# Codebase Memory — AI Coding Tool Review & Pricing

> 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. By indexing structural relationships, it allows agents to perform precise queries and reduce token usage by avoiding repeated file reads.

Source: https://ai.dosa.dev/tools/codebase-memory-mcp · Updated Nov 1, 2026 · Category: AI Codebase Knowledge & Generation · Published by dosa.dev

## At a glance

- **Tool**: Codebase Memory
- **Company**: DeusData
- **Category**: [AI Codebase Knowledge & Generation](https://ai.dosa.dev/category/codebase-ai)
- **Pricing model**: Open Source
- **Official website**: https://deusdata.github.io/codebase-memory-mcp/

## Key features

- Persistent local knowledge graph of code, docs, and infrastructure
- 17 MCP tools for structural search, call tracing, and dependency analysis
- Hybrid LSP-tier semantic resolution for accurate cross-file call mapping
- Infrastructure integration for tracing Docker, Kubernetes, Terraform, and CI configurations
- CBM Lens visual workspace for graph exploration and coverage diagnostics

## Pricing

**Model**: Open Source

Released under the MIT license; the software and its components are free to use.

## Who it is for

- **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.

## Verdict

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.

## Recent updates

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.

## Frequently asked questions

### 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.

## Top alternatives

- [Greptile](https://ai.dosa.dev/tools/greptile) (Freemium) — Engineering teams needing automated, context-aware code reviews that extend beyond simple syntax checks to include logic, security, and runtime validation.
- [Fern](https://ai.dosa.dev/tools/fern) (Freemium) — API-first engineering teams needing to synchronize SDK distribution with high-quality, searchable, and AI-optimized developer documentation.
- [Remio](https://ai.dosa.dev/tools/remio) (Freemium) — Knowledge workers such as consultants, researchers, product managers, and strategists who need to synthesize large volumes of internal documentation and research into finished work.
- [ContextStream](https://ai.dosa.dev/tools/contextstream) (Freemium) — Developers and teams who need AI agents to maintain consistent project context, understand architectural decisions, and avoid repeating the same mistakes across long-running projects.
- [OKF Agent Memory](https://ai.dosa.dev/tools/okf-agent-memory) (Open Source) — Software engineering teams and developers who require auditable, version-controlled persistent memory for AI agents without recurring API costs or infrastructure complexity.
- [Tseha](https://ai.dosa.dev/tools/tseha) (Freemium) — Engineering teams using MCP-compatible AI coding agents who need to enforce consistent coding standards, architectural rules, and design tokens across multiple repositories.
- Full alternatives guide: https://ai.dosa.dev/tools/codebase-memory-mcp/alternatives