atomic
kenforthewin/atomic
Atomic is an AI-augmented personal knowledge base that transforms freeform markdown notes into a semantically-connected knowledge graph using Rust and SQLite. It operates as a Tauri desktop application, headless server, or Model Context Protocol (MCP) bridge with pluggable AI providers.
1.8k 127MITUpdated 2026-08-09
86
GreatOverview
This skill defines the architecture and operational structure of Atomic, a multi-transport knowledge management system. It leverages a clean separation of concerns via a framework-agnostic Rust core (`atomic-core`), thin wrappers for Tauri, REST, WebSockets, and MCP, and a React frontend. The application automatically chunks markdown notes, generates vector embeddings, builds semantic graphs, and supports agentic RAG chat and automated wiki synthesis.
Capabilities
- ▸Markdown chunking and vector embedding generation
- ▸Semantic similarity edge creation and graph visualization
- ▸Hierarchical tag auto-extraction using LLM structured outputs
- ▸Agentic RAG chat with knowledge base scoping
- ▸Incremental wiki article synthesis with inline citations
- ▸Pluggable AI providers (OpenRouter, Ollama)
Best for
Building and managing a personal knowledge base with semantic search and vector embeddings, Integrating markdown notes with local (Ollama) or cloud (OpenRouter) AI providers for automated tagging and wiki generation, Deploying a self-hosted knowledge server with REST, WebSocket, and MCP capabilities, Visualizing connected ideas in a spatial d3-force canvas
Works with
Claude CodeCursorGitHub CopilotChatGPT
Evoa Score breakdown= Σ (score × weight)
86Task usefulness20%100 → +20.0
実タスクにどれだけ役立つか（機能の豊富さ・用途の明確さ）。 — AIによるcapabilities/use-cases解析
Code quality15%90 → +13.5
実装・指示の品質。 — AIによるSKILL.md/README解析
Maintenance15%100 → +15.0
リポジトリがどれだけ活発に保守されているか。 — GitHub 最終push日時の新しさ
Documentation12%47 → +5.6
ドキュメントの充実度・分かりやすさ。 — README/独自要約の情報量
Security15%80 → +12.0
危険・不審な挙動が無いか。 — AIによるセキュリティレビュー
Originality10%85 → +8.5
ありふれたラッパーではない独自性。 — AIによる独自性判定
Popularity8%83 → +6.6
コミュニティの採用度。 — GitHub Stars/Forks（対数スケール）
Compatibility5%100 → +5.0
対応AIエージェントの広さ。 — AIによる対応エージェント判定
Weighted total86.3 / 100
ライセンス不明/制限あり（Red）のSkillは総合スコアに0.85倍の補正を適用します。 ランキングはこのScoreのみで決まり、広告で変わりません。 算出方法の詳細 →
Security considerations
Authentication utilizes named, revocable API tokens stored as SHA-256 hashes. Ensure proper access controls if exposing the headless server publicly.
Categories
Summary and analysis are original content generated by AI Skills Rank. The skill's source text is not reproduced here — view it on the linked repository.