[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"project-74793":3},{"id":4,"name":5,"fullName":6,"owner":7,"repo":5,"description":8,"homepage":9,"htmlUrl":10,"language":11,"languages":10,"totalLinesOfCode":10,"stars":12,"forks":13,"watchers":14,"openIssues":15,"contributorsCount":16,"subscribersCount":16,"size":16,"stars1d":17,"stars7d":18,"stars30d":19,"stars90d":16,"forks30d":16,"starsTrendScore":20,"compositeScore":21,"rankGlobal":10,"rankLanguage":10,"license":22,"archived":23,"fork":23,"defaultBranch":24,"hasWiki":25,"hasPages":23,"topics":26,"createdAt":10,"pushedAt":10,"updatedAt":43,"readmeContent":44,"aiSummary":45,"trendingCount":16,"starSnapshotCount":16,"syncStatus":46,"lastSyncTime":47,"discoverSource":48},74793,"mission-control","builderz-labs\u002Fmission-control","builderz-labs","Self-hosted AI agent orchestration platform: dispatch tasks, run multi-agent workflows, monitor spend, and govern operations from one mission control dashboard.","https:\u002F\u002Fmc.builderz.dev",null,"TypeScript",5258,907,24,7,0,58,168,492,174,39.87,"MIT License",false,"main",true,[27,28,29,30,31,32,33,34,35,36,37,38,39,40,41,42],"agent-orchestration","ai-agents","ai-automation","ai-dashboard","claude","dashboard","developer-tools","llm","mcp","nextjs","open-source","openclaw","self-hosted","sqlite","task-management","typescript","2026-06-12 02:03:28","\u003Cdiv align=\"center\">\n\n# Mission Control\n\n**Open-source dashboard for AI agent orchestration.**\n\nManage AI agent fleets, dispatch tasks, track costs, and coordinate multi-agent workflows — self-hosted, zero external dependencies, powered by SQLite.\n\n[![License: MIT](https:\u002F\u002Fimg.shields.io\u002Fbadge\u002FLicense-MIT-blue.svg)](LICENSE)\n[![Next.js 16](https:\u002F\u002Fimg.shields.io\u002Fbadge\u002FNext.js-16-black?logo=next.js)](https:\u002F\u002Fnextjs.org\u002F)\n[![TypeScript](https:\u002F\u002Fimg.shields.io\u002Fbadge\u002FTypeScript-5.7-3178C6?logo=typescript&logoColor=white)](https:\u002F\u002Ftypescriptlang.org\u002F)\n[![Tests](https:\u002F\u002Fimg.shields.io\u002Fbadge\u002FTests-577%20(282%20unit%20%2B%20295%20E2E)-brightgreen)](https:\u002F\u002Fgithub.com\u002Fbuilderz-labs\u002Fmission-control)\n[![GitHub stars](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002Fbuilderz-labs\u002Fmission-control?style=social)](https:\u002F\u002Fgithub.com\u002Fbuilderz-labs\u002Fmission-control\u002Fstargazers)\n[![GitHub forks](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fforks\u002Fbuilderz-labs\u002Fmission-control?style=social)](https:\u002F\u002Fgithub.com\u002Fbuilderz-labs\u002Fmission-control\u002Fnetwork\u002Fmembers)\n[![Last commit](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Flast-commit\u002Fbuilderz-labs\u002Fmission-control)](https:\u002F\u002Fgithub.com\u002Fbuilderz-labs\u002Fmission-control\u002Fcommits\u002Fmain)\n[![Open issues](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fissues\u002Fbuilderz-labs\u002Fmission-control)](https:\u002F\u002Fgithub.com\u002Fbuilderz-labs\u002Fmission-control\u002Fissues)\n\n![Mission Control Dashboard](docs\u002Fmission-control-overview.png)\n\n\u003C\u002Fdiv>\n\n---\n\n> **Alpha Software** — Mission Control is under active development. APIs, database schemas, and configuration formats may change between releases. Review the [security considerations](#security) before deploying to production.