Codebase Memory is an open-source Model Context Protocol server that provides AI coding agents with a persistent local knowledge graph of a project's code, documentation, and infrastructure.
Follow Codebase Memory to get an email when its listing changes, such as new pricing or features. One digest a day at most, and you can unsubscribe anytime.
By indexing structural relationships, it allows agents to perform precise queries and reduce token usage by avoiding repeated file reads.
- 01
Persistent local knowledge graph of code, docs, and infrastructure
- 02
17 MCP tools for structural search, call tracing, and dependency analysis
- 03
Hybrid LSP-tier semantic resolution for accurate cross-file call mapping
- 04
Infrastructure integration for tracing Docker, Kubernetes, Terraform, and CI configurations
- 05
CBM Lens visual workspace for graph exploration and coverage diagnostics
Open Source
Released under the MIT license; the software and its components are free to use.
Best for
Developers building AI agent workflows who need to provide structural codebase context, reduce API token consumption during agentic tasks, and trace complex relationships across code and deployment infrastructure.
Not ideal for
Users requiring full source-level pattern matching, line-by-line grep operations, or exhaustive text searching that ignores structural boundaries.
An essential performance-focused tool for serious AI coding agents, providing highly efficient structural awareness that often outperforms standard file-reading approaches in cost and speed.
Version 0.10.0 introduced a shared coordination daemon for improved performance, tree-format tool output to significantly reduce token overhead, and a new coverage system with the check_index_coverage tool to identify graph blind spots.
As of
Is Codebase Memory free?+
Yes - Codebase Memory is Open Source. Released under the MIT license; the software and its components are free to use.
Is Codebase Memory open source?+
Yes - Codebase Memory is open source. Released under the MIT license; the software and its components are free to use.
Who is Codebase Memory best for?+
Developers building AI agent workflows who need to provide structural codebase context, reduce API token consumption during agentic tasks, and trace complex relationships across code and deployment infrastructure.
Who is Codebase Memory not ideal for?+
Users requiring full source-level pattern matching, line-by-line grep operations, or exhaustive text searching that ignores structural boundaries.
What are the best Codebase Memory alternatives?+
The closest Codebase Memory alternatives on ai.dosa.dev are Greptile, Fern, Remio - all listed under AI Codebase Knowledge & Generation.
Who makes Codebase Memory?+
Codebase Memory 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.