# lucasastorian/llmwiki

Open Source Implementation of Karpathy's LLM Wiki. Upload documents, connect your Claude account via MCP, and have it write your wiki !

Repository: https://github.com/lucasastorian/llmwiki
Canonical: https://ross.abutalabs.com/products/llmwiki
Homepage: https://llmwiki.app
Language: Python
License: Apache-2.0
License Family: permissive
Topics: agents, ai-agents, claude, karpathy, knowledge-base, llm, llm-wiki, mcp, mcp-server, rag, supabase
Last push: 2026-08-09T22:48:54+00:00

## Health v2 (maintenance only)
Score: 57/100 (v2, computed 2026-09-03T02:20:16.233290+00:00)
- activity 96, release rhythm 35, longevity 10
- inputs: {"age_days": 151, "days_push": 24, "days_rel": null, "gap_med": null, "n_releases_24m": 0}
- flags: no_releases, young
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 1533, forks 225 (observed 2026-08-28T04:04:59.541010+00:00)

## What it is
An open-source implementation of Andrej Karpathy's LLM Wiki concept: a self-maintaining personal knowledge base where an LLM (connected via MCP, e.g. Claude) autonomously synthesizes uploaded documents, notes, and web clippings into cross-linked wiki pages. It ships as a Next.js web app, Python API, MCP server, CLI, and Chrome extension for clipping sources.

## Use cases
- build a personal wikipedia from my reading that maintains itself
- have Claude write and update my knowledge base from documents I upload
- turn PDFs, notes, and web clippings into a cross-linked wiki
- give my LLM a persistent context layer of my own mental models
- clip webpages and PDFs with highlights and have AI synthesize them
- build an institutional knowledge base maintained by AI
- visualize how concepts in my notes relate as a graph

## When to choose
- you want an AI-maintained knowledge base rather than manually curated notes
- you already use Claude or another MCP-compatible app and want it to manage your wiki
- you want self-hosted control over your personal knowledge layer
- you value source preservation with highlights and citations back to originals

## When to avoid
- you want a traditional hand-edited wiki like MediaWiki or Obsidian
- you don't want to pay for or connect an LLM API/MCP client
- you need offline-only operation without any LLM involvement
- you need a lightweight note-taking app rather than an autonomous synthesis pipeline

## Facets
- artifact type: application
- maturity: active
- function: rag, agent-framework, mcp, llm-inference, search-engine, web-framework, cli
- domain: artificial-intelligence, large-language-models, documentation, self-hosted, developer-tools
- platform: python, self-hosted, cross-platform, browser-extension, cli
- tags: personal-wiki, knowledge-management, second-brain, claude, supabase, nextjs, autonomous-maintenance, note-taking, web-clipper, ai-agents, retrieval-augmented-generation, knowledge-base, nodejs, web-server

## Member repositories
- lucasastorian/llmwiki (main) score 57

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:04:59.541010+00:00.
- Health v2: computed from the inputs above; adoption is never an input.
- Inferred fields (summary, facets, guidance): AI-extracted, prompt v1, taxonomy v1, on 2026-08-30T04:31:15.502108+00:00, confidence not recorded.
  - readme: https://github.com/lucasastorian/llmwiki (fetched 2026-08-28T04:04:59.541010+00:00, sha 60f3722c0973)
  - homepage: https://llmwiki.app (fetched 2026-08-29T11:33:26.812088+00:00, sha 4f9f6c8d5c27)
- Data as of 2026-08-30T08:39:29.467469+00:00.