letta
★ 25.2k
vs
daimon-memory
★ 14
letta vs daimon-memory
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.; daimon-memory: Daimon-memory is a self-hostable memory backend for AI agents, storing typed records in PostgreSQL with Qdrant as a semantic index. It provides fast, cheap, and reproducible hybrid keyword + vector search recall without an LLM in the recall path.
01
TL;DR
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.
daimon-memoryMemory & Context · ★ 14
Providing persistent, shared memory for AI agents across different tools.
02
Side-by-Side Comparison
Field
lettadaimon-memoryCategory
Memory & Context
Memory & Context
Stars
★ 25.2k
★ 14
License
Apache-2.0
MIT
Install Command
npm install -g @letta-ai/letta-code
git clone https://github.com/wakbijok/daimon-memory && cd daimon-memory && ./install.sh --yes
Updated
5d ago
2mo ago
Open Source
Yes
Yes
Tags
Stateful AI, Agent Platform, Advanced Memory
AI Agents, Memory, Persistence
03
Features
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
daimon-memory01Persistent and typed memory for AI agents
02Deterministic and LLM-free recall using hybrid keyword + vector search
03Self-hostable backend using PostgreSQL for canonical storage and Qdrant for semantic indexing
04Single-subject memory space shared across multiple AI tools
04
Use Cases
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.
daimon-memory↳Providing persistent, shared memory for AI agents across different tools.
↳Maintaining consistent personas and operating disciplines for AI agents.
↳Storing and retrieving AI agent decisions, lessons, incidents, and reminders.
↳Integrating memory capabilities with existing AI agent platforms like Claude Code, Codex, and Hermes.
05
Best For
lettaMost PopularEssentialTrending
daimon-memory—
FAQ
FAQ
What is the difference between letta and daimon-memory?
Both letta and daimon-memory are in the Memory & Context category. letta has 25.2k stars, while daimon-memory has 14 stars.
Which is better, letta or daimon-memory?
The best choice depends on your use case. Choose letta if Running AI agents locally in your terminal for coding and general tasks., and daimon-memory if Providing persistent, shared memory for AI agents across different tools..
Is letta free or open source?
Yes, letta is open source on GitHub (Apache-2.0).
Is daimon-memory free or open source?
Yes, daimon-memory is open source on GitHub (MIT).
Cloud Infrastructure
AdDeploy on DigitalOcean
Host your MCP servers, Docker containers, and AI agents with $200 free credit over 60 days.
→