llmwiki

LLMwiki

LLMwiki turns a team's raw research folder into a reviewed, queryable, self-improving Obsidian wiki. Headless-first. Cites, doesn't guess.

Language: English (this page) · 简体中文 — Guide: English · 简体中文 — Wiki: Home · Architecture · Rationale · FAQ

You are reading this because your team has already lost knowledge.

Not because nobody wrote it down. They did: papers, meeting notes, repo findings, screenshots, agent answers. The problem is worse: the knowledge has no state. No source. No reviewer. No promotion path. No way to tell a draft from team truth.

LLMwiki gives that mess a compiler pass:

capture -> compile -> ask -> file -> review -> promote

Put source material in raw/. Compile it into wiki/ summaries, concept pages, backlinks, and contradiction reports. Ask agents cited questions. File useful answers into 00-Inbox/AI-Output/. Promote only reviewed knowledge into decisions, architecture, and runbooks.

It is not an AI companion. It is a reviewed team memory compiler. Obsidian is the IDE, Git/Gitea review is the ledger, and MCP/CLI tools are the execution surface.

Inspired by Andrej Karpathy's LLM Wiki. Markdown is the source of truth; the compiler turns structure into a graph; MCP exposes it.

---

Quick start (10 seconds, Claude Code)

Inside any Claude Code session:

/plugin marketplace add 2233admin/obsidian-llm-wiki
/plugin install llmwiki@obsidian-llm-wiki

That's it. No clone, no build, no config file to edit. The plugin ships the MCP server (runs from the plugin directory, Node 20+), all /llmwiki:vault-* knowledge-work roles, and the thinking/research commands. Start Claude Code inside your vault and the server finds it automatically (cwd is the vault); otherwise set VAULT_MIND_VAULT_PATH or drop a vault-mind.yaml.

Other hosts (Codex / OpenCode / Gemini)

git clone --depth 1 https://github.com/2233admin/obsidian-llm-wiki.git
cd obsidian-llm-wiki && ./setup                      # --host codex | opencode | gemini

Windows: .\setup.ps1. The script copies the skill bundle into your host's skills directory and prints the .mcp.json snippet to paste into your agent config. docs/INSTALL.md has per-host paths and the manual recipe.

Recall: keyword out of the box, semantic optional

Natural-language recall works with zero setup. The first context.recall / query.answer against a fresh vault lazily indexes your notes (keyword: Postgres full-text + trigram, no embeddings, no daemon), so an agent can ask questions immediately — large vaults index in the background and sharpen as they finish.

Semantic (vector) recall is an optional upgrade: run Ollama with ollama pull bge-m3 (or point VAULT_MIND_EMBED_URL at any OpenAI-compatible embedding endpoint). Recall answers tell you when semantic is off and how to turn it on; keyword recall keeps working regardless.

---

See the loop (5 minutes)

You can verify the compiler loop before wiring any agent host. This demo is local, report-only, and the compiler dry-run uses stub extraction, so it does not need an API key.

python compiler/compile.py examples/collab-vault/research-compiler --tier haiku --dry-run
python scripts/knowledge_health.py --vault examples/collab-vault --json
python scripts/llmwiki_doctor.py --vault examples/collab-vault --json

Then inspect the before/after:

Step	Path
Raw source	examples/collab-vault/research-compiler/raw/team-memory-os.md
Compiled summary	examples/collab-vault/research-compiler/wiki/summaries/team-memory-os.md
Compiled concept	examples/collab-vault/research-compiler/wiki/concepts/team-memory-os.md
Filed AI output	examples/collab-vault/00-Inbox/AI-Output/codex/project-setup-proposal.md
Reviewed memory	examples/collab-vault/20-Decisions/2026-05-16-gitea-reviewed-vault.md

That is the product: raw material becomes cited, inspectable, reviewable team memory.

---

Works with

Any MCP-compatible host: