# kenforthewin/atomic

Self-hosted, semantically-connected personal knowledge base

Repository: https://github.com/kenforthewin/atomic
Canonical: https://ross.abutalabs.com/products/atomic
Homepage: https://atomicapp.ai
Language: Rust
License: MIT
License Family: permissive
Topics: knowledge-base
Last push: 2026-08-09T20:19:46+00:00

## Health v2 (maintenance only)
Score: 77/100 (v2, computed 2026-09-03T02:39:23.370411+00:00)
- activity 96, release rhythm 84, longevity 20
- inputs: {"age_days": 281, "days_push": 24, "days_rel": 24, "gap_med": 0, "n_releases_24m": 128}
- flags: none
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 1928, forks 140 (observed 2026-08-28T04:05:55.769357+00:00)

## What it is
Atomic is a self-hosted, local-first personal knowledge base that turns markdown notes into a semantically-connected, AI-augmented knowledge graph. It automatically chunks, embeds, tags, and links notes, and offers semantic search, wiki synthesis, agentic RAG chat, a spatial canvas, and MCP integration, runnable as a desktop app, self-hosted server, or hosted cloud.

## Use cases
- organize my markdown notes into a knowledge graph
- search my notes by meaning instead of keywords
- chat with my notes and get citations
- auto-generate wiki articles from my notes
- visualize how my ideas connect on a canvas
- automatically tag notes as I save them
- clip web pages and RSS articles into my knowledge base
- connect my notes to Claude or Cursor via MCP

## When to choose
- you want a self-hosted, local-first alternative to Notion/Obsidian-style tools with AI features
- you want semantic search and RAG chat over your own notes on your own hardware
- you prefer markdown-based, exportable data with no vendor lock-in
- you want scheduled research reports and auto-tagging over a personal corpus

## When to avoid
- you need a mature, battle-tested tool with a large plugin ecosystem
- you don't want to run an LLM/embedding provider or pay for AI usage
- you need real-time multi-user collaborative editing
- you only need simple plain-text notes without AI features

## Facets
- artifact type: application
- maturity: active
- function: rag, search-engine, nlp, machine-learning, mcp, chatbot, data-visualization, web-scraping
- domain: artificial-intelligence, developer-tools, self-hosted
- platform: self-hosted, cross-platform, browser-extension, rust
- tags: personal-knowledge-base, knowledge-graph, semantic-search, wiki-synthesis, auto-tagging, spatial-canvas, local-first, markdown-notes, rss-ingestion, agentic-chat, knowledge-base, retrieval-augmented-generation, natural-language-processing, docker, desktop, web-server, ios

## Member repositories
- kenforthewin/atomic (main) score 77

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:05:55.769357+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 2026-08-30T03:09:07.541915+00:00, confidence not recorded.
  - readme: https://github.com/kenforthewin/atomic (fetched 2026-08-28T04:05:55.769357+00:00, sha 576242f05bf5)
  - homepage: https://atomicapp.ai (fetched 2026-08-29T10:48:34.851964+00:00, sha 55e815df0620)
  - site_page: https://atomicapp.ai/getting-started (fetched 2026-08-29T10:48:34.861245+00:00, sha 8f29b9d3587b)
  - site_page: https://atomicapp.ai/getting-started/self-hosting (fetched 2026-08-29T10:48:34.863155+00:00, sha af49be9f0ba0)
  - site_page: https://atomicapp.ai/cloud (fetched 2026-08-29T10:48:34.864902+00:00, sha 4f4550a9e5bf)
- Data as of 2026-08-30T08:39:29.467469+00:00.