\n\n## Contents\n\n- [Quick Start](#quick-start)\n- [Why teams adopt Mission Control](#why-teams-adopt-mission-control)\n- [Use-case recipes](#use-case-recipes)\n- [Getting Started with Agents](#getting-started-with-agents)\n- [Documentation](#documentation)\n- [Features](#features)\n- [Architecture](#architecture)\n- [API Reference](#api-reference)\n- [Development](#development)\n- [Troubleshooting](#troubleshooting)\n- [Security](#security)\n- [Built with Mission Control](#built-with-mission-control)\n- [Roadmap](#roadmap)\n- [Contributing](#contributing)\n- [Support](#support)\n- [License](#license)\n\n\u003Ctable>\n\u003Ctr>\u003Ctd>\u003Cb>32 panels\u003C\u002Fb>\u003C\u002Ftd>\u003Ctd>Tasks, agents, skills, logs, tokens, memory, security, cron, alerts, webhooks, pipelines, and more — all from a single SPA shell.\u003C\u002Ftd>\u003C\u002Ftr>\n\u003Ctr>\u003Ctd>\u003Cb>Real-time everything\u003C\u002Fb>\u003C\u002Ftd>\u003Ctd>WebSocket + SSE push updates with smart polling that pauses when you're away. Zero stale data.\u003C\u002Ftd>\u003C\u002Ftr>\n\u003Ctr>\u003Ctd>\u003Cb>Zero external deps\u003C\u002Fb>\u003C\u002Ftd>\u003Ctd>SQLite database, single \u003Ccode>pnpm start\u003C\u002Fcode> to run. No Redis, no Postgres, no Docker required.\u003C\u002Ftd>\u003C\u002Ftr>\n\u003Ctr>\u003Ctd>\u003Cb>Role-based access\u003C\u002Fb>\u003C\u002Ftd>\u003Ctd>Viewer, operator, and admin roles with session + API key auth. Google Sign-In with admin approval workflow.\u003C\u002Ftd>\u003C\u002Ftr>\n\u003Ctr>\u003Ctd>\u003Cb>Quality gates\u003C\u002Fb>\u003C\u002Ftd>\u003Ctd>Built-in Aegis review system that blocks task completion without sign-off.\u003C\u002Ftd>\u003C\u002Ftr>\n\u003Ctr>\u003Ctd>\u003Cb>Skills Hub\u003C\u002Fb>\u003C\u002Ftd>\u003Ctd>Browse, install, and security-scan agent skills from ClawdHub and skills.sh registries. Bidirectional disk ↔ DB sync.\u003C\u002Ftd>\u003C\u002Ftr>\n\u003Ctr>\u003Ctd>\u003Cb>Multi-gateway\u003C\u002Fb>\u003C\u002Ftd>\u003Ctd>Connect to multiple agent gateways simultaneously. Framework adapters for OpenClaw, CrewAI, LangGraph, AutoGen, Claude SDK.\u003C\u002Ftd>\u003C\u002Ftr>\n\u003Ctr>\u003Ctd>\u003Cb>Recurring tasks\u003C\u002Fb>\u003C\u002Ftd>\u003Ctd>Natural language scheduling (\"every morning at 9am\") with cron-based template spawning.\u003C\u002Ftd>\u003C\u002Ftr>\n\u003Ctr>\u003Ctd>\u003Cb>Claude Code bridge\u003C\u002Fb>\u003C\u002Ftd>\u003Ctd>Read-only integration surfaces Claude Code team tasks, sessions, and configs on the dashboard.\u003C\u002Ftd>\u003C\u002Ftr>\n\u003Ctr>\u003Ctd>\u003Cb>Agent eval & security\u003C\u002Fb>\u003C\u002Ftd>\u003Ctd>Four-layer eval framework, trust scoring, secret detection, MCP call auditing, and hook profiles (minimal\u002Fstandard\u002Fstrict).\u003C\u002Ftd>\u003C\u002Ftr>\n\u003C\u002Ftable>\n\n---\n\n## Quick Start\n\n### One-Command Install\n\n```bash\ngit clone https:\u002F\u002Fgithub.com\u002Fbuilderz-labs\u002Fmission-control.git\ncd mission-control\nbash install.sh --local     # or: bash install.sh --docker\n```\n\nAfter installation:\n\n```bash\nopen http:\u002F\u002Flocalhost:3000\u002Fsetup    # create your admin account\n```\n\nThe installer handles Node.js 22+, pnpm, dependencies, and auto-generates secure credentials. For Windows, use `.\\install.ps1 -Mode local` in PowerShell.\n\n### Manual Setup\n\n```bash\ngit clone https:\u002F\u002Fgithub.com\u002Fbuilderz-labs\u002Fmission-control.git\ncd mission-control\nnvm use 22 && pnpm install\npnpm dev                    # http:\u002F\u002Flocalhost:3000\u002Fsetup\n```\n\n### Docker Zero-Config\n\n```bash\ndocker compose up           # auto-generates credentials, persists across restarts\n```\n\n### Prebuilt Images\n\nThe project publishes multi-arch images to GHCR on main and version tags.