{"name":"Codebase-Memory-MCP: High-Performance Code Intelligence for AI Agents","description":"Codebase-Memory-MCP is an exceptionally fast and efficient code intelligence engine tailored for AI coding agents. It transforms your codebase into a persistent knowledge graph, indexing an average repository in milliseconds and supporting 158 languages. This tool significantly reduces token usage and integrates seamlessly with various agents as a single, dependency-free binary.","github":"https://github.com/DeusData/codebase-memory-mcp","url":"https://osrepos.com/repo/deusdata-codebase-memory-mcp","source":"osrepos.com","sourceDescription":"This repository profile is provided by osrepos.com, an open source repository discovery platform.","repositoryProfile":"https://osrepos.com/repo/deusdata-codebase-memory-mcp","generatedFor":"open source discovery and AI-assisted research","markdown":"https://osrepos.com/repo/deusdata-codebase-memory-mcp.md","json":"https://osrepos.com/repo/deusdata-codebase-memory-mcp.json","topics":["code-intelligence","AI agents","knowledge-graph","code-analysis","developer-tools","tree-sitter","C","mcp-server"],"keywords":["code-intelligence","AI agents","knowledge-graph","code-analysis","developer-tools","tree-sitter","C","mcp-server"],"stars":null,"summary":"Codebase-Memory-MCP is an exceptionally fast and efficient code intelligence engine tailored for AI coding agents. It transforms your codebase into a persistent knowledge graph, indexing an average repository in milliseconds and supporting 158 languages. This tool significantly reduces token usage and integrates seamlessly with various agents as a single, dependency-free binary.","content":"## Introduction\n\nCodebase-Memory-MCP is an exceptionally fast and efficient code intelligence engine tailored for AI coding agents. It transforms your codebase into a persistent knowledge graph, indexing an average repository in milliseconds and even the Linux kernel in just 3 minutes. Supporting 158 languages through Tree-sitter and Hybrid LSP, it enables sub-millisecond structural queries and drastically reduces token consumption for AI interactions. Packaged as a single, static binary with zero dependencies, it offers plug-and-play integration across 11 popular coding agents.\n\n## Installation\n\nGetting started with Codebase-Memory-MCP is straightforward.\n\nFor macOS / Linux, use the following one-line command:\n\nbash\ncurl -fsSL https://raw.githubusercontent.com/DeusData/codebase-memory-mcp/main/install.sh | bash\n\n\nTo include the built-in graph visualization UI, use:\n\nbash\ncurl -fsSL https://raw.githubusercontent.com/DeusData/codebase-memory-mcp/main/install.sh | bash -s -- --ui\n\n\nFor Windows (PowerShell), download and run the installer:\n\npowershell\nInvoke-WebRequest -Uri https://raw.githubusercontent.com/DeusData/codebase-memory-mcp/main/install.ps1 -OutFile install.ps1\n.\\install.ps1\n\n\nAfter installation, restart your coding agent. You can then instruct your agent with \"Index this project\" to begin. To keep your installation up to date, simply run:\n\nbash\ncodebase-memory-mcp update\n\n\n## Examples\n\nCodebase-Memory-MCP provides a powerful command-line interface (CLI) for direct interaction. Here are some examples:\n\n*   **Index a repository:**\n    bash\n    codebase-memory-mcp cli index_repository '{\"repo_path\": \"/path/to/your/repo\"}'\n    \n\n*   **Search for functions matching a pattern:**\n    bash\n    codebase-memory-mcp cli search_graph '{\"name_pattern\": \".*Handler.*\", \"label\": \"Function\"}'\n    \n\n*   **Trace inbound calls to a specific function:**\n    bash\n    codebase-memory-mcp cli trace_path '{\"function_name\": \"ProcessOrder\", \"direction\": \"inbound\"}'\n    \n\n*   **Execute a Cypher-like graph query:**\n    bash\n    codebase-memory-mcp cli query_graph '{\"query\": \"MATCH (f:Function) RETURN f.name LIMIT 5\"}'\n    \n\nAdditionally, if you installed the UI variant, you can explore your codebase's knowledge graph visually by running `codebase-memory-mcp --ui=true --port=9749` and opening [http://localhost:9749](http://localhost:9749){:target=\"_blank\"} in your browser.\n\n## Why Use Codebase-Memory-MCP\n\nCodebase-Memory-MCP stands out with several compelling features:\n\n*   **Extreme Indexing Speed**: Indexes the Linux kernel (28M LOC) in 3 minutes and an average repository in milliseconds, thanks to a RAM-first pipeline.\n*   **Broad Language Support with Hybrid LSP**: Parses 158 languages using vendored Tree-sitter grammars, enhanced by a lightweight C implementation of language type-resolution algorithms (Hybrid LSP) for 10+ languages, providing semantic accuracy without external language servers.\n*   **Exceptional Token Efficiency**: Achieves up to a 99.2% reduction in tokens for AI agents, replacing dozens of grep/read cycles with single graph queries.\n*   **Plug and Play Simplicity**: Delivered as a single static binary for macOS, Linux, and Windows, requiring zero runtime dependencies or API keys.\n*   **Seamless Multi-Agent Integration**: Automatically configures MCP entries, instruction files, and pre-tool hooks for 11 popular coding agents, including Claude Code, Codex CLI, and Gemini CLI.\n*   **Team-Shared Graph Artifacts**: Supports committing a compressed knowledge graph snapshot to your repository, allowing teammates to skip full re-indexing and accelerate onboarding.\n*   **Comprehensive Security**: Ensures trust with SLSA Level 3 cryptographic build provenance, VirusTotal scans on all binaries, Sigstore keyless signatures, and zero runtime dependencies.\n*   **Powerful MCP Tools**: Offers 14 specialized tools for architecture overview, semantic search, call graph analysis, dead code detection, cross-service linking, and Cypher-like queries.\n\n## Links\n\n*   **GitHub Repository**: [DeusData/codebase-memory-mcp](https://github.com/DeusData/codebase-memory-mcp){:target=\"_blank\"}\n*   **Research Paper (arXiv)**: [Codebase-Memory: Tree-Sitter-Based Knowledge Graphs for LLM Code Exploration via MCP](https://arxiv.org/abs/2603.27277){:target=\"_blank\"}","metrics":{"detailViews":4,"githubClicks":0},"dates":{"published":null,"modified":"2026-06-20T00:25:00.000Z"}}