engram-mcp
★ 18
vs
letta
★ 25.2k
engram-mcp vs letta
engram-mcp: Engram is an MCP server that provides persistent, Git-aware session memory for coding agents, allowing structured handoffs between sessions and branches. It helps agents retain context, decisions, and tasks, backed by local SQLite and ONNX embeddings without cloud dependencies.; 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
engram-mcpMemory & Context · ★ 18
Developers can capture session state and structured notes (decisions, todos, blockers) at the end of a coding session for seamless handover.
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
engram-mcplettaCategory
Memory & Context
Memory & Context
Stars
★ 18
★ 25.2k
License
Apache-2.0
Apache-2.0
Install Command
cargo install engram_mcp
npm install -g @letta-ai/letta-code
Updated
5d ago
5d ago
Open Source
Yes
Yes
Tags
Git-aware Memory, Coding Agent Tools, Context Management
Stateful AI, Agent Platform, Advanced Memory
03
Features
engram-mcp01Provides Git-aware session memory that scopes context to specific git branches, preventing information leakage.
02Enables structured session handoffs to capture summaries, decisions, todos, blockers, and mental models for continuity.
03Offers local-first persistent storage using SQLite and ONNX embeddings, ensuring no cloud or LLM calls are needed for storage.
04Features advanced memory retrieval with hybrid scoring (cosine, recency, importance), hierarchical clustering, and branch-aware queries.
05Includes automated memory management capabilities such as decay, semantic deduplication, and auto-pruning of low-relevance memories.
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
engram-mcp↳Developers can capture session state and structured notes (decisions, todos, blockers) at the end of a coding session for seamless handover.
↳Automatically retrieve relevant context and prior session details when resuming work on the same or a different Git branch.
↳LLM agents can proactively load relevant memories at the start of a conversation, building context from recent Git activity.
↳Passively capture coding decisions and session summaries into memory through integrated hooks without explicit tool calls.
↳Maintain a centralized, searchable, and structured memory of project-specific decisions, recurring patterns, and past debug solutions.
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
engram-mcp—
lettaMost PopularEssentialTrending
FAQ
FAQ
What is the difference between engram-mcp and letta?
Both engram-mcp and letta are in the Memory & Context category. engram-mcp has 18 stars, while letta has 25.2k stars.
Which is better, engram-mcp or letta?
The best choice depends on your use case. Choose engram-mcp if Developers can capture session state and structured notes (decisions, todos, blockers) at the end of a coding session for seamless handover., and letta if Running AI agents locally in your terminal for coding and general tasks..
Is engram-mcp free or open source?
Yes, engram-mcp is open source on GitHub (Apache-2.0).
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.
→