Verified project record
DeusData/codebase-memory-mcp
A code intelligence MCP server that indexes local repositories into a persistent knowledge graph to reduce token consumption during structural code queries. It ships as a zero-dependency binary, operates entirely locally, and auto-configures supported AI coding agents.
Project overview
It full-indexes an average repository in milliseconds and the Linux kernel (28M LOC) in 3 minutes while reducing token usage by 99.2% compared to file-by-file grep exploration.
- Project type
- MCP · AI Coding · AI Search
- Use cases
- Knowledge Q&A · Coding & Development
- Deployment
- Refer to project documentation
- License
- MIT
Best for
- Developers and AI engineers using supported MCP clients who need structural code understanding without remote data transfer or paid external APIs.
- Teams looking to reduce token overhead when agents explore unfamiliar or large local codebases.
Key capabilities
- Indexes codebases into a persistent knowledge graph of functions, classes, call chains, HTTP routes, and cross-service links using tree-sitter AST analysis across 158 languages.
- Enhances tree-sitter parsing with lightweight C implementation of language type-resolution algorithms for supported languages.
- Provides vector search across the entire graph powered by bundled embeddings compiled into the binary, with 11-signal combined scoring.
- Provides an interactive 3D UI at localhost:9749 for exploring the codebase knowledge graph via an optional UI binary variant.
- Executes Cypher-like relationship traversal queries against the knowledge graph.
- Detects and configures MCP entries, durable instructions, skills, and lifecycle hooks for 43 supported client surfaces.
- Optionally indexes new projects automatically on first connection and uses a background watcher for ongoing git-based change detection.
- Allows every MCP tool to be invoked from the command line, supporting headless operations like indexing and querying.
Limitations and risks
- The tool does not include a built-in LLM and relies entirely on the connected MCP client for natural language processing.
- Context hooks are withheld for Cursor because session injection races and readonly blocks MCP.
- Child agents cannot use MCP for Cline, and automatic file hooks are withheld.
- The installer reads the codebase and writes to agent configuration files, requiring user trust in the installer script.
Getting started
- Run a one-line curl or PowerShell install script, execute the installer to auto-configure supported agents, and restart the agent.
Evidence and sources
- GitHub project description: High-performance code intelligence MCP server. Indexes codebases into a persistent knowledge graph — average repo in milliseconds. 158 languages, sub-ms queries, 99% fewer tokens.…
- README: The fastest and most efficient code intelligence engine for AI coding agents. Full-indexes an average repository in milliseconds, the Linux kernel (28M LOC, 75K files) in 3 minute…
- README: Plug and play — single static binary for macOS (arm64/amd64), Linux (arm64/amd64), and Windows (amd64). No Docker, no runtime dependencies, no API keys. Download → install → resta…
- README: **One-line install** (macOS / Linux): ```bash curl -fsSL https://raw.githubusercontent.com/DeusData/codebase-memory-mcp/main/install.sh | bash ``` With graph visualization UI: ```…
- README: The install command auto-detects installed coding agents and configures their documented MCP entries plus durable instructions, skills, and lifecycle hooks where supported.
AI Search
Find projects, verify facts, compare options, or turn a complex need into an actionable plan
Try a searchA click only fills the search box; you stay in control
Project Details
0