# Ar9av/obsidian-wiki

Framework for AI agents to build and maintain a digital brain through Obsidian wiki

Repository: https://github.com/Ar9av/obsidian-wiki
Canonical: https://ross.abutalabs.com/products/obsidian-wiki
Language: Python
License: MIT
License Family: permissive
Topics: agent-skills, knowledge-base, llm-tools, obsidian, wiki, brain, obsidian-brain, knowledge-graph, memory
Last push: 2026-08-26T20:08:36+00:00

## Health v2 (maintenance only)
Score: 81/100 (v2, computed 2026-09-03T02:20:16.233290+00:00)
- activity 99, release rhythm 99, longevity 10
- inputs: {"age_days": 149, "days_push": 7, "days_rel": 8, "gap_med": 1, "n_releases_24m": 34}
- flags: young
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 3289, forks 324 (observed 2026-08-28T04:07:53.861874+00:00)

## What it is
A skill-based Python framework that lets AI coding agents (Claude Code, Cursor, Codex, etc.) build and maintain an Obsidian markdown knowledge base following Karpathy's LLM Wiki pattern. It ingests documents, chat history, and codebases into interconnected wiki pages with wikilink citations, giving agents persistent, queryable memory.

## Use cases
- build a second brain with my AI agent
- stop re-asking the LLM the same questions
- ingest PDFs and chat logs into an Obsidian vault
- give my coding agent persistent memory across projects
- query my knowledge base with citations
- distill what I learn in a repo into markdown notes
- mine my Claude chat history into a wiki

## When to choose
- you use Obsidian and an AI coding agent and want a durable, self-owned knowledge base
- you want markdown files with wikilink citations instead of re-running RAG or chat logs
- you want vendor-neutral skills that work across many agents with no runtime or API keys

## When to avoid
- you need a hosted knowledge base with a web UI or database backend
- you don't use Obsidian or any AI coding agent
- you need real-time collaborative editing rather than agent-maintained markdown

## Facets
- artifact type: framework
- maturity: active
- function: agent-framework, rag, documentation, markdown, llm-inference, developer-tools
- domain: artificial-intelligence, developer-tools
- platform: python, cli, cross-platform
- tags: obsidian, second-brain, knowledge-graph, agent-skills, llm-tools, digital-brain, wikilinks, memory, ai-agents, retrieval-augmented-generation, knowledge-base

## Member repositories
- Ar9av/obsidian-wiki (main) score 81

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:07:53.861874+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 2026-08-30T07:22:50.145400+00:00, confidence not recorded.
  - readme: https://github.com/Ar9av/obsidian-wiki (fetched 2026-08-28T04:07:53.861874+00:00, sha 46664d18438e)
  - registry_pypi: https://pypi.org/pypi/obsidian-wiki/json (fetched 2026-08-29T09:35:51.669879+00:00, sha b455c8d742cd)
- Data as of 2026-08-30T08:39:29.467469+00:00.