Codebase Memory
Codebase knowledge graph for AI agents — 159 languages, sub-ms queries, 99% fewer tokens.
Builds and maintains a persistent knowledge graph of codebase architecture, patterns, and conventions that survives AI session restarts and context window compaction. Stores structural information including component relationships, coding patterns, and project decisions in a local graph database for instant retrieval across sessions.
Source
Repository: https://github.com/deusdata/codebase-memory-mcp
Maintain Codebase Memory?
Let people know it's listed here — add the badge (live metrics, light/dark aware) or a plain link to your README or docs.
[](https://getagentictools.com/mcp/deusdata-codebase-memory-mcp?ref=badge) Related mcp
Toolbox for Databases Provides a secure, configurable interface for executing pre-defined queries against multiple database systems including PostgreSQL
DBX Query databases from AI agents using connections configured in the DBX database client.
Cipher Memory-powered agent framework that provides persistent memory capabilities across conversations and sessions using vector databas
Supabase Integrates with the Supabase platform for managing databases, projects, migrations, and storage.
Claude Flow Agent orchestration platform with multi-agent swarms, workflow coordination, and conversational AI systems
PaddleOCR Integrates with PaddleOCR and PP-StructureV3 to extract text from images and PDFs with confidence scores and bounding boxes, plus