GBrain
Featuredby Garry Tan
Gives existing agent harnesses a self-hosted memory and skills layer with sourced facts, hybrid search, and cited synthesis, served over a CLI or local and remote MCP.
Skills
Memory Verbs Protocol
Exposes recall, remember, entity, synthesize, forget, context_pack, and delta as a versioned seven-verb MCP memory surface for agents.
Search And Synthesis
Runs hybrid keyword and vector retrieval with gbrain search, or composes a cited answer with gap analysis using gbrain think.
Remote MCP Publishing
Publishes the brain as an OAuth 2.1 HTTP MCP server on a Tailscale tailnet, or publicly with --funnel, using gbrain mcp expose.
Schema Packs
Detects, suggests, reviews, and activates page-type schema packs that fit your notes with the gbrain schema command family.
Related Agents
LightRAG
Builds a graph-based retrieval index over documents so agents can answer questions spanning many sources, served throug…
Cognee
Builds queryable memory for agents by turning documents and conversations into a knowledge graph plus vector store, sel…
Rowboat
Builds a backlinked knowledge graph from your email, meetings and Slack in a local desktop app, then lets agents query…
LanceDB
Stores and searches multimodal vectors in an embedded database built on the Lance columnar format, running in-process o…