An open-source Model Context Protocol (MCP) server that indexes codebases into a persistent knowledge graph to provide AI coding agents with structural context.
It enables agents to perform complex queries with significantly fewer tokens by mapping functions, classes, call chains, and HTTP routes locally.
- 01
Persistent knowledge graph indexing with Hybrid LSP semantic type resolution
- 02
Extreme indexing speed (e.g., Linux kernel in 3 minutes) using a RAM-first pipeline
- 03
17 specialized MCP tools for structural search, call tracing, and architecture analysis
- 04
Built-in 3D graph visualization served locally at localhost:9749
- 05
Local-only semantic vector search using bundled Nomic embeddings
Open Source
Free and open-source under the MIT license with no paid tiers, cloud services, or API keys required.
Best for
Teams working in large monorepos or complex codebases (over 50 files) who need to reduce token usage and improve agentic understanding of project architecture.
Not ideal for
Small projects or single-file scripts where the setup and indexing overhead outweighs the benefits of structural graph analysis.
A highly efficient, local-first tool that is an essential utility for power users of AI coding agents, offering massive token savings and superior structural awareness at the cost of a slight learning curve for setup.
Version 0.11.0 (released 2026-09-15) follows the 0.10.x series, which introduced a shared coordination daemon for multi-agent workflows, tree-format tool output for ~99% token reduction, and a new coverage system (check_index_coverage) to identify graph blind spots.
As of
Is codebase-memory-mcp free?+
Yes - codebase-memory-mcp is Open Source. Free and open-source under the MIT license with no paid tiers, cloud services, or API keys required.
Is codebase-memory-mcp open source?+
Yes - codebase-memory-mcp is open source. Free and open-source under the MIT license with no paid tiers, cloud services, or API keys required.
Who is codebase-memory-mcp best for?+
Teams working in large monorepos or complex codebases (over 50 files) who need to reduce token usage and improve agentic understanding of project architecture.
Who is codebase-memory-mcp not ideal for?+
Small projects or single-file scripts where the setup and indexing overhead outweighs the benefits of structural graph analysis.
What are the best codebase-memory-mcp alternatives?+
The closest codebase-memory-mcp alternatives on ai.dosa.dev are Greptile, Fern, remio - all listed under AI Codebase Knowledge & Generation.
Who makes codebase-memory-mcp?+
codebase-memory-mcp is developed by DeusData. It is listed in the AI Codebase Knowledge & Generation category on ai.dosa.dev.
Favorite this tool to revisit it later, or Zap it to contribute to the public vote count.