# DeusData/codebase-memory-mcp

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. Single static binary, zero dependencies.

Repository: https://github.com/DeusData/codebase-memory-mcp
Canonical: https://ross.abutalabs.com/products/codebase-memory-mcp
Homepage: https://deusdata.github.io/codebase-memory-mcp/
Language: C
License: MIT
License Family: permissive
Topics: claude-code, code-analysis, code-intelligence, developer-tools, knowledge-graph, mcp, mcp-server, model-context-protocol, sqlite, tree-sitter, codex, cursor, windsurf, aider, gemini-cli, graph-visualization, kilocode, opencode, ast, cypher
Last push: 2026-08-27T00:36:19+00:00

## Health v2 (maintenance only)
Score: 81/100 (v2, computed 2026-09-03T02:20:16.233290+00:00)
- activity 99, release rhythm 98, longevity 13
- inputs: {"age_days": 190, "days_push": 7, "days_rel": 14, "gap_med": 0, "n_releases_24m": 44}
- flags: none
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 40771, forks 3305 (observed 2026-08-28T04:12:08.310218+00:00)

## What it is
A Model Context Protocol (MCP) server that indexes codebases into a persistent knowledge graph of functions, classes, call chains, and HTTP routes using tree-sitter AST parsing across 158 languages. It ships as a single static C binary with zero dependencies, letting AI coding agents answer structural code questions with far fewer tokens than file-by-file exploration.

## Use cases
- index a codebase so AI coding agents can query code structure
- reduce token usage when an LLM explores a large repository
- build a knowledge graph of functions, classes, and call chains
- give Claude Code or Cursor fast structural code search via MCP
- visualize and explore codebase dependencies as a graph
- answer questions like 'who calls this function' without reading files

## When to choose
- you use MCP-compatible AI coding agents and want faster, cheaper codebase exploration
- you need fast structural queries over very large repositories
- you want a dependency-free, locally-run code intelligence tool that keeps code private

## When to avoid
- you need deep semantic analysis beyond AST and hybrid LSP resolution
- you want a chatbot or embedded LLM - this is a structural backend only
- your tooling does not support the Model Context Protocol

## Facets
- artifact type: service
- maturity: active
- function: mcp, parser, search-engine, developer-tools, code-review
- domain: developer-tools, large-language-models, parsers, apis
- platform: windows, cli, self-hosted
- tags: mcp-server, tree-sitter, knowledge-graph, code-intelligence, static-analysis, sqlite, ast, llm-tools, single-binary, ai-agents, macos, linux

## Member repositories
- DeusData/codebase-memory-mcp (main) score 81

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:12:08.310218+00:00.
- Health v2: computed from the inputs above; adoption is never an input.
- Inferred fields (summary, facets, guidance): AI-extracted, prompt v1, taxonomy v1, on 2026-08-29T16:23:21.050959+00:00, confidence not recorded.
  - readme: https://github.com/DeusData/codebase-memory-mcp (fetched 2026-08-28T04:12:08.310218+00:00, sha 0c3d2aee7d06)
  - homepage: https://deusdata.github.io/codebase-memory-mcp/ (fetched 2026-08-29T07:46:24.014788+00:00, sha a85c396f4d8f)
- Data as of 2026-08-30T08:39:29.467469+00:00.