letta-ai/letta Alternatives

Choose Pi if you want a lighter TypeScript agent toolkit/CLI without Letta's server/memory-block stack.

AI agent toolkit: unified LLM API, agent loop, TUI, coding agent CLI

Choose Agno if you want a Python-native agent platform/library to embed in your app instead of deploying Letta's runtime.

Build, run, and manage agent platforms.

Choose Mastra if you prefer a TypeScript agent/workflow framework over Letta's memory-centric server.

Mastra is the modern TypeScript framework for AI-powered applications and agents.

Choose VoltAgent if you want a TypeScript agent engineering framework with its own orchestration layer instead of Letta's memory-first platform.

AI Agent Engineering Platform built on an Open Source TypeScript AI Agent Framework

Choose fast-agent if you want evaluation- and MCP-oriented agent development in Python rather than Letta's stateful memory runtime.

Code, Build and Evaluate agents - excellent Model and Skills/MCP/ACP/A2A Support

Choose MetaGPT if you want role-based multi-agent simulation of a software team, not a persistent memory service.

🌟 The Multi-Agent Framework: First AI Software Company, Towards Natural Language Programming

Choose Agent Zero if you want a flexible Python autonomous-agent framework without Letta's managed memory/runtime.

Agent Zero AI framework

Choose qm if you need a multi-agent/session harness for collaborative work rather than Letta's single remembered-agent model.

Multiplayer agent harness for work.

Choose agentUniverse if you need Python multi-agent orchestration in your own server rather than Letta's agent memory service.

agentUniverse is a LLM multi-agent framework that allows developers to easily build multi-agent applications.

Choose OpenAkita if you want a smaller skills-based assistant framework rather than Letta's larger stateful memory platform.

An open-source AI assistant framework with skills and agent architecture

Choose loong if you want a very small Rust agent runtime instead of Letta's heavier platform/dependency.

Lightweight, clear, and fully extensible AI agent infrastructure — learn easily, customize anything 🐉

Choose activegraph if you want to build durable agent state on an event-sourced graph instead of Letta's managed memory model.

Event-sourced graph runtime for durable and stateful agents

Choose gptme if you want a local Python terminal agent loop to extend, rather than Letta's server/memory platform.

Your agent in your terminal, equipped with local tools: writes code, uses the terminal, browses the web. Make your own persistent autonomous agent on top!

Choose ChatDev if you only need a self-contained multi-agent software generator instead of a general-purpose stateful agent platform.

ChatDev 2.0: Dev All through LLM-powered Multi-Agent Collaboration

Choose SWE-AF if your target is autonomous PR creation in software repos, not general-purpose stateful agents.

Autonomous software engineering fleet of AI agents for production-grade PRs on AgentField: plan, code, test, and ship.

Choose Goose if you want a ready-to-run OS-operating agent rather than building and hosting agents with Letta.

an open source, extensible AI agent that goes beyond code suggestions - install, execute, edit, and test with any LLM

Choose AIlice if you want a standalone autonomous assistant rather than a platform for building your own agents.

AIlice is a fully autonomous, general-purpose AI agent.

Choose Rowboat if you want a ready-deployed AI coworker with memory instead of composing one with Letta.

Open-source AI coworker, with memory

Choose KiroCrew if you want a persistent self-improving development workspace/agent out of the box, not a general memory platform.

A persistent workspace for development work that self-improves and continues beyond one session.

Choose Hermes Agent if you want a single ready-to-run agent that personalizes over time, not a server or SDK for many agents.

The agent that grows with you

Choose Qwen Code if you want a terminal/IDE coding assistant rather than a framework for stateful agents.

An open-source AI coding agent that lives in your terminal.

Choose AnythingLLM if you want a self-hosted chat/agent application instead of a library/platform to build agents.

Stop renting your intelligence. Own it with AnythingLLM. Everything you need for a powerful local-first agent experience