· portable llm wiki
Portable LLM Wiki

Your LLM doesn't
know you.

It will in 60 seconds.

A portable database of you. Sign in, paste a bio or import your notes, get a URL and a QR. Drop the URL into Cursor, Claude Code, or ChatGPT. Scan the QR onto a phone, a résumé, or any multimodal chat. Same artifact, two formats. Whoever opens it gets cited answers about you.

Sign in with GitHubor see it in action →
Live demo · the Avery Chen wiki
QR is real. Scan it with any phone, paste into any LLM, then ask “who am I?”
POST /wiki/chat/stream
Question
Answer
retrieving from the wiki…

How it works.

Step 1
Sign in with GitHub
Your GitHub login becomes your handle. No password, no email confirmation, no dashboard to set up.
Step 2
Paste your bio, resume, or profile URL
Drop in a paragraph about yourself, paste a resume, or hand us a LinkedIn / personal-site URL. A model digests it into a starter wiki.
Step 3
Share the URL or QR
Live at portablellm.wiki/<you>/llm. Paste the URL into Cursor, Claude Code, ChatGPT, or any system prompt. Hand someone the QR for a phone scan or image upload to ChatGPT, Claude, or Gemini. Either way they get cited answers about you.
Sign in with GitHub

Three operations.
That's the whole protocol.

see the spec →
Anything in.
Ingest
Slack thread, screenshot, voice memo, PDF, raw note. An LLM digests it, extracts entities, cross-references with [[wikilinks]], and never loses provenance back to the source.
POST /owner/ingest
Cited answers out.
Query
Natural-language Q&A grounded in your markdown. Graph-aware retrieval expands by wikilinks. Every answer carries the pages it cited, like the box above.
POST /wiki/chat/stream
Self-maintaining.
Lint
Four Puppetmaster agents run in parallel: contradictions, stale claims, missing pages, public-tier leaks. They surface issues for review. Never silently rewrite.
POST /owner/lint/swarm

Plug it into any LLM.

The wiki is vendor-neutral by design. Cursor, Claude, ChatGPT, Gemini, a local Llama: anything that can fetch a URL or speak MCP gets your context for free.

connection guide →
Recommended for everyone
Paste this URL into ChatGPT, Claude, or anywhere.
works on phones too. no install.

The URL returns a self-describing markdown briefing. The LLM reads it, learns the API, and answers questions about the wiki for the rest of the conversation. No plugin, no MCP setup, no auth dance.

https://portablellm.wiki/llm
preview what an LLM sees →·QR code for sharing·llms.txt
Power-user path: MCP
One config block for Cursor or Claude Desktop. Typed tool calls in every conversation, forever.
full instructions →
{
  "mcpServers": {
    "portable-llm-wiki": {
      "command": "npx",
      "args": ["-y", "portable-llm-wiki-mcp"],
      "env": { "WIKI_BASE_URL": "https://your-wiki.example.com" }
    }
  }
}

About this demo

hosted at portablellm.wiki/avery

This is the Avery Chen demo wiki, a fictional founding engineer at Strand Bio. Twenty-five pages across her entities, operating principles, career decisions (leaving grad school, joining Strand, postponing the Series A), saved deliberations, and source digests. Avery is here so the wiki has something real to talk about. When you sign in, you get your own.

open the Avery wiki →start your own →