MCP-memento
★ 11
vs
letta
★ 25.2k
MCP-memento vs letta
MCP-memento: Memento-mcp is a local-first MCP server designed to provide AI agents with durable, high-signal memory for code repositories. It offers indexed code context, semantic relationships, fast search capabilities, and explicit notes that persist across sessions.; 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
MCP-mementoMemory & Context · ★ 11
Enhancing AI agent performance with rich, persistent code context.
lettaMemory & Context · ★ 25.2k
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
MCP-mementolettaCategory
Memory & Context
Memory & Context
Stars
★ 11
★ 25.2k
License
MIT
Apache-2.0
Install Command
git clone https://github.com/caiowilson/MCP-memento.git && cd MCP-memento && make build
npm install -g @letta-ai/letta-code
Updated
1mo ago
5d ago
Open Source
Yes
Yes
Tags
AI Agent Memory, Code Indexing, Semantic Search
Stateful AI, Agent Platform, Advanced Memory
03
Features
MCP-memento01Provides durable, high-signal memory for AI agents by indexing code context.
02Supports fast search and retrieval of code context based on semantic relationships.
03Stores explicit, repo-scoped notes that persist across sessions.
04Integrates with Claude Code and Claude Desktop as an MCP server.
05Offers a companion VS Code extension for installation and configuration.
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
MCP-memento↳Enhancing AI agent performance with rich, persistent code context.
↳Enabling AI-powered code search and understanding within a repository.
↳Managing and retrieving explicit notes or institutional knowledge related to specific codebases.
↳Integrating long-term memory capabilities into AI development workflows via MCP clients.
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
MCP-memento—
lettaMost PopularEssentialTrending
FAQ
FAQ
What is the difference between MCP-memento and letta?
Both MCP-memento and letta are in the Memory & Context category. MCP-memento has 11 stars, while letta has 25.2k stars.
Which is better, MCP-memento or letta?
The best choice depends on your use case. Choose MCP-memento if Enhancing AI agent performance with rich, persistent code context., and letta if Running AI agents locally in your terminal for coding and general tasks..
Is MCP-memento free or open source?
Yes, MCP-memento 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.
→