OpenViSTAI · Agents · Blockchain · Crypto
Submit a project
Menu
Agent Evaluation & Observability

Mission Control

Mission Control is a self-hosted control plane with a SQLite-backed local dashboard for dispatching tasks, inspecting agent runs, reviewing failures, tracking spend and coordinating AI-agent runtimes.

Explore the practical guide ↓

Independent OpenViST project profile, based on linked sources.

Mission Control — OpenViST project profile in Agent Evaluation & Observability.
OpenViST project illustration. See the linked sources for product details.
Understand the project

Practical overview

When it fits

Use Mission Control when native runtime interfaces no longer provide a sufficiently clear view of task ownership, execution history, review status, failures or spend.

Who it is for

  • Operators coordinating multiple AI agents or runtimes
  • Teams that need shared task ownership, run review and operational records
  • Developers integrating agent operations through REST, CLI, MCP or web interfaces

Documented uses

  • Dispatch and assign tasks to agents
  • Inspect runs, activity and failures
  • Review results and completion evidence
  • Track token use, costs and operational alerts
  • Coordinate OpenClaw, Claude Code, Codex and other agent runtimes
Before you choose

Requirements & limits

The project is open source under the MIT license. Documented access models include a local source installation, Docker Compose and a published container image. A first admin account is created through the local setup page; an API key is available from Settings for headless access.

  • Self-hosting is central to the deployment model.
  • Node.js 22 or newer and pnpm are required for the documented source installation.
  • Docker-based deployment is also documented.
  • Live session messaging requires a connected runtime gateway, while several task and operations functions can work without one.
  • The project is alpha software, so API, schema and configuration changes are an explicit deployment consideration.

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

Install Mission Control locally

Set up a local Mission Control instance and create its first administrator account.

Before you start

  • Node.js 22 or newer
  • pnpm
  • A cloned copy of the Mission Control repository

Steps

  1. Clone the repository and enter its directory.

  2. Run the documented local installer with the command below.

    Documented command
    bash install.sh --local

  3. Open http://localhost:3000/setup.

  4. Create the first admin account and copy the API key from Settings if headless agent or script access is needed.

Expected outcome

A local Mission Control instance is configured with an initial administrator account.

Guide limitations

  • The project is alpha software, and APIs, schemas and configuration may change between releases.
  • This procedure documents local setup; it does not verify a particular environment or runtime integration.
Documentation 1 ↗
Source-based practical guide

Connect an agent through the REST API

Register an agent, create a task and retrieve that agent’s queue from a running Mission Control instance.

Before you start

  • A running Mission Control instance
  • The URL shown for that instance
  • An API key copied from Settings
  • A registered agent name and role

Steps

  1. Export the Mission Control URL and API key as MC_URL and MC_API_KEY.

  2. Send the documented registration request for an agent such as scout with a role such as researcher.

  3. Create a task through the documented tasks endpoint and assign it to the registered agent.

  4. Request the agent’s task queue using the documented queue endpoint.

Expected outcome

The agent is registered, assigned work and queried for its task queue through the REST interface.

Guide limitations

  • This source-based procedure does not constitute an execution test or compatibility guarantee.
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
Mission ControlDispatch and assign tasks to agentsCloud, Self-hostedThe project is open source under the MIT license. Documented access models include a local source installation, Docker Compose and a published container image. A first admin account is created through the local setup page; an API key is available from Settings for headless access.
Agent FlowTrace the sequence of decisions and tool calls that led to an unexpected result.Desktop, Linux, macOS, Web
Evidence and transparency

Sources & review

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