About LLM Wiki
llm-wiki is a toolkit for creating knowledge bases that are compiled and maintained by AI agents. Rather than being a standalone app, it ships as a plugin and skill set for agent environments such as Claude Code, OpenAI Codex and OpenCode, plus portable agents, and the resulting wikis are compatible with Obsidian.
The workflow covers capturing rough ideas, researching and shaping them, and promoting approved briefs into delivery projects. It includes parallel multi-agent research, thesis-driven investigation, collector catalogs, session memory, source ingestion, wiki compilation, audits, querying at different depths and artifact generation. Recent releases add lint exit gates, project knowledge exports, cross-runtime packaging and an optional framework for personal specialist review methods.
The project is written in Python and licensed under MIT, with a website and a changelog documenting frequent releases. It runs locally with your own agent subscription or API access. It suits developers and researchers who already work with AI coding agents and want a persistent, linked, reviewable wiki instead of scattered chat transcripts.
Key features
- Parallel multi-agent research
- Source ingestion and wiki compilation
- Querying at different depths
- Audits and lint gates for wiki quality
- Support for Claude Code, Codex, and OpenCode
- Obsidian-compatible output
Good fit for
- Building a research wiki with AI agents
- Keeping project knowledge across agent sessions
- Turning sources into linked Markdown notes
LLM Wiki: questions and answers
- What is LLM Wiki used for?
- LLM Wiki is a plugin that lets AI coding agents like Claude Code and Codex build and maintain Markdown knowledge bases through research, ingestion, compilation and querying. It is a good fit for building a research wiki with AI agents, keeping project knowledge across agent sessions and turning sources into linked Markdown notes.
- Is LLM Wiki open source?
- Yes. LLM Wiki is open source under the MIT licence. Its source code is on GitHub at nvk/llm-wiki and is written mainly in Python.
- Is LLM Wiki free?
- Yes. LLM Wiki is open source, so the software itself is free to use.
- What are some alternatives to LLM Wiki?
- Similar open-source tools in the AI Tools category include Obsidian Second Brain, pi-llm-wiki and Agno Scout. SaaS products in the same category include Agent One, Founderside Agents and MausBot.
- Is LLM Wiki actively maintained?
- Yes. The most recent commit to LLM Wiki was on 25 October 2026, and the latest release is v1.0.0, published on 24 October 2026. The project has 1.5k stars on GitHub, with 119 added in the last 30 days.
Open-source alternatives to LLM Wiki
See all
Obsidian Second Brain
AI Tools
Persistent memory for Claude Code and 6 other CLI agents, stored as plain markdown in your
MIT★ 5.3k
pi-llm-wiki
AI Tools
Self-maintaining, Obsidian-compatible knowledge base for pi — turn raw sources into an int
MIT★ 627
Agno Scout
AI Tools
Open Source Company Brain
Apache-2.0vs Glean★ 752
Kiro Crew
AI Tools
A persistent workspace for development work that self-improves and continues beyond one se
Apache-2.0vs Devin★ 4.9k
Skill Seekers
AI Tools
Convert documentation websites, GitHub repositories, and PDFs into Claude AI skills with a
MIT★ 15k
Golutra
AI Tools
Multi-agent AI orchestration platform for automation, workflows, and developer tools. Golu
OSS★ 3.9k
SaaS alternatives to LLM Wiki
See all
Agent One
AI Tools
No-code platform to build and host custom AI chatbots from instructions and uploaded documents
SaaS
Founderside Agents
AI Tools
AI co-founder with six specialized agents for research, finance, growth, sales, product and brand work
SaaS
MausBot
AI Tools
Open-source team of AI bots that browse, research, fill in forms and write for you on a computer
SaaS
Aldena
AI Tools
AI agent teams that build and maintain client applications, with an isolated workspace per client
SaaS
Ask it
AI Tools
Web app for AI-powered analysis of YouTube videos, sold through credit packs
SaaS
Askee
AI Tools
AI assistant to chat with the content of any website you are visiting
SaaS

