llm-wiki
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 Claude Code plugin that enables AI agents to build, maintain, and query structured knowledge bases organized as topic-specific wikis. It orchestrates parallel multi-agent research workflows, compiles ingested sources into synthesized markdown articles with confidence scoring, and supports thesis-driven investigation with balanced evidence gathering. The plugin offers session memory, personal specialist review methods, and cross-compatible dual-linking that works in Obsidian, GitHub, and plain markdown viewers. Developers can research topics, collect catalogs, track inventory, generate artifacts, and query accumulated knowledge without leaving their AI coding environment.
Key Features
Use Cases
- 01Conduct deep research on technical topics with parallel agents searching from different angles and compiling findings into a structured wiki
- 02Evaluate specific claims or theses by gathering balanced evidence for and against, with anti-confirmation-bias mechanisms
- 03Build domain-specific knowledge bases (nutrition, Bitcoin, woodworking) that persist across chat sessions and can be queried later
- 04Collect and catalog examples, media, or tools with deduplication and provenance tracking
- 05Generate project handoffs with cross-topic evidence, privacy scanning, and deterministic sealing for team collaboration
- 06Track durable inventory items, datasets, and Ideas that evolve from rough seeds to approved delivery Projects
Related Plugins
View moreandrej-karpathy-skills
A single CLAUDE.md file to improve Claude Code behavior, derived from Andrej Karpathy's observations on LLM coding pitfalls.
claude-mem
Persistent Context Across Sessions for Every Agent – Captures everything your agent does during sessions, compresses it with AI, and injects relevant context back into future sessions. Works with Claude Code, OpenClaw, Codex, Gemini, Hermes, Copilot, OpenCode + More
Understand-Anything
Graphs that teach > graphs that impress. Turn any code into an interactive knowledge graph you can explore, search, and ask questions about. Works with Claude Code, Codex, Cursor, Copilot, Gemini CLI, and more.
rtk
CLI proxy that reduces LLM token consumption by 60-90% on common dev commands. Single Rust binary, zero dependencies
llm-wiki — FAQ
What is llm-wiki?+
llm-wiki is a Claude Code plugin (also available for Codex and OpenCode) that adds LLM-compiled knowledge bases to AI coding assistants. It enables parallel research, source ingestion, wiki compilation, querying, and artifact generation organized by topic.
How do I install llm-wiki in Claude Code?+
Run 'claude plugin install wiki@llm-wiki' in Claude Code, then restart. The plugin adds /wiki commands and can create topic wikis at ~/wiki/topics/ by default.
Which AI clients support llm-wiki?+
llm-wiki works natively in Claude Code as a plugin, in OpenAI Codex as a marketplace plugin, and in OpenCode or Pi as a skill file. A portable AGENTS.md file supports any LLM agent that can read instructions.
Do I need API keys or external services?+
No external API keys are required for basic functionality; the plugin uses the AI agent's built-in web search and file operations. Optional web search enhancements for OpenCode require setting OPENCODE_ENABLE_EXA=1.
Is llm-wiki free?+
Yes, llm-wiki is open source under the MIT License and free to use. You only pay for the underlying AI model usage (e.g., Claude API credits).
What are the different research modes?+
Standard mode uses 5 parallel agents, --deep uses 8 agents with historical and adjacent research, and --retardmax uses 10 agents with maximum speed and aggressive ingestion. Thesis mode focuses agents on evaluating a specific claim with balanced evidence.
How do I install llm-wiki?+
Open the source repository on GitHub and follow its README. llm-wiki is a plugin — MCP Agents Market links you directly to the official repo.
Is llm-wiki free?+
llm-wiki is an open-source project hosted on GitHub. Check the repository for its license and any usage requirements.