\n\n```bash\ndocker pull ghcr.io\u002Fbuilderz-labs\u002Fmission-control:latest\ndocker run --rm -p 3000:3000 ghcr.io\u002Fbuilderz-labs\u002Fmission-control:latest\n```\n\nDocker Hub publishing is optional and may depend on org package visibility\u002Fsecrets. If `docker.io\u002Fbuilderz-labs\u002Fmission-control` is unavailable, use GHCR.\n\nFor production hardening (read-only filesystem, capability dropping, HSTS, network isolation):\n\n```bash\ndocker compose -f docker-compose.yml -f docker-compose.hardened.yml up -d\n```\n\n---\n\n## Why teams adopt Mission Control\n\n- Predictable orchestration: one dashboard for task flow, dispatch, quality gates, and audit trails.\n- Faster operator response: real-time agent\u002Ftask\u002Fsecurity telemetry without stitching tools together.\n- Local-first deployment: SQLite-backed stack with no mandatory Redis\u002FPostgres dependency.\n- Security by default: RBAC, trust scoring, secret detection, and hardened deployment profile.\n\n## Use-case recipes\n\n1) Stand up a local control center in 5 minutes\n- Run `bash install.sh --local`\n- Open `\u002Fsetup`\n- Create your first agent and task from the UI\n\n2) Run multi-agent workflows with quality gates\n- Register specialist agents (research, coding, reviewer)\n- Enable orchestration rules and quality review\n- Track handoffs end-to-end in the Kanban board\n\n3) Operate production safely\n- Deploy with `docker-compose.hardened.yml`\n- Configure `MC_ALLOWED_HOSTS` and TLS reverse proxy\n- Monitor trust score + security audit panels continuously\n\n4) Integrate existing CLI agents without re-platforming\n- Connect Claude Code\u002FCodex via CLI integration\n- Keep your current workflows while adding centralized observability and controls\n\n---\n\n## Getting Started with Agents\n\nRegister your first agent in under 5 minutes — no gateway required:\n\n```bash\nexport MC_URL=http:\u002F\u002Flocalhost:3000\nexport MC_API_KEY=your-api-key   # shown in Settings after first login\n\n# Register an agent\ncurl -X POST \"$MC_URL\u002Fapi\u002Fagents\u002Fregister\" \\\n  -H \"Authorization: Bearer \u003CMC_API_KEY>\" \\\n  -H \"Content-Type: application\u002Fjson\" \\\n  -d '{\"name\": \"scout\", \"role\": \"researcher\"}'\n\n# Create a task\ncurl -X POST \"$MC_URL\u002Fapi\u002Ftasks\" \\\n  -H \"Authorization: Bearer \u003CMC_API_KEY>\" \\\n  -H \"Content-Type: application\u002Fjson\" \\\n  -d '{\"title\": \"Research competitors\", \"assigned_to\": \"scout\", \"priority\": \"medium\"}'\n\n# Poll the queue as the agent\ncurl \"$MC_URL\u002Fapi\u002Ftasks\u002Fqueue?agent=scout\" \\\n  -H \"Authorization: Bearer \u003CMC_API_KEY>\"\n```\n\nFor the full walkthrough, see the **[Quickstart Guide](docs\u002Fquickstart.md)**.\n\n---\n\n## Documentation\n\n| Guide | What You'll Learn |\n|-------|-------------------|\n| [Quickstart](docs\u002Fquickstart.md) | Register an agent, create a task, complete it — 5 minutes |\n| [Agent Setup](docs\u002Fagent-setup.md) | SOUL personalities, config, heartbeats, agent sources |\n| [Orchestration](docs\u002Forchestration.md) | Multi-agent workflows, auto-dispatch, quality review gates |\n| [CLI Reference](docs\u002Fcli-agent-control.md) | Full CLI command list for headless\u002Fscripted usage |\n| [CLI Integration](docs\u002Fcli-integration.md) | Connect Claude Code, Codex, or any CLI tool directly |\n| [Deployment](docs\u002Fdeployment.md) | Production deployment, reverse proxy, VPS setup |\n| [Security Hardening](docs\u002FSECURITY-HARDENING.md) | Docker hardening, CSP, network