
Letta is an open-source platform for AI agents that retain memory across conversations and use experience to improve over time. Formerly called MemGPT, it's for people building or using assistants that need continuity beyond a single chat. Agents can run locally or on a self-hosted server.
Memory is central to its approach: an agent's identity, context, and capabilities can evolve as it works. Letta's research covers programmatic context management, memory versioning with Git, and reasoning about stored context during idle time. These approaches focus on how agents retain and learn from experience, rather than treating each conversation as a fresh start.
You can interact with agents through a terminal interface or desktop apps for macOS, Windows, and Linux. Letta also offers a browser service at chat.letta.com that works on mobile. The browser service is separate from the local and self-hosted runtime.
For agents that need to participate in existing conversations, Letta supports Slack, Telegram, Discord, and custom channels. Its App Server provides the runtime for local or self-hosted agents, and the current codebase also includes the terminal interface and the runtime used by the desktop and web apps.
The linked letta-ai/letta repository is licensed under Apache 2.0. The retired V1 API server remains available as historical source; active development lives in letta-ai/letta-code.
Claim this page with an email at letta.com. Letta gets the verified badge, and you can upgrade the listing to be featured on localhosted. Proud to be listed? Put our badge on your site.
Want more people to find Letta?Promote it
Something wrong or outdated on this page?
41.2KUpdated 1 day agoAGPL-3.0
macOS · Docker · Web#Code execution#Hybrid search#LM Studio integration
AstrBot brings AI assistants into messaging apps such as Telegram, Discord, Slack, QQ and WeCom. It's an open source platform under AGPL-3.0 for people building personal companions, customer support bots or team automation. You can run it on your own computer or server, including through Docker, or use its desktop app for browser-style chat.
250.1KUpdated 18 hours agoMIT
macOS · Windows · Linux · Android · Docker#Agent Skills#Code execution#Multi-agent workflows
390.8KUpdated 18 hours ago
macOS · Windows · Linux · iOS · Android · Docker#Multi-user access#Persistent memory#Tool calling
886Updated 2 weeks agoMIT
macOS · Windows · Linux · Docker · Web#Agent Skills#Code execution#Guardrails
10.5KUpdated 7 months agoApache-2.0
macOS · Windows · Linux · Android · Web#Code execution#MCP#Multimodal input
42.5KUpdated 2 hours agoMIT
#Human approval#Multi-agent workflows#Persistent memory
Hermes Agent is a self-hosted AI agent from Nous Research for people who want an assistant that remembers past work and develops reusable skills. It creates skills after complex tasks, revises them through use, and searches earlier conversations to recover context across sessions. The project is open source under the MIT license.
OpenClaw is a self-hosted AI assistant that connects your own computer to the messaging services you already use. It's for people who want a personal assistant on their laptop, or teams that want to run a shared assistant on their own hardware. The project is open source under the MIT license.
PocketPaw is a self-hosted AI agent for people who want a personal assistant that can work with files, write code and use a browser on their own computer or server. It runs on macOS, Windows and Linux, with a web dashboard and access through messaging apps. It is open source under the MIT license.
aichat brings Ollama and cloud AI services into the same terminal interface for developers and people who work at the command line. It runs locally on macOS, Linux and Windows, with Android support through Termux. Model processing happens through the backend you choose: Ollama supports local models, while providers such as OpenAI, Claude and Gemini process requests in the cloud.
LangGraph is a free, MIT-licensed Python framework for developers building AI agents that need to keep state and handle complex tasks. It gives teams control over how an agent moves between steps, where people can intervene, and what happens when a long-running task is interrupted.