codebase-memory-mcp
★ 47.7k
vs
letta
★ 25.3k
codebase-memory-mcp vs letta
codebase-memory-mcp: codebase-memory-mcp is a structural analysis backend that indexes codebases into a persistent knowledge graph, drastically reducing token usage for code exploration by providing precise structural results. It integrates with AI assistants like Claude Code, offering advanced capabilities such as call graph tracing, architecture overviews, and dead code detection.; letta: Letta is a powerful platform for building stateful AI agents equipped with advanced memory, enabling them to learn and self-improve over time. It provides both a command-line interface for local agent execution and a comprehensive API with Python and TypeScript SDKs for seamless integration into applications.
01
TL;DR
codebase-memory-mcpMemory & Context · ★ 47.7k
When to choose:
- Your agent burns tokens searching a medium or large codebase: one graph query replaces many grep and read steps, according to the README.
- You want everything local: a single static binary with no runtime dependencies or API keys.
- You work in many languages and with several coding agents, which the installer configures automatically.
When to skip:
- You do not want an installer to edit your agents' config files and add hooks; the README offers --skip-config to install only the binary.
- You need project decisions and conventions rather than code structure; a scaffold such as mex is closer.
- You are cautious about unsigned binaries: some antivirus engines have flagged the release, which the project documents as a false positive.
lettaMemory & Context · ★ 25.3k
When to choose:
- You want a long-lived agent that remembers past work and rewrites its own memory and context over time.
- You want one agent reachable from CLI, desktop, browser, mobile and messaging apps, with subagents, schedules and hooks.
- You want memory you can inspect: the README says context is tracked in git and can sync to your own repository.
When to skip:
- You only need to add memory to an agent you already use through MCP; a small MCP memory server is a lighter fit.
- You rely on older Letta tutorials or the V1 API server: the project restructured, and the V1 server is retired.
- You want everything to work without signing in: Letta Cloud is the default backend and some features need it.
02
Side-by-Side Comparison
Field
codebase-memory-mcplettaCategory
Memory & Context
Memory & Context
Stars
★ 47.7k
★ 25.3k
License
MIT
Apache-2.0
Install Command
curl -fsSL https://raw.githubusercontent.com/DeusData/codebase-memory-mcp/main/install.sh | bash
npm install -g @letta-ai/letta-code
Updated
1d ago
1w ago
Open Source
Yes
Yes
Tags
knowledge-graph, codebase-analysis, AI-assistant-tools
Stateful AI, Agent Platform, Advanced Memory
03
Features
codebase-memory-mcp01Indexes a codebase into a persistent knowledge graph using tree-sitter, with semantic type resolution for several major languages
02Supports 150+ languages with grammars compiled into a single static binary
0317 MCP tools: search, call tracing, architecture overview, impact analysis, dead code detection, Cypher queries and more
04Indexes infrastructure-as-code such as Dockerfiles and Kubernetes manifests
05Built-in 3D graph visualisation served locally
letta01Build stateful AI agents with advanced memory
02Agents capable of learning and self-improvement over time
03CLI tool for running agents locally in your terminal
04Comprehensive API for integrating agents into applications
05Support for skills and subagents; fully model-agnostic
04
Use Cases
codebase-memory-mcp↳Code exploration and understanding: Quickly understand codebase architecture, find functions, and trace call paths without high token costs.
↳Impact analysis and refactoring: Map git diffs to affected symbols, detect dead code, and analyze function fan-out to aid refactoring efforts.
↳AI assistant integration: Enhance AI assistants like Claude Code with precise structural queries for more effective code-related questions.
↳Architecture Decision Records management: Store, update, and retrieve architectural decisions directly within the codebase context.
↳Automated scripting and CI/CD: Utilize CLI mode for single-shot graph operations in scripts or CI/CD pipelines.
letta↳Running AI agents locally in your terminal for coding and general tasks.
↳Integrating stateful AI agents into custom applications using the API and SDKs.
↳Developing self-improving AI systems that adapt and learn continually.
05
Best For
codebase-memory-mcpMost Popular
lettaMost PopularEssentialTrending
FAQ
FAQ
What is the difference between codebase-memory-mcp and letta?
Both codebase-memory-mcp and letta are in the Memory & Context category. codebase-memory-mcp has 47.7k stars, while letta has 25.3k stars.
Which is better, codebase-memory-mcp or letta?
The best choice depends on your use case. Choose codebase-memory-mcp if Code exploration and understanding: Quickly understand codebase architecture, find functions, and trace call paths without high token costs., and letta if Running AI agents locally in your terminal for coding and general tasks..
Is codebase-memory-mcp free or open source?
Yes, codebase-memory-mcp is open source on GitHub (MIT).
Is letta free or open source?
Yes, letta is open source on GitHub (Apache-2.0).
Cloud Infrastructure
AdDeploy on DigitalOcean
Host your MCP servers, Docker containers, and AI agents with $200 free credit over 60 days.
→