elie222/rakazo

Open-source Grok Bot alternative. Choose your own model and sandbox.

What it solves

Rakazo provides a self-hosted, persistent AI agent platform that allows users to maintain their own AI teammates. It solves the problem of relying on closed-source, hosted AI assistants by enabling users to run their own infrastructure while maintaining control over their data, memory, and agent routines.

How it works

The project acts as a central hub for AI agents, offering a web, desktop, and mobile interface. It integrates with various model providers and sandbox environments (like Docker, E2B, or Daytona) to give agents access to browsers, terminals, and file systems. Users can connect their own API keys for models and tools, and the system manages agent memory, history, and task delegation between peer bots.

Who it’s for

It is designed for developers and power users who want a private, self-hosted alternative to platforms like Grok Bot or Meta Muse. It is suitable for those who want to build and deploy persistent AI agents that can perform real-world tasks on their local machine or a private server.

Highlights

  • Persistent AI agents with dedicated memory, history, and routines.
  • Multi-platform support: Web, Electron desktop app, and native mobile apps (iOS/Android).
  • Secure, self-hosted architecture with support for isolated sandboxes (Docker, E2B, etc.).
  • Extensible tool integration via Composio, Pipedream, MCP, and OpenAPI.
  • Voice-enabled capabilities with support for providers like ElevenLabs and Cartesia.

Related

  • Project
    nightly-labs/openbot

    A local-first desktop workspace for persistent AI teammates, consolidating multiple agent providers like Claude Code and Codex into a single interface with dedicated workspaces.

  • Project
    CopilotKit/OpenDots

    An open-source template for building persistent AI coworkers with their own isolated computers, capable of working across web, mobile, Slack, and voice calls.

  • Project
    hezo-ai/hezo

    An open-source server and web app for running teams of AI agents organized like a company, featuring sandboxed execution and secure secret management.

  • Project
    kirodotdev/KiroCrew

    A persistent, self-learning AI development workspace that runs on your own hardware to execute long-running, unattended tasks across multiple sessions.

  • Project
    siddsachar/row-bot

    Row‑Bot is a self‑hosted desktop AI assistant that lets you converse with LLMs to create files, run code, manage designs, and interact with services—all while keeping data locally. It offers memory via a personal knowledge graph, goal‑driven agents, approval‑gated actions, multi‑device remote access, and integrations (GitHub, Notion, Slack, etc.). Runs on Windows/macOS/Linux or Docker, using Ollama or any OpenAI‑compatible provider, and stores everything securely on your machine.