isolation |\n| [Release Process](RELEASE.md) | SemVer policy, branch strategy, tag\u002Frelease checklist |\n| [API Reference](openapi.json) | OpenAPI 3.1 spec — 101 REST endpoints with Scalar UI at `\u002Fapi-docs` |\n\n### Gateway Optional Mode\n\nMission Control can run standalone without a gateway connection — useful for VPS deployments with firewall restrictions or when running primarily for project\u002Ftask operations:\n\n```bash\nNEXT_PUBLIC_GATEWAY_OPTIONAL=true pnpm start\n```\n\nTask board, projects, agents, sessions, scheduler, webhooks, alerts, and cost tracking all work without a gateway. Real-time session updates and agent messaging require an active gateway connection.\n\n### Project health files\n\n- [CONTRIBUTING.md](CONTRIBUTING.md) — contribution workflow and development standards\n- [SECURITY.md](SECURITY.md) — vulnerability disclosure and security policy\n- [CODE_OF_CONDUCT.md](CODE_OF_CONDUCT.md) — community conduct expectations\n- [CHANGELOG.md](CHANGELOG.md) — release history\n- [RELEASE.md](RELEASE.md) — release process and checklist\n- [LICENSE](LICENSE) — MIT license\n\n---\n\n## Features\n\n### Agent Management\n\nMonitor agent status, configure models, view heartbeats, and manage the full agent lifecycle from registration to retirement. Local agent discovery from `~\u002F.agents\u002F`, `~\u002F.codex\u002Fagents\u002F`, and `~\u002F.claude\u002Fagents\u002F`. Agent SOUL system with bidirectional workspace sync.\n\n![Mission Control Agents Panel](docs\u002Fmission-control-agents.png)\n\n### Task Board\n\nKanban board with six columns (inbox → assigned → in progress → review → quality review → done), drag-and-drop, priority levels, assignments, threaded comments, and inline sub-agent spawning. Multi-project support with per-project ticket prefixes.\n\n![Mission Control Tasks Panel](docs\u002Fmission-control-tasks.png)\n\n### Memory Knowledge Graph\n\nExplore agent knowledge through the Memory Browser, filesystem-backed memory tree, and interactive relationship graph for sessions, memory chunks, and linked knowledge files.\n\n### Skills Hub\n\nBrowse, install, and manage agent skills from local directories and external registries (ClawdHub, skills.sh). Built-in security scanner checks for prompt injection, credential leaks, data exfiltration, obfuscated content, and dangerous shell commands before installation. Supports 5 skill roots across `~\u002F.agents\u002Fskills`, `~\u002F.codex\u002Fskills`, project-local directories, and `~\u002F.openclaw\u002Fskills`.\n\n### Cost Tracking\n\nToken usage dashboard with per-model breakdowns, trend charts, and cost analysis. Session-level granularity powered by Recharts.\n\n### Security Audit & Agent Trust\n\nReal-time posture scoring (0-100), secret detection across agent messages, MCP tool call auditing, injection attempt tracking, and per-agent trust scores. Hook profiles (minimal\u002Fstandard\u002Fstrict) let operators tune security strictness per deployment.\n\n### Agent Eval Framework\n\nFour-layer evaluation: output evals (task completion scoring against golden datasets), trace evals (convergence\u002Floop detection), component evals (tool reliability with p50\u002Fp95\u002Fp99 latency), and drift detection (10% threshold vs 4-week rolling baseline).\n\n### Natural Language Recurring Tasks\n\nCreate recurring tasks with natural language like \"every morning at 9am\" or \"every 2 hours\". The built-in schedule parser converts expressions to cron and stores them in task metadata. A template-clone pattern keeps the original as a template and spawns dated child tasks on schedule.