Not in the top 1,000 by GitHub stars
charlie947/ai-second-brain
Build a living, searchable AI second brain from your ChatGPT, Claude, and research history - Karpathy-style. A Claude Code skill.
History
Review weekly changes to SKILL.md before updating. Dates mark the weeks in which we observed each version; checks apply to the recorded commits.
View weekly changes
SKILL.md
Week of Nov 2, 2026 · Line counts unavailable
Before Not checked yet → After Network or broad shell
First observation → 6b14a5282f3f
No earlier version was observed for comparison.
224GitHub stars
16stars in 7 days
1skill in this repository
1commit in 30 days
Heat
5.0- Star growth, last 7 daysNot available
- Star growth, last 24 hoursNot available
- Rank movement, last 7 daysNot available
- Commits, last 30 daysNot available
- Accounts asking about it through MCP, last 7 daysNot available
- Hot votes this weekNot available
Heat never changes the order by stars, and sponsorship never touches it. How heat works
Stars over time
30-day change not yet available: not enough history.
Individual skills in this repository
How it works
ai-second-brain
When your agent uses it
Walks the user through Charlie Hills's AI Second Brain + Karpathy Wiki setup from the MarTech AI newsletter. Use whenever the user mentions building an AI second brain, the Karpathy wiki, organising their ChatGPT/Claude exports in Obsidian, setting up a living wiki with Claude Code, connecting iMessage Channels, or installing the /today, /ideas, /create slash commands. Trigger on phrases like "set up my second brain", "build the Karpathy wiki", "follow Charlie's newsletter setup", "organise my AI conversations", "Obsidian + Claude Code setup", "I exported my ChatGPT data what now", or any reference to MarTech AI's Karpathy Wiki issue. Use even if the user only mentions one of the three steps (AI Brain, Karpathy Wiki, or Channels + slash commands).
What it loads into context
Frontmatter
178 tokensAlways available to the agent
SKILL.md
3,290 tokensWhen the skill is activated
Reference documents
1,778 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- How to use this skill
- Step 0: Pre-flight check
- Step 1: Build the AI Brain
- Step 2: Set up the Karpathy Wiki
- Step 3: Give the wiki a heartbeat (MCP + Channels + slash commands)
- Wrapping up
- Things that commonly go wrong
Scripts executed separately
render-social-preview.js
Files
.gitattributesasset359 bytes.gitignoreasset32 bytesCHANGELOG.mddoc598 bytesLICENSEasset1,070 bytesREADME.mddoc6,373 bytesSKILL.mdcore13,988 bytesSKILL.mdcore13,988 bytesSKILL.mdcore13,988 bytesSKILL.mdcore13,988 bytesSKILL.mdcore13,988 bytesSKILL.mdcore13,988 bytesSKILL.mdcore13,988 bytesai-second-brain.skillasset5,820 bytesrender-social-preview.jsruns936 bytessocial-preview.htmlasset6,201 bytessocial-preview.pngasset557,493 bytes
Read SKILL.md
# AI Second Brain Setup
This skill walks the user through the full setup from Charlie Hills's MarTech AI newsletter issue *"How to build a second brain with Obsidian and Claude Code"*. The process turns a folder of exports and raw research into a living wiki the user can talk to from their phone.
The setup has three steps. The user can do all three or pick one — confirm at the start which they want.
1. **AI Brain** — export ChatGPT and Claude history, organise it in Obsidian as tagged, linked markdown
2. **Karpathy Wiki** — set up `raw/` and `wiki/` folders with Karpathy's `CLAUDE.md` instruction file so Claude Code can compile a living wiki from raw research
3. **Living Wiki** — add MCP connectors (Gmail, NotebookLM, Granola), set up iMessage Channels, scaffold the `/today`, `/ideas`, `/create` slash commands
## How to use this skill
The user is most likely a non-technical newsletter reader. Many will be opening Terminal for the first time. Default to plain English, never assume CLI familiarity, and explain what each command does *before* running it.
Skills included
- ai-second-brain
Repository facts
- License
- MIT
- Created
- Apr 17, 2026
- Last pushed
- Oct 24, 2026
- Forks
- 44
- Open issues
- 0
- Project activity
- Active
Before you install
Network or broad shellAutomated signals, not a guarantee
Checked Nov 7, 2026
Not fully analyzed: some files were too long, unreadable or missing. This never lowers the level.
