

anycap video generate    --prompt "animate this scene with gentle wind"    --model <model-id>    --mode image-to-video    --param images=https://example.com/photo.jpg

--model <model-id> \   --mode image-to-video \   --param images=https://example.com/photo.jpg

--param images=https://example.com/photo.jpg

metadata:   version: 0.6.5   website: https://anycap.ai

version: 0.6.5   website: https://anycap.ai license: MIT

website: https://anycap.ai

# Read a specific important page anycap crawl https://important-source.com/article \

anycap crawl https://important-source.com/article \

# Extract just the markdown for reading anycap crawl https://docs.example.com/spec | jq -r '.data.markdown' \

anycap crawl https://docs.example.com/spec | jq -r '.data.markdown' \

# Download an image from a source curl -o research-topic/assets/architecture-diagram.png "https://example.com/diagram.png"

curl -o research-topic/assets/architecture-diagram.png "https://example.com/diagram.png"

# Analyze a video for key insights anycap actions video-read --url https://example.com/talk.mp4 \

anycap actions video-read --url https://example.com/talk.mp4 \

# Check the original source directly anycap crawl https://primary-source.com/data \

anycap crawl https://primary-source.com/data \

> Cloudflare Workers uses [V8 isolates rather than traditional containers](https://blog.cloudflare.com/workers-architecture) for workload isolation.

> Cloudflare Workers uses V8 isolates rather than traditional containers [[1]](https://blog.cloudflare.com/workers-architecture) for workload isolation.

**Include specific data.** Numbers, dates, version numbers, quotes -- specifics make a report credible. Vague claims ("many companies use X") are weak; specific claims ("as of 2026, [Cloudflare Workers](https://workers.cloudflare.com/), [Fa

![Architecture diagram from the official documentation](research-topic/assets/architecture-diagram.png) *Source: [Official Docs](https://example.com/docs) [[3]](https://example.com/docs)*

*Source: [Official Docs](https://example.com/docs) [[3]](https://example.com/docs)*

metadata:   version: 0.6.5   website: https://anycap.ai

version: 0.6.5   website: https://anycap.ai license: MIT

website: https://anycap.ai

- Gemini Omni Flash guide: https://ai.google.dev/gemini-api/docs/omni

- Gemini API video overview: https://ai.google.dev/gemini-api/docs/video

- Gemini Omni Flash model card: https://ai.google.dev/gemini-api/docs/models/gemini-omni-flash

metadata:   version: 0.6.5   website: https://anycap.ai

version: 0.6.5   website: https://anycap.ai license: MIT

website: https://anycap.ai

`<target>` is auto-detected by content: image file, URL (`http://` or `https://`), video file, or audio file.

- **Direct access:** `http://<server-ip>:8888` (if the port is exposed) - **SSH port forward:** `ssh -L 8888:localhost:8888 user@host`, then open `http://localhost:8888`

- **SSH port forward:** `ssh -L 8888:localhost:8888 user@host`, then open `http://localhost:8888`

- **Container port mapping:** `docker run -p 8888:8888 ...`, then open `http://localhost:8888`

https://yourserver.com/tools/annotate/  ->  http://localhost:8888/

# Local dev server anycap annotate http://localhost:3000 --no-wait

anycap annotate http://localhost:3000 --no-wait

# Live URL anycap annotate https://staging.example.com --no-wait

anycap annotate https://staging.example.com --no-wait

# Round 1: Initial review anycap annotate http://localhost:3000 --no-wait

anycap annotate http://localhost:3000 --no-wait

# Round 2: Verification review anycap annotate http://localhost:3000 --no-wait

anycap annotate http://localhost:3000 --no-wait

|-----------|----------|-----| | Built/modified a web page | URL Review (single-user) | Recording captures browsing, scrolling, and narrated feedback | | Local dev server needs review | URL Review (single-user) | Same as above -- use `http:

| Built/modified a web page | URL Review (single-user) | Recording captures browsing, scrolling, and narrated feedback | | Local dev server needs review | URL Review (single-user) | Same as above -- use `http://localhost:PORT` | | Generated

| Local dev server needs review | URL Review (single-user) | Same as above -- use `http://localhost:PORT` |

metadata:   version: 0.6.5   website: https://anycap.ai

version: 0.6.5   website: https://anycap.ai license: MIT

website: https://anycap.ai

anycap image generate    --prompt "a portrait in the style of the reference images"    --model <model-id>    --mode image-to-image    --param images='["./local-ref.png","https://example.com/style-ref.jpg"]'

--model <model-id> \   --mode image-to-image \   --param images='["./local-ref.png","https://example.com/style-ref.jpg"]' \

--mode image-to-image \   --param images='["./local-ref.png","https://example.com/style-ref.jpg"]' \   -o portrait-styled.png

--param images='["./local-ref.png","https://example.com/style-ref.jpg"]' \

metadata:   version: 0.6.5   website: https://anycap.ai

version: 0.6.5   website: https://anycap.ai license: MIT

website: https://anycap.ai

> Predict who will win and the likely scoreline for any World Cup match -- backed by > structured, verifiable pre-match intel. An [AnyCap](https://anycap.ai) agent skill

> structured, verifiable pre-match intel. An [AnyCap](https://anycap.ai) agent skill

- The [`anycap`](https://anycap.ai) CLI, installed and authenticated (`anycap status`).

metadata:   version: 0.6.5   website: https://anycap.ai

version: 0.6.5   website: https://anycap.ai license: MIT

website: https://anycap.ai

- **Wikipedia is reliably crawlable** (`anycap crawl https://en.wikipedia.org/wiki/<Player>` returns full Markdown). Use it as the primary verification source.

| `anycap search --prompt "...JSON..."` | Structured profile / stats in one shot (5 cr) | | `anycap search --query "..." --no-crawl` | Find/disambiguate the right player page (1 cr) | | `anycap crawl https://en.wikipedia.org/wiki/<Player>` 

| `anycap search --query "..." --no-crawl` | Find/disambiguate the right player page (1 cr) | | `anycap crawl https://en.wikipedia.org/wiki/<Player>` | Authoritative verification source (1 cr) | | `anycap status` | Check auth before a batch

| `anycap crawl https://en.wikipedia.org/wiki/<Player>` | Authoritative verification source (1 cr) |

anycap crawl "https://en.wikipedia.org/wiki/<Player>" | jq -r '.data.markdown' > /tmp/<player>.md

"date_of_birth": "2003-06-29",   "current_club": "Real Madrid",   "_sources": ["grounding", "https://en.wikipedia.org/wiki/Jude_Bellingham"],

"current_club": "Real Madrid",   "_sources": ["grounding", "https://en.wikipedia.org/wiki/Jude_Bellingham"],   "_retrieved_at": "2026-06-18"

"_sources": ["grounding", "https://en.wikipedia.org/wiki/Jude_Bellingham"],