\n\n### Claude Code Integration\n\n- **Session Tracking** — Auto-discovers local Claude Code sessions from `~\u002F.claude\u002Fprojects\u002F`, extracts token usage, model info, cost estimates, and active status.\n- **Task Bridge** — Read-only scanner surfaces team tasks and configs from `~\u002F.claude\u002Ftasks\u002F` and `~\u002F.claude\u002Fteams\u002F` on the dashboard.\n- **Direct CLI** — Connect Claude Code, Codex, or any CLI tool directly without requiring a gateway.\n\n### Activity Feed\n\nReal-time activity stream across all agents, tasks, and system events. Filter by event type, agent, or time range.\n\n![Mission Control Activity Panel](docs\u002Fmission-control-activity.png)\n\n### Integrations\n\nOutbound webhooks with delivery history, retry with exponential backoff, circuit breaker, and HMAC-SHA256 signature verification. GitHub Issues sync with label\u002Fassignee mapping. Agent inter-agent messaging via the comms API.\n\n### Framework Adapters\n\nBuilt-in adapter layer for multi-agent registration: OpenClaw, CrewAI, LangGraph, AutoGen, Claude SDK, and generic fallback. Each adapter normalizes registration, heartbeats, and task reporting to a common interface.\n\n### Workspace Management\n\nMulti-tenant workspace isolation via `\u002Fapi\u002Fsuper\u002F*` endpoints. Create client instances, monitor provisioning jobs, and decommission tenants with optional cleanup. Each workspace gets its own isolated environment with dedicated gateway and state directory.\n\n---\n\n## Architecture\n\n```\nmission-control\u002F\n├── src\u002F\n│   ├── proxy.ts               # Auth gate + CSRF + network access control\n│   ├── app\u002F\n│   │   ├── page.tsx           # SPA shell — routes all panels\n│   │   ├── login\u002Fpage.tsx     # Login page\n│   │   └── api\u002F               # 101 REST API routes\n│   ├── components\u002F\n│   │   ├── layout\u002F            # NavRail, HeaderBar, LiveFeed\n│   │   ├── dashboard\u002F         # Overview dashboard\n│   │   ├── panels\u002F            # 32 feature panels\n│   │   └── chat\u002F              # Agent chat UI\n│   ├── lib\u002F\n│   │   ├── db.ts              # SQLite (better-sqlite3, WAL mode)\n│   │   ├── auth.ts            # Session + API key auth, RBAC\n│   │   ├── migrations.ts      # 39 schema migrations\n│   │   ├── scheduler.ts       # Background task scheduler\n│   │   ├── skill-sync.ts      # Bidirectional disk ↔ DB skill sync\n│   │   ├── skill-registry.ts  # Registry client & security scanner\n│   │   ├── agent-evals.ts     # Four-layer agent eval framework\n│   │   ├── security-events.ts # Security event logger + trust scoring\n│   │   └── adapters\u002F          # Framework adapters\n│   └── store\u002Findex.ts         # Zustand state management\n└── .data\u002F                     # Runtime data (SQLite DB, token logs)\n```\n\n## Tech Stack\n\n| Layer | Technology |\n|-------|------------|\n| Framework | Next.js 16 (App Router) |\n| UI | React 19, Tailwind CSS 3.4 |\n| Language | TypeScript 5.7 |\n| Database | SQLite via better-sqlite3 (WAL mode) |\n| State | Zustand 5 |\n| Charts | Recharts 3 |\n| Real-time | WebSocket + Server-Sent Events |\n| Auth | scrypt hashing, session tokens, RBAC |\n| Validation | Zod 4 |\n| Testing | Vitest (282 unit) + Playwright (295 E2E) |\n\n## Authentication\n\n| Method | Details |\n|--------|---------|\n| Session cookie | `POST \u002Fapi\u002Fauth\u002Flogin` — 7-day expiry |\n| API key | `x-api-key` header |\n| Google Sign-In | OAuth with admin approval workflow |\n\n| Role | Access |\n|------|--------|\n| `viewer` | Read-only |\n| `operator` | Read + write (tasks, agents, chat) |\n| `admin` | Full access (users, settings, system ops) |\n\n## API Reference\n\nMission Control exposes 101 REST endpoints documented via OpenAPI 3.1. Browse the interactive API docs at `\u002Fapi-docs` (Scalar UI) when running locally, or see [`openapi.json`](openapi.json).