Show 6 notes
SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedSKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedSKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedSKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedSKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedSKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzed
- No broad tool permissions
- 1 dangerous shell commandin 1 file: README.md:104
- 22 network referencesin 3 files: README.md:5 social-preview.html:4 SKILL.md:33
- No hidden or obfuscated text
- No instruction overrides
- 1 executable scriptin 1 file: render-social-preview.js:1
- No access to secrets
- No requests to vote in Hot
Show all 24 signals by file
README.md
- Network accessline 5
On 3rd April 2026, [Andrej Karpathy](https://github.com/karpathy) published a 1,500-word gist describing how to build a personal wiki using a folder of markdown and an LLM. Within 48 hours the X thread about it hit **16 million views**. - Network accessline 7
This skill packages Karpathy's idea — plus an AI-history organiser by [Alex Freedman](https://instagram.com/alex2learn) and the slash-command workflow shared by [Greg Isenberg](https://www.youtube.com/@GregIsenberg) — into a single Claude C - Network accessline 9
Built for non-technical readers of [MarTech AI](https://charliehills.substack.com). - Network accessline 18
git clone https://github.com/charlie947/ai-second-brain.git ~/.claude/skills/ai-second-brain - Network accessline 72
- [Claude Code](https://docs.anthropic.com/claude-code) installed and working - Network accessline 73
- [Obsidian](https://obsidian.md) (free) - Dangerous shell operationline 104
rm -rf ~/.claude/skills/ai-second-brain - Network accessline 123
- **[Andrej Karpathy](https://github.com/karpathy)** — published the [original gist](https://gist.github.com/karpathy/442a6bf555914893e9891c11519de94f) on 3rd April 2026 describing how to maintain a living wiki with an LLM and a folder of m - Network accessline 124
- **Alex Freedman ([@alex2learn](https://instagram.com/alex2learn))** — wrote the AI Brain export-and-organise process this skill adapts in Step 1. - Network accessline 125
- **[Greg Isenberg](https://www.youtube.com/@GregIsenberg)** — published the YouTube breakdown of slash commands built on top of an Obsidian vault that Step 3c is based on. Three commands here, twelve in his video. - Network accessline 133
I'm Charlie Hills — founder of [Vislo](https://www.vislo.ai/), an AI design tool, and writer of [MarTech AI](https://charliehills.substack.com), a weekly Substack on what I'm actually building with AI as a creator with 200k+ LinkedIn follow - Network accessline 137
Reach me on [LinkedIn](https://linkedin.com/in/charlie-hills) or [Instagram](https://instagram.com/charliehills).
SKILL.md
- Network accessline 33
If Obsidian isn't installed, point them to https://obsidian.md and pause until it's done. If they haven't requested the ChatGPT export, kick that off **first** (instructions in Step 1) so it's processing in the background while they do the - Network accessline 100
mkdir -p ~/Desktop/Brain/raw ~/Desktop/Brain/wiki curl -L https://gist.githubusercontent.com/karpathy/442a6bf555914893e9891c11519de94f/raw -o ~/Desktop/Brain/CLAUDE.md - Network accessline 101
curl -L https://gist.githubusercontent.com/karpathy/442a6bf555914893e9891c11519de94f/raw -o ~/Desktop/Brain/CLAUDE.md - Network accessline 109
If the curl fails, fall back to: `WebFetch` the gist URL (`https://gist.github.com/karpathy/442a6bf555914893e9891c11519de94f`) and write the contents to `~/Desktop/Brain/CLAUDE.md` using the Write tool.
render-social-preview.js
- Executable scriptline 1
#!/usr/bin/env node
social-preview.html
- Network accessline 4
<meta charset="UTF-8"> <title>AI Second Brain — Social Preview</title> <link rel="preconnect" href="https://fonts.googleapis.com"> - Network accessline 5
<title>AI Second Brain — Social Preview</title> <link rel="preconnect" href="https://fonts.googleapis.com"> <link rel="preconnect" href="https://fonts.gstatic.com" crossorigin> - Network accessline 6
<link rel="preconnect" href="https://fonts.googleapis.com"> - Network accessline 7
<link rel="preconnect" href="https://fonts.gstatic.com" crossorigin> - Network accessline 8
<link href="https://fonts.googleapis.com/css2?family=Space+Grotesk:wght@400;500;600;700&display=swap" rel="stylesheet"> - Network accessline 150
<div class="right"> <svg class="graph" viewBox="0 0 540 640" xmlns="http://www.w3.org/2000/svg"> - Network accessline 151
<svg class="graph" viewBox="0 0 540 640" xmlns="http://www.w3.org/2000/svg">
How the signals fit together
Facts from a static read of the files at the pinned commit. They describe what the code does, not why.
Some files could not be read; the facts below still hold.
Signal confidence: 17 facts
- Network access in prose of documentationREADME.md:5Low confidence
- Network access in prose of documentationREADME.md:7Low confidence
- Network access in prose of documentationREADME.md:9Low confidence
- Network access in code of documentationREADME.md:18Low confidence
- Network access in prose of documentationREADME.md:72Low confidence
- Network access in prose of documentationREADME.md:73Low confidence
- Dangerous shell operation in code of documentationREADME.md:104Low confidence
- Network access in prose of documentationREADME.md:123Low confidence
- Network access in prose of documentationREADME.md:124Low confidence
- Network access in prose of documentationREADME.md:125Low confidence
- Network access in prose of documentationREADME.md:133Low confidence
- Network access in prose of documentationREADME.md:137Low confidence
- Network access in prose of the SKILL.mdSKILL.md:33Low confidence
- Network access in code of the SKILL.mdSKILL.md:100High confidence
- Network access in code of the SKILL.mdSKILL.md:101High confidence
- Network access in prose of the SKILL.mdSKILL.md:109Low confidence
- Executable script in code of a file that runsrender-social-preview.js:1High confidence
Works with
| Agent | Status | Evidence | Install to |
|---|---|---|---|
| Claude Code | Compatible | Standard SKILL.md SKILL.md | .claude/skills/<skill-name>/ |
| Codex | Compatible | Standard SKILL.md SKILL.md | .agents/skills/<skill-name>/ |
| Cursor | Compatible | Standard SKILL.md SKILL.md | .cursor/skills/<skill-name>/ |
| Gemini CLI | Compatible | Standard SKILL.md SKILL.md | .gemini/skills/<skill-name>/ |
| GitHub Copilot | Compatible | Standard SKILL.md SKILL.md | .github/skills/<skill-name>/ |
| OpenCode | Compatible | Standard SKILL.md SKILL.md | .opencode/skills/<skill-name>/ |
- Native The repository ships a manifest, folder or frontmatter field for this agent.
- Compatible A standard SKILL.md that this agent can read.
- Unknown No evidence either way.
Derived automatically from paths, manifests and frontmatter. Not tested on each agent.
