garrytan/gbrain

Features

• MCP-Connected Frameworks - Provides a framework for AI agents that utilizes the Model Context Protocol to interact with structured knowledge bases.
• Model Context Protocol Integrations - Exposes internal tools and data to AI agents using the Model Context Protocol for direct interaction.
• Multi-Protocol Tool Exposures - Exposes internal functions and private data to AI agents via the Model Context Protocol.
• Knowledge Graph Extraction - Automatically generates a typed knowledge graph by extracting entity references and wikilinks from markdown files.
• Action Function Exposures - Exposes internal functions as discoverable tools for AI agents using a standardized Model Context Protocol server.
• RAG Knowledge Management - Implements a RAG system that synchronizes markdown files into a database for semantic retrieval and cited answer synthesis.
• Git-Based Content Management Systems - Utilizes a git repository as the primary record while syncing content to a database for high performance access.
• Hybrid Vector-Keyword Indexing - Combines semantic vector embeddings with keyword matching to locate relevant information within a knowledge base.
• Git-Synchronized - Synchronizes markdown files from a Git repository into a database for fast semantic retrieval.
• Knowledge Graph Builders - Automatically creates typed edges between pages by extracting entity references from markdown and wikilinks.
• Knowledge Graph Indexing Engines - Provides an engine that extracts entity references and wikilinks from markdown to build a typed knowledge graph.
• Hybrid Retrieval - Combines vector search and keyword matching to synthesize cited answers from a knowledge base.
• Git Repository Synchronizers - Uses a git repository as the primary record by syncing markdown files into a database.
• Markdown Database Syncs - Syncs markdown files from a git repository into a database for high-performance semantic retrieval.
• Hybrid Search Retrievers - Combines vector embeddings and keyword matching to retrieve relevant pages based on semantic and factual connectivity.
• Agentic Workflow Automation - Runs durable background jobs and tool loops to automate data collection and processing for AI agents.
• Automated Knowledge Synthesis Tools - Composes cited answers from retrieved data and performs gap analysis to identify missing information or contradictions.
• Durable Task Processors - Provides a persistent background job processor that executes tool loops and shell commands to prevent data loss.
• Personal Knowledge Management - Organizes personal information into a structured knowledge graph using markdown files and custom schemas.
• Filesystem-Based Schemas - Defines data types and taxonomies based on the physical structure of the underlying file system.
• Taxonomy Schema Packs - Organizes information using customizable schema packs that define page types and taxonomies based on filesystem structure.
• Database-Backed Deferred Queues - Implements a database-backed queue to execute persistent background jobs and shell loops with durability during failures.
• Background Job Schedulers - Executes persistent tool loops and shell jobs using a database queue to prevent data loss.

Star history