What problem it solves

People need AI teammates that retain conversations, memory, routines, and history while remaining under their own control. They also need a way to connect different models, computer providers, tools, and applications without depending on a fixed assistant environment.

Key features

• Persistent AI teammates — Each bot can maintain its own conversations, memory, routines, and history. Bots can also delegate work to peer bots or short-lived subagents.

  Source: README

• Self-hosted across clients — The same assistant is available through the web, an Electron desktop app, and mobile apps for iPhone and Android. A backend running on a server keeps bots available to connected clients.

  Source: README

• Computer and device access — Bots can work with browsers, terminals, files, and graphical desktops. Shared Team Computers and isolated Private computers provide different collaboration and isolation modes.

  Source: README

• Flexible model and provider choices — Users can bring their own model credentials through Pi and choose supported computer providers. The documented stack includes Docker, E2B, Daytona, CreateOS, Boat, and trusted local-computer support.

  Source: README

• Tools, integrations, and voice — The assistant can connect to app integrations and user-installed tool sources, including Composio, Pipedream Connect, Treg, remote MCP, and OpenAPI sources. Voice mode supports spoken replies, dictation, and calls with selectable voice providers.

  Source: README

Quick start

Copied verbatim from the project's README.

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

git clone https://github.com/elie222/rakazo.git
cd rakazo
cp .env.example .env

pnpm install
pnpm sandbox:build
pnpm dev

Who it may suit

This project may suit people and teams who want persistent AI agents with self-hosted infrastructure and control over models, computer providers, and integrations. It may also suit developers who want to contribute to a TypeScript agent platform with web, desktop, mobile, and backend components.

Topics to discuss

• Which model and computer-provider configuration is the best default for a self-hosted installation?

• How should shared Team Computers and isolated Private computers balance collaboration and data separation?

• What additional integrations, tools, or agent workflows should the community prioritize next?

Written by ReadmeX AI from the project's README, source and public GitHub data; it may contain mistakes.

Read the original README https://github.com/elie222/rakazo#readme

ReadmeX opened this community for a trending project; it is not run by the project. Maintainers can claim it from the community page.