autopedia

Personal knowledge wiki maintained by your AI tool via MCP.

Your AI tool (Claude Code, Cursor, etc.) maintains a Karpathy-style wiki through MCP. No separate LLM client. No API keys. Your existing AI tool IS the brain.

Requires Node.js 20+

Get started

1. Install

npm install -g autopedia

2. Initialize

autopedia init

Creates ~/.autopedia/ with:

wiki/           ← synthesized knowledge (AI-maintained)
sources/        ← raw inputs (URLs, text notes, files)
ops/            ← audit trail (log, metrics, queue)
schema/         ← your profile and rules

3. Connect to your AI tool

Add to your AI tool's MCP config (one-time setup):

Claude Code (~/.claude.json):

{
  "mcpServers": {
    "autopedia": {
      "command": "autopedia",
      "args": ["serve"]
    }
  }
}

Cursor (.cursor/mcp.json):

{
  "mcpServers": {
    "autopedia": {
      "command": "autopedia",
      "args": ["serve"]
    }
  }
}

4. Verify

autopedia status
# Should show: Wiki pages: 1, Queued: 0

5. Start using it

Start a new Claude Code or Cursor session. On first connection, autopedia interviews you (~30 seconds) to personalize your wiki. After that, it's silent until you need it.

Add stuff anytime (from any terminal):

autopedia add "GPU prices dropped 20% this quarter"
autopedia add https://example.com/article
autopedia add ~/research/notes.md

Process when ready (tell your AI tool):

You: "sync my wiki"
AI:  Processing 1/3: gpu-pricing-note → created gpu-pricing.md
     Processing 2/3: example.com/article → updated market-trends.md
     Processing 3/3: notes.md → created research-notes.md
     Done. Created 2 pages, updated 1.

Ask questions anytime:

You: "What do I know about GPU pricing?"
AI:  → answers from YOUR research, not training data

autopedia never hijacks your conversation. It's a quiet knowledge layer — there when you need it, invisible when you don't.

CLI Commands

Command	What it does
autopedia init	Create ~/.autopedia/ directory structure
autopedia add <source>	Queue a URL, text note, file, folder, or repo
autopedia add --repo <path>	Scan a codebase and create an architectural bundle
autopedia lint	Check wiki health: orphans, stale pages, broken links
autopedia remove <name>	Remove a wiki page (or source with -s)
autopedia scan	Detect files added outside autopedia (Obsidian, IDE) and queue them
autopedia status	Show wiki stats and unprocessed sources
autopedia search <query>	Search wiki pages from the terminal
autopedia view	Browse your wiki in a local dashboard
autopedia export	Export wiki as a single markdown file
autopedia serve	Start MCP server (used by AI tools, not run manually)

Braindump from anywhere

autopedia add "GPU prices dropped 20% this quarter"     # text note
autopedia add https://example.com/article                # URL
autopedia add ~/research/gpu-report.pdf                  # file
autopedia add ~/research/                                # whole folder
autopedia add ~/code/my-project/                         # auto-detect repo (.git/)
autopedia add --repo ~/code/my-project/                  # explicit repo mode

Everything is saved instantly. Tell your AI tool "sync" to process.

Dashboard

Run autopedia view to open a local dashboard.

• Wiki index with rendered markdown and clickable [[wikilinks]]
• Knowledge graph — force-directed visualization of page connections
• Backlinks — each page shows what links to it
• Source browser with content-derived titles
• Status — page count, queue, untracked files
• Light/dark theme with Newsreader + DM Sans typography

Obsidian integration

Open ~/.autopedia/ as an Obsidian vault. Wikilinks, graph view, and backlinks work out of the box.

Drag-and-drop workflow: Drop files into the vault via Obsidian, then run autopedia scan to queue them. Tell your AI tool "sync" to process.

How it works

Implements Karpathy's three wiki operations:

1. INGEST — Fetch URLs, save notes, synthesize into wiki pages
2. QUERY — Search and read, answer grounded in your research
3. LINT — Find orphans, stale content, contradictions, fix them

MCP Tools (9)

Tool	Operation	Purpose
add_source	INGEST	Fetch URL or save text (queue or ingest mode)
apply_wiki_ops	INGEST	Create/update wiki pages
read_source	QUERY	Read a saved source
search	QUERY	Search wiki pages
read_page	QUERY	Read a specific page
get_status	STATUS	Page count, queue, untracked files
lint	LINT	Orphans, stale pages, broken links, low crossrefs
question_assumptions	LINT	Challenge high-confidence claims
complete_onboarding	ONBOARDING	Write identity + interests

MCP Resources (3)

Resource	What
autopedia://prompt	System prompt (auto-updates on upgrade)
autopedia://identity	Your profile
autopedia://interests	What you care about

Security

• Sacred boundary: Server writes only to wiki/, ops/, sources/agent/. User content is never modified.
• Path traversal: path.resolve() + startsWith() + symlink chain validation
• SSRF protection: Blocks localhost, private IPs, IPv6, metadata endpoints, redirect bypasses
• XSS prevention: All rendered content HTML-escaped, link text escaped, graph JSON escaped
• No API keys: Server makes zero LLM calls — your AI tool does all the thinking

Architecture

src/wiki.ts      — File I/O, boundary enforcement, wikilink graph, lint, scan
src/mcp.ts       — 9 MCP tools + 3 resources
src/cli.ts       — CLI: init, add, lint, scan, serve, status, view, search, export, remove
                   Repo scanner: smart file discovery, role scoring, bundle formatting
src/dashboard.ts — Server-rendered HTML dashboard (graph, backlinks, source titles)
schema/prompt.md — System prompt (served via MCP, auto-updates on upgrade)

7 runtime dependencies. No LLM SDK. No database. No Express.

Development

git clone https://github.com/devp1/autopedia
cd autopedia
npm install
npm run build
npm test          # 259 tests
npm run typecheck
npm run lint

License

MIT