LLM-compiled knowledge bases for any AI agent. Parallel multi-agent research, thesis-driven investigation, source ingestion, wiki compilation, querying, and artifact generation.
LLM Wiki is a system that uses AI agents to research sources, compile knowledge bases, organize project briefs, and answer questions from the resulting wiki. It is used to turn rough ideas and investigations into structured, reusable knowledge for agents, including Claude Code, Codex, and OpenCode. The catalogue entries are commands, hooks, skills, instructions, and a plugin that implement its workflow.
This repository also configures its own agents. See what llm-wiki tells them →
Hook Claude Code
One of 6 in hooks.json
Runs when a session starts, executing llm_wiki_session.py via python3 with --harness and --if-enabled. From nvk/llm-wiki.
Hook Claude Code
One of 6 in hooks.json
Runs when you submit a prompt, before the agent sees it, executing llm_wiki_session.py via python3 with --harness and --if-enabled. From nvk/llm-wiki.
Hook Claude Code
One of 6 in hooks.json
Runs after a tool call finishes, executing llm_wiki_session.py via python3 with --harness and --if-enabled. From nvk/llm-wiki.
Hook Claude Code
One of 6 in hooks.json
Runs before the context is compacted, executing llm_wiki_session.py via python3 with --harness and --if-enabled. From nvk/llm-wiki.
Hook Claude Code
One of 6 in hooks.json
Runs after the context is compacted, executing llm_wiki_session.py via python3 with --harness and --if-enabled. From nvk/llm-wiki.
Hook Claude Code
One of 6 in hooks.json
Runs when the agent finishes a response, executing llm_wiki_session.py via python3 with --harness and --if-enabled. From nvk/llm-wiki.
At most 3 mods per repository are shown here, and a mod shipped inside a plugin is left to that plugin's page — the rest are on their repository pages: