A headless wiki engine for agents. 24 MCP tools. One Rust binary. No LLM inside.
Build knowledge that compounds — not answers that evaporate.
A git-backed Markdown wiki — searchable, typed, graph-linked. Accessible from
the command line, from any MCP-compatible agent, or from any IDE via ACP.
Git-backed wiki engine with MCP server — build knowledge that compounds
Bintang
49
Tool
—
Uptime
—
The problem with RAG
Most AI knowledge tools retrieve and generate on every query. Each answer is
disposable — nothing is learned, nothing is kept. Ask the same question twice
and the LLM reasons from scratch.
llm-wiki implements a different pattern — the Dynamic Knowledge Repository
(DKR), introduced by Andrej Karpathy:
Process sources at ingest time, not query time. The LLM integrates each
source into the wiki — updating concept pages, creating source summaries,
flagging contradictions — and commits the result. Knowledge compounds with
every addition.
Traditional RAG
llm-wiki (DKR)
When knowledge is built
At query time
At ingest time
Cross-references
Ad hoc or missed
Pre-built, typed graph
Knowledge accumulation
Resets each query
Compounds over time
Audit trail
None
Git history per page
Data ownership
Provider systems
Your files, your git repo
How it works
The engine is pure infrastructure. It manages files, git, full-text search,
and graph structure. The LLM is always external — it calls the engine's tools
via MCP, reads pages, writes pages, and commits knowledge. Intelligence flows
through skills, not the binary.
LLM agent
│
├── wiki_list(format: "llms") → all pages grouped by type
├── wiki_search("mixture of experts") → ranked results + facets
├── wiki_content_read("concepts/moe") → full page + backlinks
├── wiki_graph(root: "concepts/moe") → typed graph in Mermaid/DOT
├── wiki_suggest("concepts/moe") → pages worth linking
├── wiki_content_new("concepts/new-page") → scaffold + returns local path
├── [write directly to path] → no MCP round-trip
└── wiki_ingest(path: "concepts/") → validate, index, commit
A wiki page is a plain Markdown file with typed frontmatter:
---
type: concept
title: Mixture of Experts
status: active
confidence: 0.9
tags: [routing, scaling, efficiency]
sources:
- sources/switch-transformer-2021
- sources/mixtral-2024
concepts:
- concepts/sparse-routing
- concepts/scaling-laws
---
Sparse routing of tokens to expert subnetworks...
The engine validates frontmatter against a JSON Schema, extracts typed graph
edges from sources and concepts, and indexes everything in tantivy. The
graph is live the moment a page is committed.
Works with Claude Code, VS Code (Copilot), Cursor, Windsurf, and any MCP-compatible client. For Zed (ACP over stdio), see the IDE integration guide.
IDE integration via ACP
In addition to MCP, llm-wiki speaks ACP (Agent Client Protocol) — a
session-oriented streaming protocol over stdio. Connect from Zed or any
ACP-compatible editor and trigger built-in workflows directly from the IDE
panel:
Prompt
What runs
llm-wiki:research <query>
Search + read top results, stream summaries
llm-wiki:lint [rules]
Run structural lint rules, stream findings
llm-wiki:graph [root]
Build and stream the concept graph
llm-wiki:ingest [path]
Ingest a path, stream the report
llm-wiki:use <slug>
Stream a page body directly into the IDE
llm-wiki:help
List all available workflows
Start with --acp alongside --http to give ACP exclusive stdio:
The engine exposes tools. Skills tell agents how to use them.
llm-wiki-skills is a
Claude Code plugin that ships ready-to-use workflows:
Skill
What it does
crystallize
Distil a session into durable wiki pages — decisions, findings, open questions
ingest
Process source files from inbox/ into synthesized, cross-referenced pages
research
Search the wiki and synthesize an answer from existing knowledge
lint
Structural audit — orphans, broken links, schema issues; uses summary: true first for large wikis
graph
Explore and interpret the concept graph
migrate
Clean up built-in schema copies left by the old copy-on-create model; runs wiki migrate --all
Skills are plain Markdown files — readable by the LLM, replaceable, forkable.
Write your own for your own workflows.
Architecture
llm-wiki-engine pure Rust binary — tools, git, index, graph
llm-wiki-skills Claude Code plugin — workflow skills (Markdown)
llm-wiki-hugo-cms Hugo scaffold — render the wiki as a website
The engine has no opinions about workflows, LLM providers, or interfaces.
Every LLM call happens outside the binary. Every workflow lives in a skill.
The separation means skills ship independently, the engine stays stable, and
nothing is coupled to a specific AI provider.
Technology
The file format is Markdown. The history store is git. Both predate llm-wiki
and will outlive it — your wiki is readable, diffable, and portable with zero
dependency on this tool. The engine itself is a single Rust binary with no
runtime, no database, and nothing to keep running between sessions.
Single Rust binary. No runtime, no database, no Docker.
Like many of you, I've been exploring agents, LLMs, and all that comes with it.
This project started after Andrej Karpathy's post — he put into words something
I was already practicing: plain Markdown files with structured frontmatter as a
practical knowledge base, for work and for the messier explorations.
The technical direction reflects years of SRE-minded practice: minimize
dependencies, use proven tools, keep the binary dumb. Written in Rust with
Claude as a pair programmer — a language I enjoy exploring more and more.
I have "a few" years of experience, but if you spot bad practices, call them
out — I'm doing this to learn together too. And if you're using it, personally
or at work, I'd love to hear about it :)
Belum ada daftar tool. Server remote mendapatkannya setelah pemeriksaan kesehatan pertama.
FAQ
Pertanyaan
Bagaimana cara menginstal Llm Wiki?
Salin konfigurasi stdio untuk Cursor, Claude Desktop, Claude Code, atau VS Code di halaman ini. Konfigurasi ini memakai instalasi dari penerbit, bukan proxy PlugMCP.
Apakah Llm Wiki memerlukan kunci API?
Tidak ada variabel lingkungan wajib yang tercantum di catatan ini.
Transport apa yang digunakan Llm Wiki?
Llm Wiki berjalan secara lokal melalui stdio.
Kapan Llm Wiki terakhir diperiksa?
Terakhir diperiksa 2026-10-27. Git-backed wiki engine with MCP server — build knowledge that compounds