A persistent memory system for AI coding agents that provides codebase context through FAISS vector storage and AST-based symbol indexing. Enables AI agents to maintain awareness of code structure and relationships for improved code generation.
CogniRepo is an MCP (Model Context Protocol) server that provides persistent memory and intelligent codebase context for AI coding agents. It uses FAISS (Facebook AI Similarity Search) vector stores to enable semantic code search and maintains an AST (Abstract Syntax Tree) reverse index for O(1) symbol lookup. This allows AI agents to efficiently retrieve relevant code context and maintain awareness of project structure during development tasks.
Installation requires Python 3.7+ and involves cloning the repository from GitHub, installing dependencies via pip, and configuring the MCP server endpoint. The tool integrates with AI platforms supporting the Model Context Protocol standard, including Claude and other compatible AI coding agents.
Monday.com MCP Server streamlines board management, item operations, and workflow automation for teams. I…
от NotionFlow
Sentry MCP Server provides comprehensive error tracking and performance monitoring, helping developers id…
от AnalyticsPro
Cloudflare MCP Server simplifies Cloudflare management by providing tools for DNS management, Workers dep…
от PricingBot