\n\n\u003Cdetails>\n\u003Csummary>\u003Cstrong>Core endpoints at a glance\u003C\u002Fstrong>\u003C\u002Fsummary>\n\n| Area | Key Endpoints |\n|------|---------------|\n| **Agents** | `GET\u002FPOST \u002Fapi\u002Fagents`, `POST \u002Fapi\u002Fagents\u002Fregister`, `POST \u002Fapi\u002Fagents\u002Fsync` |\n| **Tasks** | `GET\u002FPOST \u002Fapi\u002Ftasks`, `GET \u002Fapi\u002Ftasks\u002Fqueue`, `PUT \u002Fapi\u002Ftasks\u002F[id]` |\n| **Skills** | `GET\u002FPOST \u002Fapi\u002Fskills`, `GET\u002FPOST \u002Fapi\u002Fskills\u002Fregistry` |\n| **Security** | `GET \u002Fapi\u002Fsecurity-audit`, `GET \u002Fapi\u002Fsecurity-scan` |\n| **Evals** | `GET\u002FPOST \u002Fapi\u002Fagents\u002Fevals`, `GET \u002Fapi\u002Fagents\u002Foptimize` |\n| **Monitoring** | `GET \u002Fapi\u002Fstatus`, `GET \u002Fapi\u002Ftokens`, `GET \u002Fapi\u002Factivities` |\n| **Webhooks** | `GET\u002FPOST\u002FPUT\u002FDELETE \u002Fapi\u002Fwebhooks`, `POST \u002Fapi\u002Fwebhooks\u002Ftest` |\n| **Claude Code** | `GET \u002Fapi\u002Fclaude\u002Fsessions`, `GET \u002Fapi\u002Fclaude-tasks` |\n| **Pipelines** | `GET \u002Fapi\u002Fpipelines`, `POST \u002Fapi\u002Fpipelines\u002Frun` |\n| **Workspaces** | `GET\u002FPOST \u002Fapi\u002Fsuper\u002Ftenants`, `GET\u002FPOST \u002Fapi\u002Fsuper\u002Fprovision-jobs` |\n\n\u003C\u002Fdetails>\n\n## Environment Variables\n\nSee [`.env.example`](.env.example) for the complete list. Key variables:\n\n| Variable | Required | Description |\n|----------|----------|-------------|\n| `AUTH_USER` | No | Initial admin username (default: `admin`) |\n| `AUTH_PASS` | No | Initial admin password (auto-generated if unset) |\n| `API_KEY` | No | API key for headless access (auto-generated if unset) |\n| `OPENCLAW_CONFIG_PATH` | No* | Absolute path to `openclaw.json` |\n| `OPENCLAW_STATE_DIR` | No* | Exact path to the OpenClaw state directory (default: `~\u002F.openclaw`). Preferred over `OPENCLAW_HOME` — avoids double-nesting |\n| `OPENCLAW_HOME` | No* | Legacy alias — treated as *parent* home dir (`.openclaw` is appended). Use `OPENCLAW_STATE_DIR` when it already points to the state dir |\n| `MISSION_CONTROL_DATA_DIR` | No | Directory for all MC data files (DB, tokens, etc.). Use an absolute path with the standalone server to survive rebuilds. |\n| `MC_CLAUDE_HOME` | No | Path to `~\u002F.claude` directory |\n| `MC_ALLOWED_HOSTS` | No | Host allowlist for production |\n| `NEXT_PUBLIC_GATEWAY_OPTIONAL` | No | Run without gateway connection |\n\n*Required for memory browser, log viewer, and gateway features.\n\n---\n\n## Development\n\n```bash\npnpm dev              # Dev server\npnpm build            # Production build\npnpm typecheck        # TypeScript check\npnpm lint             # ESLint\npnpm test             # Vitest unit tests (282)\npnpm test:e2e         # Playwright E2E (295)\npnpm quality:gate     # All checks\n```\n\n### Diagnostics\n\n```bash\nbash scripts\u002Fstation-doctor.sh     # Installation health check\nbash scripts\u002Fsecurity-audit.sh     # Security configuration audit\n```\n\n## Troubleshooting\n\n| Problem | Fix |\n|---------|-----|\n| \"Internal server error\" on login | `pnpm rebuild better-sqlite3` (Node version mismatch) |\n| Docker: gateway not connecting | Set `OPENCLAW_GATEWAY_HOST=host.docker.internal` in `.env` |\n| Docker: browser WebSocket fails | Leave `NEXT_PUBLIC_GATEWAY_HOST` empty (auto-detected) or set to a browser-reachable hostname |\n| 404 on all pages | Clear Next.js cache: `rm -rf .next && pnpm dev` |\n| `AUTH_PASS` with `#` ignored | Quote it: `AUTH_PASS=\"my#pass\"` or use `AUTH_PASS_B64` |\n\nSee [docs\u002Fdeployment.md](docs\u002Fdeployment.md) for detailed troubleshooting.