workspace

Mission Control

Open-source task management for the agentic era.
The command center for solo entrepreneurs who delegate work to AI agents.

Why Mission Control?

AI coding agents (Claude Code, Cursor, Windsurf) are powerful executors — but managing multiple agents across multiple projects is chaos. There's no shared task board, no inbox, no way to see who's working on what or whether they finished.

Mission Control gives your AI agents structure. Agents get roles, inboxes, and reporting protocols. You delegate work through a visual dashboard, they execute and report back. You stay in control without micromanaging.

How is this different from Linear, Asana, or Notion? Mission Control was built agent-first. Agents read and write tasks through a token-optimized API, report progress to your inbox, and ask you for decisions. You manage outcomes, not keystrokes. And it runs locally — no cloud dependency, no API keys, no vendor lock-in.

Features

• Eisenhower Matrix — Prioritize by importance and urgency with drag-and-drop between quadrants
• Kanban Board — Track work through Not Started, In Progress, and Done columns
• Goal Hierarchy — Long-term goals with milestone tracking, progress bars, and linked tasks
• Brain Dump — Capture ideas instantly, triage into tasks later
• Agent Crew — 5 built-in agents + create unlimited custom agents with unique instructions
• Skills Library — Define reusable knowledge modules and inject them into agent prompts
• Profiles — Named configurations for Claude Code with custom environment variables per agent
• Multi-Agent Tasks — Assign a lead agent + collaborators for team-based work
• Orchestrator — Run /orchestrate to spawn all agents on pending work simultaneously
• Autonomous Daemon — Background process that automatically polls tasks, spawns Claude Code sessions, enforces concurrency, and provides a real-time dashboard
• One-Click Execution — Press play on any task card to spawn a Claude Code session; live status indicators, success/failure toasts, and automatic completion (task → done, inbox report, activity log)
• Session Resilience — Agents that timeout or hit max turns automatically re-spawn continuation sessions, preserving progress in task notes and subtasks. Configurable max continuations per task and per inbox response
• Cost & Usage Tracking — Captures cost and full token usage (input, output, cache read, cache creation) from every Claude Code session; displayed on the Autopilot dashboard with per-task cost breakdown and running totals
• Failure Logging — Failed tasks generate task_failed activity events with error details, session count, and agent info. Failure reports are automatically posted to your inbox
• Inbox Stop Button — Stop an agent mid-response with a single click; kills the process tree and prevents continuation chains from spawning
• Continuous Missions — Run an entire project with one click; tasks auto-dispatch as others complete, respect dependency chains, and skip decision-blocked work. Real-time progress bar with stop button
• Loop Detection — Auto-detects agents stuck in failure loops; after 3 attempts, escalates to a user decision with options to retry differently, skip, or stop
• Token-Optimized API — Filtered queries, sparse field selection, 92% context compression (~50 tokens vs ~5,400)
• Inbox & Decisions — Full agent communication layer: delegation, reports, questions, and approvals