AgentToolDrop

7 of 66

Rakazo

Self-hosted agent app with persistent bots that use your own model and run in Docker or remote sandboxes

  • score 67
  • 4.9k stars
  • 71.1 stars/day since creation
  • pushed
  • v0.3.1 on
  • Apache-2.0

Install the published images with Docker Compose

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

Copied from the project's docs at github.com/elie222/rakazo

Why you'd want it

Rakazo is an open source, self-hosted AI agent where you create persistent bots with their own conversations, memory, routines and history. Each bot works on a computer with browser, terminal, file and graphical desktop access, either a shared Team Computer or an isolated Private one. Computers run on local Docker or on E2B, Daytona, CreateOS, Boat or Railway, and models come from your own credentials through Pi. App integrations come from Composio or Pipedream Connect, plus user-added remote MCP and OpenAPI tool sources, and the same API serves a web app, an Electron desktop app, and iPhone and Android apps.

Best for

  • Self-hosting persistent agent teammates
  • Running agents in Docker or remote sandboxes
  • Bringing your own model and tools

Use it when

You want a self-hosted agent you can reach from the web, desktop and phone, with your own choice of model and sandbox provider. The quick start needs only Docker Engine, the Compose plugin, curl and OpenSSL.

Skip it if

The README says Rakazo is in beta. Bots get terminal, browser and desktop access, and the server holds your model and connector credentials (encrypted on the server, per the README), so read the installer script and review the sandbox setup before use. The quick start pulls the edge image tag built from main, and the README notes that Railway sandbox usage and Treg are metered.

Editor's note

Other routes in the README: a Railway template, an Electron desktop app, and iPhone and Android apps.

Related tools

Same category or shared tags.

  1. Rank 17

    OpenBot

    Framework

    Runs self-hosted AI coworkers with their own browser, files and shell, each action policy-checked and logged

    • score 58
    • 6.7k stars
    • 38.3 stars/day last 5 days
    • pushed
    • v0.2.0 on
    • MIT

    Run the published Docker image

    docker run -p 3001:3001 --env-file .env \
  -e EMBEDDED_POSTGRES=on -v openbot-data:/var/lib/postgresql \
  ghcr.io/copilotkit/openbot:latest
    Use it when, skip it if, stats for OpenBot

    Why you'd want it

    OpenBot is a template for an in-house agent platform: Docker Compose brings up the app, PostgreSQL and the Bots, and you supply the model key. Each Bot gets its own container with a Chromium profile, a workspace volume and a shell, and every browser, file, shell, MCP or component action passes through one gateway that evaluates CEL policy rules, writes an audit row and only then acts. Any agent that speaks the AG-UI protocol, built with LangGraph, Mastra, CrewAI, Pydantic AI, Google ADK or by hand, can join as a coworker with its own channel, and you can watch its screen and take over. It ships with General Assistant and Knowledge coworkers plus example roles to copy.

    Best for

    • Self-hosted agent coworkers for a team
    • Auditable browser and shell actions
    • Bringing AG-UI agents into one workspace

    Use it when

    You want to give agents real computers inside your own infrastructure but need allow and deny rules and an audit trail for what they do.

    Skip it if

    You want a finished product: the README calls it an alpha template to clone and change, with no hosted version. It needs Docker, Bun, a model key and a CopilotKit Intelligence project (a free plan exists, or you can self-host it), and Bots drive a browser with saved logins and run shell commands, so set up sign-in before anyone else can reach it.

    Stats

    New and rising score
    58 of 100
    Stars per day, last 5 days
    38.3
    Release
    v0.2.0,
    License
    MIT
    Pricing
    Open source
    Works with
    Docker, Web
    Forks
    931
    Open issues
    29
    GitHub checked

    Full stat block for OpenBot

  2. Rank 27

    Omnigent

    Framework

    Orchestrates Claude Code, Codex, Cursor and other agents in one session, with policies and sandboxing

    • score 47
    • 10.9k stars
    • 20 stars/day last 4 days
    • pushed
    • v0.18.0 on
    • Apache-2.0

    Install with uv or pip

    uv tool install omnigent        # or: pip install "omnigent"
    Use it when, skip it if, stats for Omnigent

    Why you'd want it

    Omnigent is a meta-harness that puts a common orchestration layer over Claude Code, Codex, Cursor, OpenCode, Hermes, Pi and agents you write yourself, so you can swap or combine harnesses without rewriting. Agents are short YAML files with a prompt, local Python functions, MCP servers and sub-agents, and several agents can share one session, for example one reviewing another's work. Policies can pause for your approval before risky actions, cap spend or limit which tools an agent reaches, at server, agent or session level. Sessions can be followed from the terminal, a browser or a phone, and can run in cloud sandboxes such as Modal, Daytona or E2B.

    Best for

    • Running Claude Code and Codex in one session
    • Approval and spend policies across agents
    • Sharing live agent sessions with a team

    Use it when

    You want one layer to run and supervise several coding agents, with approval policies and sessions you can share or pick up from another device.

    Skip it if

    The README badges it alpha and says anonymized telemetry is collected by default, with an opt-out documented. It picks up model credentials from your environment, runs agents that execute commands on your machine, and lets a co-attached teammate's messages execute there too. On native Windows the Job Object backend does not isolate the filesystem or network.

    Stats

    New and rising score
    47 of 100
    Stars per day, last 4 days
    20
    Release
    v0.18.0,
    License
    Apache-2.0
    Pricing
    Open source
    Works with
    Claude Code, Codex, Cursor, macOS, Linux, Windows, Web, Docker
    Forks
    1,772
    Open issues
    2,300
    GitHub checked

    Full stat block for Omnigent

  3. n8n

    Framework Standard

    Builds AI agents and automation workflows on a visual canvas that connects to 1500+ integrations

    • 208k stars
    • 134 stars/day last 5 days
    • pushed
    • n8n@2.44.4 on
    • Sustainable Use License

    Run with Docker

    docker volume create n8n_data
docker run -it --rm --name n8n -p 5678:5678 -v n8n_data:/home/node/.n8n docker.n8n.io/n8nio/n8n
    Use it when, skip it if, stats for n8n

    Why you'd want it

    n8n combines a node-based visual editor with custom JavaScript, Python and npm packages, and its README says workflows can use OpenAI, Anthropic, Google or open-source models. You can self-host it with Docker or npm, or use the paid n8n Cloud. Its docs cover building agents, LangChain components and MCP servers inside workflows.

    Best for

    • Connecting agents to business apps
    • Self-hosted internal automations
    • Teams mixing visual building with code

    Use it when

    You want an agent to act across many SaaS tools through a workflow you can see, edit and self-host.

    Skip it if

    You need an OSI open source license or plan to offer n8n to others as a paid service; the Sustainable Use License limits use to internal business, non-commercial or personal purposes. If you build agents in code, a library will fit better.

    Stats

    Stars per day, last 5 days
    134
    Release
    n8n@2.44.4,
    License
    Sustainable Use License
    Pricing
    Free tier + paid
    Works with
    Docker, Web
    Forks
    61,193
    Open issues
    1,203
    GitHub checked

    Full stat block for n8n

For agents

The same entry, as files an agent can read without scraping this page. 

# read one entry
curl -s https://agenttooldrop.com/tools/rakazo.md

# list the MCP servers in the catalog
curl -s https://agenttooldrop.com/tools.json \
  | jq -r '.tools[] | select(.category=="mcp-server") | .slug'