LLM Wiki

Self-maintaining personal Wikipedia: an agent ingests your sources over MCP and compiles the wiki.

AdaptableOperable Business appWeb app Hybrid PythonTypeScript MCP server License: Apache-2.0

LLM Wiki stores documents, clippings, and notes, and exposes an MCP server through which Claude (or any MCP client) ingests sources, writes and lints wiki pages, and answers questions against the compiled wiki. A Next.js app and a Chrome extension are the human side. Apache-2.0, with a free hosted edition at llmwiki.app and a zero-config local mode.

Use it when

you read a lot and want a wiki of what you have read that Claude keeps up to date on a nightly routine
your team wants institutional memory compiled from documents rather than written by hand

Gotchas

Local mode is loopback-only by design; no LAN or remote binding
Remote self-hosting needs four external services before the first page appears
LibreOffice is required to extract Word and PowerPoint files
Young project (1.5k stars, 26 open issues); the nightly compile depends on a Claude Routine you schedule

Last activity Aug 9, 2026. Fit: adaptable 3, operable 3.

Editions

Free (local or self-hosted) · Free open source

Clonegit clone https://github.com/lucasastorian/llmwiki
Install./llmwiki open ~/research
ImageContainer

Hosted · Free open source

HostedOpen the hosted app

For agents: JSON · Markdown

Adaptable: what is yours to change

Make it yours

Config only26 things to edit

Local mode needs no config: ./llmwiki open <folder> indexes any folder of PDFs, Office files, and markdown and serves on loopback. Remote (self-hosted) mode is driven by .env.example: DATABASE_URL and SUPABASE_URL for storage and auth, S3_BUCKET with AWS keys for files, VOYAGE_API_KEY and TURBOPUFFER_API_KEY for embeddings and vector search, MCP_URL and NEXT_PUBLIC_MCP_URL to wire the MCP endpoint, CONVERTER_URL for Office conversion, QUIZ_GRADE_DAILY_LIMIT. The agent's operating instructions live in mcp/tools/guide.py.

Env vars: APP_URL DATABASE_URL SUPABASE_URL NEXT_PUBLIC_SUPABASE_URL NEXT_PUBLIC_SUPABASE_ANON_KEY S3_BUCKET AWS_ACCESS_KEY_ID AWS_SECRET_ACCESS_KEY VOYAGE_API_KEY TURBOPUFFER_API_KEY MISTRAL_API_KEY CLOUDFLARE_ACCOUNT_ID CLOUDFLARE_AI_GATEWAY_ID CLOUDFLARE_AUTH_TOKEN MCP_URL NEXT_PUBLIC_MCP_URL NEXT_PUBLIC_API_URL CONVERTER_URL CONVERTER_SECRET QUIZ_GRADE_DAILY_LIMIT LOCAL_EXTENSION_ORIGINS STAGE
Config files: .env docker-compose.yml mcp/railway.toml
Prompt files: mcp/tools/guide.py
Accounts you need: Supabase, S3, Voyage, and Turbopuffer (remote self-host only)Mistral (optional OCR)llmwiki.app account (hosted edition)

Source

github.com/lucasastorian/llmwiki
Apache-2.0 license
Last commit Aug 9, 2026
1,563 stars

Operable: what an agent can drive

Interface

NativeMCP serverpublished by the builderremote or local

How an agent can drive an Operable Listing, in five levels: native (built for the agent as the primary interface), official (the Builder ships an agent interface), wrapped (a third party wraps the software's API), config (an agent can only drive it by editing files), gui (screen control only). An interface is official only when it is published by the same organization that ships the software. GUI-level Listings are allowed and sorted last.

Docs: github.com/lucasastorian/llmwiki/tree/main/mcp
Tools: ingest read write search list lint quiz_lint references comments reply delete guide

Reach

Partial coverage. 8 of 10 jobs reachable through the stated interface.

Job	Through the interface	Evidence
Ingest documents and clippings into the raw store	Reachable	mcp/tools/ingest.py
Write and update wiki pages with citations	Reachable	mcp/tools/write.py; frontmatter and footnote helpers
Query the compiled wiki	Reachable	mcp/tools/search.py and read.py
Lint for inconsistencies, orphans, and missing links	Reachable	mcp/tools/lint.py and quiz_lint.py
Backlinks and references	Reachable	mcp/tools/references.py get_backlinks_summary
Read and reply to highlights and comments from the extension	Reachable	mcp/tools/comments.py and reply.py
Delete pages	Reachable	mcp/tools/delete.py
Quizzes over the wiki	Reachable	quiz_lint.py; QUIZ_GRADE_DAILY_LIMIT
Graph viewer and visualizations	Not reachable	web app feature; pages can embed Mermaid and SVG the agent writes
Clip pages from the browser	Not reachable	Chrome extension; the agent ingests through the ingest tool instead

Code stack

Languages: PythonTypeScript
Frameworks: Next.jsFastMCP
Package manager: pip, npm
Database: PostgreSQL (Supabase, remote mode)local files
Hosting target: localdockerrailway
Built: Unknown (recorded, never ranked)

Model stack

Providers: any MCP client (Claude.ai, Claude Code, Codex)Voyage (embeddings, remote mode)Mistral (OCR, optional)Cloudflare AI Gateway (remote mode)
Models: none
Keys you need: VOYAGE_API_KEY TURBOPUFFER_API_KEY MISTRAL_API_KEY CLOUDFLARE_AUTH_TOKEN
Prompts live in: mcp/tools/guide.py

Evidence and confidence

Field	Where it was seen	Confidence
formFactor	README: Next.js web app plus Python API and MCP server	85%
executionModel	the agent does the synthesis over MCP; OCR and quiz grading call models server-side	70%
operability	mcp/ directory in the repo; README 'built and maintained by AI' with MCP as the write path	85%
effort	.env.example names; README local quick start needs no config	85%
editions	llmwiki.app: 'Free & open source · Apache 2.0', 'Get started free'; no price list found	70%
active	pushedAt 2026-08-09	–
provenance	no authorship statement; no agent markers	30%
reach		85%

Open questions

Does llmwiki.app have paid tiers or limits?
Which tool names are registered (file names were read, decorators were not)

Sources

github.com/lucasastorian/llmwiki sourcing:notes-knowledge:github
llmwiki.app analysis