# LLM Wiki

> LLM-compiled knowledge bases for any AI agent. Parallel multi-agent research, thesis-driven investigation, source ingestion, wiki compilation, truth-seeking audits, querying, and artifact generation. Ships as a Claude Code plugin, an OpenAI Codex plugin, an OpenCode instruction file, or a portable AGENTS.md for any other LLM. Obsidian-compatible. MIT-licensed.

Author: nvk · Source: https://github.com/nvk/llm-wiki · License: MIT

## What it is

LLM Wiki is a set of slash commands and a knowledge model that turns any LLM coding agent into a research engine and an append-only, Markdown-native wiki. It runs parallel multi-agent research (5–10 agents from different angles), ingests URLs and files, compiles raw sources into synthesized articles with cross-references and confidence scores, answers questions against the compiled knowledge, and generates artifacts like reports, slides, study guides, and implementation plans.

It is inspired by Andrej Karpathy's "LLM wiki" concept (https://x.com/karpathy/status/2039805659525644595).

## Install

- Claude Code (native plugin): `claude plugin install wiki@llm-wiki` — best for full agentic research with 200K context.
- OpenAI Codex (marketplace plugin): `codex plugin marketplace add nvk/llm-wiki`, then enable in `/plugins` and invoke with `@wiki`. For a local checkout: `./scripts/bootstrap-codex-plugin.sh --scope user --verify`.
- OpenCode (instruction file): add `"instructions": ["path/to/llm-wiki/plugins/llm-wiki-opencode/skills/wiki-manager/SKILL.md"]` to `opencode.json`. Web search requires `OPENCODE_ENABLE_EXA=1`.
- Pi (instruction file): `pi --instructions path/to/llm-wiki/plugins/llm-wiki-opencode/skills/wiki-manager/SKILL.md` — best for local models (1K system prompt leaves room for wiki skill on 32K context).
- Any LLM agent (portable): `curl -sL https://raw.githubusercontent.com/nvk/llm-wiki/master/AGENTS.md > ~/your-project/AGENTS.md`

## Core commands

- `/wiki <natural language>` — fuzzy intent router (URLs → ingest, questions → query, etc.)
- `/wiki init <name>` — create a topic wiki at `~/wiki/topics/<name>/`
- `/wiki:research <topic>` — 5 parallel agents; `--plan` (multi-path), `--deep` (8), `--retardmax` (10), `--new-topic`, `--min-time 1h`
- `/wiki:research --mode thesis "<claim>"` — thesis-driven: evidence for + against → verdict
- `/wiki:ingest <url|file|text>` — add sources; `--inbox` processes the inbox
- `/wiki:compile` — raw sources → synthesized articles with cross-refs
- `/wiki:query <question>` — Q&A; `--quick`, `--deep`, `--list`, `--resume`
- `/wiki:audit` — umbrella trust audit across wiki, outputs, provenance, and fresh research
- `/wiki:librarian` — focused wiki maintenance: score articles for staleness and quality
- `/wiki:ll` — extract lessons learned from current session into wiki; `--dry-run`, `--rules`
- `/wiki:plan <goal>` — wiki-grounded implementation plan; `--format rfc|adr|spec`
- `/wiki:output <type>` — summary, report, study-guide, slides, timeline, glossary, comparison
- `/wiki:assess <path>` — repo vs wiki vs market gap analysis
- `/wiki:librarian` — score articles for staleness and quality; `--article <path>` for single article, `--resume` from checkpoint
- `/wiki:lint [--fix|--deep]` — structural and factual health checks
- `/wiki:retract` — remove a source and clean up downstream references
- `/wiki:project` — group outputs into projects with goals and manifests

## Trust model

`/wiki:librarian` keeps the `wiki/` layer in check. `/wiki:audit` is broader: it can trace outputs through `wiki/` and `raw/`, detect drift, inspect provenance, and do new research when the stored corpus is not enough to decide whether something is trustworthy.

## Architecture (one-liner)

Hub at `~/wiki/` is a lightweight registry (`wikis.json`, `_index.md`, `log.md`). All content lives in isolated topic sub-wikis at `~/wiki/topics/<name>/`, each with `inbox/`, `raw/`, `wiki/{concepts,topics,references}/`, `output/`, plus its own `.obsidian/` vault config.

## Key design properties

- Zero runtime dependencies — uses only the host agent's built-in tools.
- Dual-linking: `[[wikilink]] + [standard markdown link](path.md)` on every cross-reference — works in Obsidian, Claude Code, GitHub, and plain text editors.
- Raw is immutable — sources are never modified once ingested.
- Topic-isolated indexes — no cross-topic noise, but queries peek sibling wikis for overlap.
- Configurable hub — store on iCloud, Dropbox, or any custom path via `/wiki config hub-path`.
- Append-only activity log at `log.md` in every wiki.

## Docs

- Home: https://llm-wiki.net/
- Install: https://llm-wiki.net/#install
- Quick start: https://llm-wiki.net/#quickstart
- Commands reference: https://llm-wiki.net/#commands
- Guides: https://llm-wiki.net/#guides
- FAQ: https://llm-wiki.net/#faq
- README (canonical): https://github.com/nvk/llm-wiki#readme
- Releases: https://github.com/nvk/llm-wiki/releases
- AGENTS.md (portable): https://raw.githubusercontent.com/nvk/llm-wiki/master/AGENTS.md

## Related

- learntoprompt.org (https://learntoprompt.org) — sister site by the same author. Practical guides for AI coding agent setup (Claude Code, Codex, OpenCode, Pi, llama.cpp, ollama), sandboxing with bondage + nono, secret management with envchain-xtra, and prompting workflows. Includes a dedicated llm-wiki guide at https://learntoprompt.org/guides/llm-wiki.html.