OpenViSTAI · Agents · Blockchain · Crypto
Menu
Multi-Agent Systems

Clawboo

Clawboo is a self-hosted studio for deploying teams of AI agents that divide requests into jobs, assign them across connected agent tools or built-in agents, and report results through a shared chat and live monitoring interface.

Independent OpenViST project profile, based on linked sources.

Clawboo — OpenViST project profile in Multi-Agent Systems.
OpenViST project illustration. See the linked sources for product details.
Understand the project

Practical overview

When it fits

Use Clawboo when a task benefits from several AI agents working under a lead agent, especially when live delegation and visibility into each job matter.

Who it is for

  • Developers running agent workspaces on their own computers.
  • Teams coordinating marketing, development or research tasks with multiple AI agents.
  • Users who want to combine hosted model providers, local Ollama models or connected agent runtimes.

Documented uses

  • Turn a broad request into delegated jobs on a shared board.
  • Assign work to specialized teammates using different agent tools.
  • Monitor agent progress live through job cards, chat and a team graph.
  • Add a reviewer agent to check work.
  • Bring completed teammate results back into a lead-agent response.
Before you choose

Requirements & limits

Clawboo is open source under the MIT license and runs on the user’s computer. The setup supports npx or a global npm installation, requires Node.js 22.12 or newer for the default setup, and does not require a Clawboo account. Connected model usage is billed by the provider; a Clawboo price is not stated.

  • Choose Clawboo when a lead agent should split work and assign it automatically rather than requiring manual routing.
  • The available execution options include built-in agents, Claude Code, Codex, Hermes and OpenClaw, so runtime availability affects team setup.
  • Ollama provides a locally connected model option, but supported model details are not specified.
  • The default installation is local and browser-accessed, with the dashboard port recorded in ~/.clawboo/api-port.txt.
  • Teams can be monitored through both a shared board and group chat, with an optional reviewer agent.

Check current requirements in the official documentation. Source-based guidance does not mean OpenViST has run or independently tested this project.

Source-based practical guide

Set up a Clawboo agent team

Install Clawboo, connect a model or local Ollama setup, add agent tools and deploy a ready-made team.

Before you start

  • Node.js 22.12 or newer for the default setup.
  • An API key from a supported provider, a local Ollama model, or a ChatGPT subscription used through the Codex CLI.
  • Optional: Claude Code, Codex, Hermes or OpenClaw if those runtimes are to be connected.
  • Internet access to run the npm-based installation command.

Steps

  1. Run the command below, or install it globally with the command below and run clawboo.

    Documented command
    npx clawboo@latest
    Documented command
    npm install -g clawboo
  2. In the browser setup wizard, connect a model using a provider API key, Ollama, or Sign in with ChatGPT through Codex CLI.

  3. Optionally add Claude Code, Codex, Hermes or OpenClaw, or skip this step and add runtimes later in Settings → Runtimes.

  4. Choose a ready-made team from the marketplace and deploy it; Boo Zero then leads the team in its group chat.

Expected outcome

A locally running Clawboo dashboard with a deployed agent team and a browser-based group chat.

Guide limitations

  • The default setup needs Node.js 22.12 or newer; OpenClaw teammates require newer Node.js versions.
  • The evidence does not specify which Ollama models are supported.
  • Connected model usage is billed by the provider; no Clawboo pricing is stated.
Evidence and transparency

Sources & review

Source record details
Source availability
Active
Sources checked
4 October 2026
Original website title
clawboo/clawboo · Official homepage title · retained in its source language