Stars
Forks
Watchers
Developer links
Atomic
Atomic transforms collections of personal Markdown notes into an AI-augmented knowledge graph by breaking documents down into semantically linked conceptual units. Users capture thoughts, research excerpts, and web clippings as modular notes that the system automatically chunks, embeds, and categorizes with hierarchical tags. An interactive force-directed canvas maps out the entire knowledge base, positioning related ideas closer together based on embedding cosine similarity rather than manual folder hierarchies. Built-in vector search queries across text embeddings directly within SQLite, retrieving precise contextual snippets in response to natural language prompts. The automated wiki engine synthesizes disparate notes into comprehensive reference articles equipped with verifiable inline citations back to original source materials. Integrated conversational agents leverage retrieved knowledge context to answer research questions, surface contradictions across past entries, and draft structured daily briefings. External AI tools can read, search, and update stored knowledge through an embedded Model Context Protocol server endpoint. Running on a dedicated VPS on RepoCloud with guaranteed CPU, RAM, and SSD, full root SSH access, and a browser serial console. MIT licensed.
Benefits
- Automated Semantic Graph Linking
- Transforms raw Markdown documents into modular atomic units that automatically generate conceptual connections, semantic tags, and associative relationships without tedious manual linking or complex folder structuring.
- Dynamic Knowledge Synthesis Articles
- Synthesizes scattered research notes into cohesive wiki articles with verifiable inline citations, allowing researchers to track evolving arguments and cross-examine claims across their knowledge archive.
- Spatial Knowledge Canvas Exploration
- Visualizes conceptual clusters and intellectual affinities using a responsive force-directed canvas where spatial distance reflects true semantic similarity derived from vector embedding distances.
- Direct Agent Protocol Ingestion
- Exposes built-in Model Context Protocol server capabilities, allowing external AI agents like Claude Desktop to search, create, and retrieve knowledge atoms securely over HTTP endpoints.
Features
- Vector Database Search
- Performs sub-second natural language semantic retrieval over embedded document chunks using the lightweight sqlite-vec extension.
- Force-Directed Spatial Canvas
- Renders interactive 2D node graphs where physics simulation positions conceptually related notes near one another in space.
- Cited Wiki Synthesis
- Generates structured encyclopedia-style overview articles that cite specific atomic source notes with interactive footnotes, allowing researchers to trace synthesized knowledge back to original materials.
- Context-Aware Agentic Chat
- Executes Retrieval-Augmented Generation conversations that answer complex questions using verified knowledge base context, surfacing relevant excerpts and resolving factual contradictions across personal archives.
- Embedded MCP Server
- Enables standard Model Context Protocol integrations for external developer tools to query and mutate note databases programmatically.