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

Clawe

Clawe is an OpenClaw-powered application for coordinating teams of AI agents through task assignments, subtasks, scheduled heartbeats, shared files and notifications. Its web dashboard connects an agent gateway and notification watcher to a Convex backend.

Independent OpenViST project profile, based on linked sources.

Clawe — 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 Clawe when coordinating several OpenClaw agents requires shared task tracking, workspace context, scheduled check-ins or recurring task creation.

Who it is for

  • Teams configuring multiple AI agents with distinct roles and workspaces
  • People who need a shared board to assign tasks, track subtasks and monitor agent status
  • Operators who want scheduled agent check-ins and recurring routines that create tasks

Documented uses

  • Assign work to agents and break tasks into subtasks
  • Check squad status, task progress and activity
  • Share team context through common files
  • Schedule agent check-ins and recurring task creation
  • Deliver mentions and task updates to agents and users
Before you choose

Requirements & limits

The README documents a self-hosted Docker Compose setup and a Convex account. It identifies an Anthropic API key as a prerequisite, with Anthropic or OpenAI keys configured during onboarding.

  • The documented stack uses OpenClaw, Convex, Docker Compose and a TypeScript project.
  • The README describes four preconfigured agents with distinct roles and 15-minute heartbeats.
  • Production setup requires deploying the Convex backend before starting the services.
  • The repository is public and licensed under AGPL-3.0.

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 Clawe’s services

Prepare the Convex backend and start the Docker-based Clawe stack.

Before you start

  • Docker and Docker Compose
  • A Convex account and deployment
  • Anthropic API key
  • A SQUADHUB_TOKEN and CONVEX_URL

Steps

  1. Clone the Clawe repository, enter its directory and copy .env.example to .env.

  2. Set SQUADHUB_TOKEN and CONVEX_URL in .env; configure the Anthropic or OpenAI API key through onboarding.

  3. Install dependencies with pnpm install, then deploy the backend from packages/backend using npx convex deploy.

  4. Start the production stack with ./scripts/start.sh.

Expected outcome

The production stack starts the agent gateway, watcher and web dashboard, which the README places at http://localhost:3000.

Guide limitations

  • The guide covers the repository’s production startup path; it does not describe agent task execution or customization.
COMPARE OPTIONS

Compare options for Agent orchestration

These projects document a common task and share a project role. This is a source-based comparison, not an execution benchmark or a guarantee of interchangeability.

ProjectDocumented purposePlatformAccess and requirements
ClaweAssign work to agents and break tasks into subtasksCloud, Self-hostedThe README documents a self-hosted Docker Compose setup and a Convex account. It identifies an Anthropic API key as a prerequisite, with Anthropic or OpenAI keys configured during onboarding.
Insurance Agentic AIRoute insurance questions to a life, home or auto specialist.Docker, Self-hosted, Web
AI ChatkitCreate and orchestrate agents with custom behavior logic.Linux, Self-hosted, Server, WebThe repository is public and identified as open source. Its README documents a local development setup with Python and Node-based frontend tooling.
Evidence and transparency

Sources & review

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