8 Best Letta Alternatives in 2026 (Open Source)
Letta — Letta is the platform for building stateful agents: AI with advanced memory that can learn and self-improve over time.. Purpose-built memory architecture that enables agents to self-improve over time — vs generic agent frameworks that only have short-term chat history
These 8 open-source tools do the same job. They are ordered by how closely they match Letta, with live GitHub data so you can see which projects are actively maintained.
| Tool | GitHub stars | Stars / 30d | Last commit |
|---|---|---|---|
| Letta(original) | 25.0k | +515 | 2026-09-10 |
| Letta | 25.0k | +515 | 2026-09-10 |
| Mem0 | 66.4k | +2,429 | 2026-09-25 |
| AI Legion | 1.4k | +1 | 2025-05-27 |
| Memary | 2.7k | +12 | 2024-10-18 |
| Agno | 42.4k | +551 | 2026-09-30 |
| DeerFlow | 83.3k | +5,343 | 2026-09-30 |
| Generative Agents | 22.2k | +190 | 2023-08-11 |
| Maestro | 4.4k | +5 | 2024-07-01 |
1. Letta
Letta is the platform for building stateful agents: AI with advanced memory that can learn and self-improve over time.
What sets it apart: Pioneered virtual context management for LLMs — enabling unlimited conversation history through intelligent memory paging
Best for: Long-running AI agents with persistent memory; Research on memory architectures for LLMs
2. Mem0
Universal memory layer for AI Agents
What sets it apart: Unlike Zep (session-focused memory) or ChatGPT's built-in memory (closed, limited), Mem0 provides a standalone, open-source memory layer with proven +26% accuracy gains over OpenAI Memory, multi-level (user/session/agent) state management, and 90% token reduction via intelligent memory retrieval.
Best for: AI assistant developers who need persistent, personalized memory across conversations without building custom infrastructure; Customer support chatbots that need to recall past tickets and user preferences
3. AI Legion
An LLM-powered autonomous agent platform
What sets it apart: Multi-agent platform where autonomous LLM agents with persistent memory collaborate through console interaction, learning from their own mistakes
Best for: multi-agent-experimentation; exploring-agent-self-organization; autonomous-task-delegation
4. Memary
The Open Source Memory Layer For Autonomous Agents
What sets it apart: vs LangChain Memory / Mem0: graph-database-backed memory system emulating human memory (breadth + depth tracking) — agents automatically build and query knowledge graphs rather than flat conversation history
Best for: Building persistent, context-aware AI agents with evolving memory; User preference tracking and personalization across sessions; Multi-user agent management with separate knowledge contexts
5. Agno
Build, run, manage agentic software at scale.
What sets it apart: Production-first agent runtime with built-in session isolation, approval workflows, and scalable FastAPI serving — unlike LangChain which is framework-first
Best for: Production multi-agent systems with session isolation; Enterprise agentic applications needing approval workflows and audit trails
6. DeerFlow
An open-source long-horizon SuperAgent harness that researches, codes, and creates. With the help of sandboxes, memories, tools, skill, subagents and message gateway, it handles different levels of ta
What sets it apart: vs AutoGPT: purpose-built for deep research with sub-agent orchestration and sandbox; vs LangGraph: higher-level harness with built-in memory, sandbox, and skill system rather than bare graph framework
Best for: Deep research and exploration tasks; Building multi-agent systems with sub-agent orchestration; Teams wanting coding agent integration (Claude Code/Codex)
7. Generative Agents
Generative Agents: Interactive Simulacra of Human Behavior
What sets it apart: The original Stanford research paper implementation that introduced generative agents — the foundational work that inspired AI Town and subsequent agent simulation projects, featuring memory stream architecture with reflection and planning that produces remarkably human-like emergent behavior
Best for: AI researchers studying emergent social behavior and collective agent dynamics; Game designers prototyping NPC behavior systems with LLM-powered decision-making
8. Maestro
A framework for Claude Opus to intelligently orchestrate subagents.
What sets it apart: vs single-model agents (AutoGPT, BabyAGI): separates orchestration/execution/refinement across different models via LiteLLM — enables using Claude for planning + GPT-4o for coding + Llama for review in one workflow
Best for: Complex projects requiring iterative task decomposition; Cost-optimized workflows using different models per stage; Teams wanting to mix cloud and local models in one pipeline