OpenViSTAI · Agents · Blockchain · Crypto
Submit a project
Menu
Agent Infrastructure

Agent Control

Agent Control is a Python-based control plane that dispatches tasks to autonomous agents, runs DAG workflows, tracks agent heartbeats and provides monitoring and MCP tools. It includes a FastAPI service, a dashboard, a Python SDK and data-collection pipeline components.

Explore the practical guide ↓

Independent OpenViST project profile, based on linked sources.

Agent Control — OpenViST project profile in Agent Infrastructure.
OpenViST project illustration. See the linked sources for product details.
Understand the project

Practical overview

When it fits

Use Agent Control when you need a self-hosted coordination layer for agent fleets, task queues or DAG-based workflows, particularly if you want to manage those tasks through Python, REST or an MCP interface.

Who it is for

  • Teams coordinating fleets of autonomous agents and distributed tasks.
  • Developers who want to dispatch and monitor agent work through a Python SDK or REST interface.
  • MCP client users who want tools for submitting tasks and inspecting agent or workflow state.

Documented uses

  • Register and monitor agents, including their heartbeat and capability status.
  • Dispatch work to an agent task queue and inspect task status, attempts, logs and artifacts.
  • Define multi-stage DAG workflows with dependencies, parallel execution and conditional branches.
  • Review agent, task, crawl-run and metrics information in a dashboard.
  • Connect MCP-capable clients to tools for task dispatch and control-plane queries.
Before you choose

Requirements & limits

The repository is public and specifies an Apache-2.0 license. The README documents local, Docker Compose and manual Python installation routes.

  • This is a control plane and orchestration service; the README describes agents and crawlers as workers it coordinates.
  • The Python SDK covers task dispatch, agent fleet management and DAG monitoring.
  • The MCP server offers task, workflow, agent and system-metric tools, as well as database query and inspection tools.
  • The README lists SQLite for local prototyping and MySQL or PostgreSQL for other deployments; its Docker Compose quickstart uses MySQL 8.0.
  • The project identifies MCP compatibility, but the supplied description does not demonstrate setup with a particular client.

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

Start the service with Docker Compose

Launch the documented FastAPI and MySQL stack using the repository's Docker Compose configuration.

Before you start

  • A clone of the Agent Control repository
  • Docker Compose

Steps

  1. Clone the repository and change into its directory.

  2. Run docker-compose up -d.

Expected outcome

The README describes this command as launching the FastAPI and MySQL 8.0 stack.

Guide limitations

  • This setup recipe does not document configuring an agent, dispatching a task or connecting an MCP client.
Documentation 1 ↗
Source-based practical guide

Prepare a manual Python installation

Install the documented Python dependencies and start the FastAPI server.

Before you start

  • Python 3.10 or later
  • The Agent Control repository

Steps

  1. Create and activate a virtual environment.

  2. Install dependencies with the command below.

    Documented command
    pip install -r requirements.txt

  3. Copy .env.example to .env.

  4. Start the server with uvicorn main:app --host 0.0.0.0 --port 8000 --reload.

Expected outcome

The README gives `http://localhost:8000/dashboard`, `/docs` and `/health` as the dashboard, API documentation and health-check addresses.

Documentation 1 ↗
Evidence and transparency

Sources & review

Official repository ↗
Source record details
Source availability
Active
Sources checked
12 October 2026
Original website title
loulanyue/agent-control · Official homepage title · retained in its source language
How we review sourcesSuggest a correction