DeusData / codebase-memory-mcp

2026-02-24 · Source: Github Trending: All languages · Field: Technology & Digital — Software Development & Engineering, Artificial Intelligence & Machine Learning · Depth: Advanced, extended

Summary

DeusData's "codebase-memory-mcp" is a high-performance code intelligence engine designed for AI coding agents, offering rapid codebase indexing and structural querying. It fully indexes large repositories like the Linux kernel (28M LOC, 75K files) in three minutes and answers structural queries in under one millisecond. The tool ships as a single static binary for macOS, Linux, and Windows, supporting 158 languages via tree-sitter and enhancing 9 languages with Hybrid LSP semantic type resolution. It generates a persistent knowledge graph of code entities, enabling 14 MCP tools for tasks like call graph tracing, dead code detection, and semantic search, reducing token consumption by 99.2% compared to file-by-file exploration. The project emphasizes security with SLSA Level 3 provenance and zero VirusTotal detections.

Key takeaway

For AI Engineers integrating code intelligence into their agent workflows, "codebase-memory-mcp" offers a compelling solution to enhance agent capabilities and reduce operational costs. You should consider deploying this tool to provide your agents with rapid, deep codebase understanding, enabling more accurate responses and significantly cutting token usage. Utilize its 14 MCP tools for tasks like call graph tracing or semantic search, and employ the team-shared graph artifact to streamline onboarding for new team members.

Key insights

"codebase-memory-mcp" provides fast, local, graph-based code intelligence for AI agents, significantly reducing token usage.

Principles

• Local processing enhances security and efficiency.
• Syntactic and semantic analysis improves code understanding.

Method

The tool uses a RAM-first pipeline with LZ4 compression and in-memory SQLite for indexing, followed by tree-sitter AST analysis and Hybrid LSP semantic type resolution to build a persistent knowledge graph.

In practice

• Install via one-line script for quick setup.
• Enable "auto_index" for automatic project indexing.
• Share "graph.db.zst" for team-wide graph reuse.

Topics

• Code Intelligence
• AI Coding Agents
• Knowledge Graphs
• Tree-sitter
• Hybrid LSP
• Code Analysis
• Semantic Search

Code references

• DeusData/codebase-memory-mcp
• DeusData/codebase-memory-mcp

Best for: AI Architect, AI Engineer, Machine Learning Engineer, Software Engineer

Related on AIssential

• can1357 / oh-my-pi — omp provides a deeply integrated, multi-tool coding agent that enhances developer productivity through intelligent automation and robust environmental awareness.
• Extending conversational memory in Kiro CLI using Amazon Bedrock AgentCore Memory — Integrating a custom MCP server with Amazon Bedrock AgentCore Memory extends Kiro CLI's conversational memory for context-aware AI agents.
• Indexing Your Codebase Into Live Documentation for AI — The `code-vector-graph` project creates live, searchable code documentation for AI by combining vector and graph databases.
• Agent memory resolved? — A git-like memory framework significantly enhances coding agent performance and context persistence across sessions.
• colbymchenry / codegraph — CodeGraph boosts AI code agent efficiency by providing a local, semantic knowledge graph of codebases.
• Formal Architecture Descriptors as Navigation Primitives for AI Coding Agents — Formal architecture descriptors significantly reduce AI coding agent navigation and behavioral variance.

Open in AIssential →

Editorial summary, takeaway, and curation by AIssential. Original article published by Github Trending: All languages.