# builderz-labs/mission-control

Self-hosted control plane for AI agents: dispatch tasks, review runs, track spend, and operate OpenClaw, Claude Code, Codex, and other runtimes.

Repository: https://github.com/builderz-labs/mission-control
Canonical: https://ross.abutalabs.com/products/mission-control
Homepage: https://mc.builderz.dev
Language: TypeScript
License: MIT
License Family: permissive
Topics: agent-orchestration, nextjs, openclaw, sqlite, ai-agents, developer-tools, mcp, open-source, self-hosted, task-management, typescript, agent-observability, agent-operations, claude-code, codex
Last push: 2026-08-25T06:00:07+00:00

## Health v2 (maintenance only)
Score: 81/100 (v2, computed 2026-09-02T17:46:02.011165+00:00)
- activity 99, release rhythm 95, longevity 14
- inputs: {"age_days": 201, "days_push": 8, "days_rel": 39, "gap_med": 7.5, "n_releases_24m": 9}
- flags: none
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 6110, forks 61 (observed 2026-08-28T04:09:35.048900+00:00)

## What it is
Mission Control is a self-hosted, MIT-licensed control plane (Next.js app backed by SQLite) for operating AI agent runtimes like OpenClaw, Claude Code, and Codex. It provides a dashboard for dispatching tasks, inspecting runs and failures, tracking token spend, and coordinating agents with RBAC, alerts, webhooks, and audit history.

## Use cases
- dispatch tasks to multiple AI agents from one dashboard
- monitor agent sessions, logs, and failures in real time
- track token usage and spend across agent runtimes
- orchestrate agent pipelines and cron-scheduled jobs
- self-host an agent operations control plane with RBAC and audit trails
- review and approve agent task completions with quality gates

## When to choose
- you operate multiple AI agents, people, or gateways and need unified visibility into tasks, spend, and failures
- you want a self-hosted, open-source alternative to stitching together internal agent dashboards
- you need operational guardrails like RBAC, secret detection, and alert rules for agent fleets

## When to avoid
- you run a single agent on one machine and don't need a control plane
- you require stable production APIs - this is alpha software with changing schemas and APIs
- you want a managed SaaS rather than self-hosted infrastructure

## Facets
- artifact type: application
- maturity: experimental
- function: agent-framework, monitoring, workflow-automation, scheduling, webhook, mcp, analytics, logging
- domain: self-hosted, developer-tools, monitoring
- platform: self-hosted, cross-platform
- tags: agent-orchestration, agent-observability, control-plane, task-management, cost-tracking, sqlite, nextjs, openclaw, claude-code, codex, alpha-software, ai-agents, automation, docker, nodejs, web-server

## Member repositories
- builderz-labs/mission-control (main) score 81

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:09:35.048900+00:00.
- Health v2: computed from the inputs above; adoption is never an input.
- Inferred fields (summary, facets, guidance): AI-extracted, prompt v1, taxonomy v1, on 2026-08-29T17:48:11.996880+00:00, confidence not recorded.
  - readme: https://github.com/builderz-labs/mission-control (fetched 2026-08-28T04:09:35.048900+00:00, sha 2c375cde42aa)
  - homepage: https://mc.builderz.dev (fetched 2026-08-29T08:44:55.642421+00:00, sha ddb28e7097f8)
- Data as of 2026-08-30T08:39:29.467469+00:00.