Suits developers comfortable with Docker who want to self-host AI agents and choose their own models; the project is in beta.

What can you build with rakazo?

Run a self-hosted AI assistant that keeps its memory and routines between chats. Give a bot a sandboxed browser and terminal to do tasks on its own computer. Deploy an always-on bot on a VPS and reach it from desktop, mobile or browser. Connect a bot to your apps through Composio, Pipedream, MCP or OpenAPI tools. Set up several bots that hand work to each other as a small team.

How do I get started with rakazo?

You need Docker Engine, the Compose plugin, curl and OpenSSL. Run the installer, open http://127.0.0.1:5173, create an account, connect a model and create your first bot. Commands from the README: mkdir -p rakazo && cd rakazo && curl -fsSLO https://raw.githubusercontent.com/elie222/rakazo/main/infra/compose/install-images.sh && bash install-images.sh.

elie222 /

rakazo

Self-hosted platform for persistent AI bots with their own computers and memory

5.3k stars
2k stars since 3 Oct
TypeScript
Updated today
Some experience
AI agents

Open on GitHub (opens in a new tab) Website (opens in a new tab)

Rakazo is an open-source platform for running AI teammates that stay around. Each bot keeps its own chat history, memory and routines. You reach them from a web app, an Electron desktop app or an Expo mobile app. The project is in beta.

Each bot gets a computer to work on, either a shared team machine or an isolated private one. It comes with a browser, terminal, files and a graphical desktop. The sandbox can be local Docker or a remote provider such as E2B, Daytona, CreateOS or Box. Bots can also hand work to peer bots or short-lived subagents.

The GitHub description calls it an open-source alternative to Grok Bot. You bring your own model credentials and choose your own sandbox instead of being tied to one vendor. The backend is TypeScript with PostgreSQL, Hono and Graphile Worker.

What it does

Persistent bots
Each bot keeps its own conversations, memory, routines and history, so it can carry on over time.
Sandboxed computers
Bots get browser, terminal, file and desktop access on shared Team Computers or isolated Private ones. Providers include Docker, E2B, Daytona, CreateOS and Box.
Bring your own model
You connect model credentials through Pi, or set an OpenRouter key.
Tool integrations
Connect apps through Composio or Pipedream Connect. You can also add remote MCP servers, Treg endpoints or OpenAPI documents.
Voice mode and delegation
Dictate, hear spoken replies or call a bot using your own ElevenLabs, OpenAI, Cartesia or Fish Audio key. Bots can delegate to other bots.

What you could build

Run a self-hosted AI assistant that keeps its memory and routines between chats.
Give a bot a sandboxed browser and terminal to do tasks on its own computer.
Deploy an always-on bot on a VPS and reach it from desktop, mobile or browser.
Connect a bot to your apps through Composio, Pipedream, MCP or OpenAPI tools.
Set up several bots that hand work to each other as a small team.

Get started

You need Docker Engine, the Compose plugin, curl and OpenSSL. Run the installer, open http://127.0.0.1:5173, create an account, connect a model and create your first bot.

mkdir -p rakazo && cd rakazo &&
curl -fsSLO https://raw.githubusercontent.com/elie222/rakazo/main/infra/compose/install-images.sh &&
bash install-images.sh

Commands are copied from the project's README. Read it on GitHub for the full setup.