OpenViSTAI · Agents · Blockchain · Crypto
Submit a project
Menu
Multi-Agent Systems

Coordclaw

A TypeScript multi-agent collaboration framework that defines AI teams as organizations and coordinates them through point-to-point message loops.

Explore the practical guide ↓

Independent OpenViST project profile, based on linked sources.

Coordclaw — 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 it when a task benefits from multiple agent roles, iterative review and visible human oversight rather than a single-agent response or a fixed workflow.

Who it is for

  • Developers exploring multi-agent orchestration.
  • People building AI teams for software-production tasks.
  • Researchers or experimenters modeling organizational and social collaboration.
  • Operators who need to observe and intervene in agent activity.

Documented uses

  • Define an AI team and its organizational relationships in natural language.
  • Coordinate specialized agents through messages rather than a hard-coded DAG.
  • Review agent decisions and work logs across collaboration rounds.
  • Intervene in conversations from a human control panel.
  • Configure shared or member-specific skills.
Before you choose

Requirements & limits

The repository is public, active and open source under the MIT license. Its documented local setup depends on an initialized OpenClaw or compatible runtime.

  • Coordclaw uses organizational relationships and message loops instead of hard-coded DAGs.
  • Agents receive point-to-point messages addressed to them, while the human can inspect the wider message flow.
  • Structured work logs are used as project memory between reset conversation rounds.
  • The documented control panel includes message-flow observation and locally estimated token-consumption charts.
  • The setup sequence requires OpenClaw or a compatible runtime to be initialized before Coordclaw is started.

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 Coordclaw with an initialized OpenClaw runtime

Prepare the documented local control panel and install Coordclaw through its setup wizard.

Before you start

  • An OpenClaw installation or compatible variant with its environment initialized.
  • A cloned Coordclaw repository.
  • Node.js, since the documented start command is node start.cjs.

Steps

  1. Install and open OpenClaw or a compatible variant once so its environment is initialized, then close it.

  2. Start Coordclaw with node start.cjs, or use start.bat on Windows.

  3. Open http://localhost:18790 and follow the installation wizard: choose a language, select the discovered OpenClaw instance and start installation.

  4. If the runtime is installed in a non-standard location and is not discovered, create findplatforms.json from findplatforms.json.example, add the relevant directory and run the wizard again.

  5. After installation, open the OpenClaw runtime first and then open the Coordclaw control panel.

Expected outcome

The documented installation sequence leaves the Coordclaw control panel connected to a discovered OpenClaw runtime.

Guide limitations

  • The repository notes that Linux and macOS startup were not tested.
  • The wizard may not find runtime instances outside the scanned locations.
  • Coordclaw requires the runtime to be initialized before discovery.
Documentation 1 ↗
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
CoordclawDefine an AI team and its organizational relationships in natural language.Cloud, Self-hosted, ServerThe repository is public, active and open source under the MIT license. Its documented local setup depends on an initialized OpenClaw or compatible runtime.
MassgenRun multiple AI agents against the same user task.CLIThe repository documents installation through pip or uv and requires Python 3.11 or later. Setup can configure API keys for OpenAI, Anthropic, Google and xAI; credentials are needed for the selected model backends.
Langchain Multi Agents BoilerplateRoute incoming football questions to model and agent workflows according to task complexity.WebThe repository is public and specifies an MIT license. Running the application requires OpenAI and Groq API keys and a Redis server.
Evidence and transparency

Sources & review

Official repository ↗
Source record details
Source availability
Active
Sources checked
30 September 2026
Original website title
CoordClaw/CoordClaw · Official homepage title · retained in its source language
How we review sourcesSuggest a correction