# SamurAIGPT/llm-wiki-agent

A personal knowledge base that builds and maintains itself. Drop in sources — Claude (or Codex/Gemini) reads them, extracts knowledge, and maintains a persistent interlinked wiki. Works with Claude Code, Codex, OpenCode, Gemini CLI. No API key needed.

Repository: https://github.com/SamurAIGPT/llm-wiki-agent
Canonical: https://ross.abutalabs.com/products/llm-wiki-agent
Language: Python
License: MIT
License Family: permissive
Topics: llm, knowledge-base, wiki, claude-code, knowledge-graph, obsidian, markdown, codex, rag, gemini, personal-knowledge-management, ai-agent, generative-ai, muapi, open-source, ai-tools, automation, note-taking, research, second-brain
Last push: 2026-08-24T04:07:01+00:00

## Health v2 (maintenance only)
Score: 74/100 (v2, computed 2026-09-02T17:46:02.011165+00:00)
- activity 99, release rhythm 35, longevity 87
- inputs: {"age_days": 1230, "days_push": 9, "days_rel": null, "gap_med": null, "n_releases_24m": 0}
- flags: no_releases
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 3458, forks 397 (observed 2026-08-28T04:08:05.568744+00:00)

## What it is
A coding-agent skill that turns source documents into a self-maintaining, interlinked markdown wiki. You drop files into a raw/ folder and instruct an agent (Claude Code, Codex, OpenCode, or Gemini CLI) to ingest them; the agent extracts entities, concepts, and syntheses into a persistent knowledge base with a knowledge graph visualization.

## Use cases
- build a personal knowledge base from research papers automatically
- turn pdfs and notes into an interlinked wiki without writing it myself
- synthesize answers across all my collected sources
- find contradictions and gaps across my reading
- visualize a knowledge graph of my research
- create a second brain that compounds as I add sources
- auto-generate entity and concept pages from documents

## When to choose
- you already use Claude Code, Codex, OpenCode, or Gemini CLI and want a self-building knowledge base
- you want markdown/Obsidian-compatible output you fully own
- you ingest many documents over time and want cross-references and synthesis maintained automatically
- you want a knowledge graph visualization of your sources

## When to avoid
- you need a standalone app with a GUI rather than an agent-driven workflow
- you don't use any coding agent and don't want to install one
- you need real-time collaborative editing or multi-user access
- you want fully deterministic, non-LLM extraction

## Facets
- artifact type: framework
- maturity: active
- function: rag, agent-framework, markdown, nlp, data-visualization
- domain: artificial-intelligence, large-language-models, developer-tools, documentation
- platform: python, cli, cross-platform
- tags: claude-code, obsidian, personal-knowledge-management, second-brain, knowledge-graph, wiki, note-taking, coding-agent-skill, llm-agent, knowledge-base, retrieval-augmented-generation, ai-agents

## Member repositories
- SamurAIGPT/llm-wiki-agent (main) score 74

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:08:05.568744+00:00.
- Health v2: computed from the inputs above; adoption is never an input.
- Inferred fields (summary, facets, guidance): AI-extracted, prompt v1, taxonomy v1, on 2026-08-29T18:36:57.050996+00:00, confidence not recorded.
  - readme: https://github.com/SamurAIGPT/llm-wiki-agent (fetched 2026-08-28T04:08:05.568744+00:00, sha bb991916ab84)
- Data as of 2026-08-30T08:39:29.467469+00:00.