\n\n## Security\n\n- **Change all default credentials** before deploying\n- **Deploy behind a reverse proxy with TLS** for any network-accessible deployment\n- **Do not expose to the public internet** without configuring `MC_ALLOWED_HOSTS` and TLS\n- See [SECURITY.md](SECURITY.md) for vulnerability reporting\n\n\n---\n\n## Built with Mission Control\n\nTeams and projects using Mission Control in production. [Add yours!](https:\u002F\u002Fgithub.com\u002Fbuilderz-labs\u002Fmission-control\u002Fissues\u002Fnew?title=Showcase:%20[Your%20Project]&labels=showcase)\n\n| Project | Description |\n|---------|-------------|\n| [MUTX](https:\u002F\u002Fx.com\u002Fmutxdev) | Agent infrastructure platform — ported and extended Mission Control for multi-agent orchestration |\n| [Builderz](https:\u002F\u002Fbuilderz.dev) | AI agent fleet management across 32+ shipped products |\n\n> **Using Mission Control?** We'd love to feature you. Open an issue with the `showcase` label or tweet [@nyk_builderz](https:\u002F\u002Fx.com\u002Fnyk_builderz).\n\n## Roadmap\n\nSee [open issues](https:\u002F\u002Fgithub.com\u002Fbuilderz-labs\u002Fmission-control\u002Fissues) for planned work.\n\n- [ ] Agent-agnostic gateway support — connect any orchestration framework\n- [ ] **[Flight Deck](https:\u002F\u002Fgithub.com\u002Fsplitlabs\u002Fflight-deck)** — native desktop companion app (Tauri v2) with PTY terminal grid and system tray HUD\n- [ ] First-class per-agent cost breakdowns\n- [ ] OAuth approval UI improvements\n- [ ] API token rotation UI\n\n## Contributing\n\nContributions are welcome. See [CONTRIBUTING.md](CONTRIBUTING.md) for setup instructions and guidelines.\n\n## Support\n\nIf you find this project useful, consider supporting the open-source work:\n\n[![Buy Me A Coffee](https:\u002F\u002Fimg.shields.io\u002Fbadge\u002FBuy%20Me%20a%20Coffee-support-orange?logo=buymeacoffee)](https:\u002F\u002Fbuymeacoffee.com\u002Fnyk_builderz)\n\n**Solana:** `BYLu8XD8hGDUtdRBWpGWu5HKoiPrWqCxYFSh4oxXuvPg`\n\n\n---\n\n\u003Cdiv align=\"center\">\n\n**Need agent infrastructure built for your team?**\n\n[Builderz](https:\u002F\u002Fbuilderz.dev) builds production AI agent systems, trading infrastructure, and Solana applications — 32+ products shipped across 15 countries.\n\n[Get in touch](https:\u002F\u002Fbuilderz.dev) | [@nyk_builderz](https:\u002F\u002Fx.com\u002Fnyk_builderz)\n\n\u003C\u002Fdiv>\n\n\u003Cp align=\"center\">\n  \u003Ca href=\"https:\u002F\u002Fstar-history.com\u002F#builderz-labs\u002Fmission-control&Date\">\n    \u003Cimg src=\"https:\u002F\u002Fapi.star-history.com\u002Fsvg?repos=builderz-labs\u002Fmission-control&type=Date\" alt=\"Star History\" width=\"400\">\n  \u003C\u002Fa>\n\u003C\u002Fp>\n\n## License\n\n[MIT](LICENSE) © 2026 [Builderz Labs](https:\u002F\u002Fgithub.com\u002Fbuilderz-labs\u002Fmission-control)\n","Mission Control 是一个自托管的AI代理编排平台，用于调度任务、运行多代理工作流、监控成本和管理操作。其核心功能包括通过单一控制面板管理AI代理集群、实时更新数据、零外部依赖（仅使用SQLite数据库），以及基于角色的访问控制等。该平台采用TypeScript编写，并利用Next.js构建，确保了良好的开发体验与性能。Mission Control适用于需要高效管理和协调多个AI代理的企业或团队，尤其是在自动化流程、任务分配及成本跟踪方面有需求的场景中。",2,"2026-06-11 03:50:50","high_star"]