░██                                             ░██       ░██            
   ░██                                                       ░██            
░████████ ░█████████████  ░██    ░██ ░██    ░██    ░██ ░████████  ░███████  
   ░██    ░██   ░██   ░██ ░██    ░██  ░██  ░██     ░██░██    ░██ ░██    ░██ 
   ░██    ░██   ░██   ░██ ░██    ░██   ░█████      ░██░██    ░██ ░█████████ 
   ░██    ░██   ░██   ░██ ░██   ░███  ░██  ░██     ░██░██   ░███ ░██        
    ░████ ░██   ░██   ░██  ░█████░██ ░██    ░██    ░██ ░█████░██  ░███████

Autonomous multi-agent missions.

2.0

Turn any project into a mission-driven development environment. One config file, multiple AI agents, fully autonomous orchestration.

tmux-ide mission demo
$

Features

Milestone Gating

Sequential execution phases, each gating the next. Tasks only dispatch when their milestone is active.

Validation Contracts

Assertion-based verification with independent validation. Failed assertions auto-create remediation tasks.

Skill-Based Dispatch

Match task specialty to agent capabilities. Specialists get specialist work. Tasks wait for the right agent.

Knowledge Library

Shared learnings that persist across tasks. Architecture docs and tag-matched references inject into prompts.

Researcher Agent

Continuous internal auditing triggered by mission events. Writes findings to the library for future agents.

Live Metrics

Session duration, agent utilization, completion rates, retry rates. All computed in real-time.

Web Dashboard

Real-time KPIs, milestone timeline, agent performance table, validation status. Auto-refreshes.

Coverage Invariant

Every assertion in the contract must be claimed by at least one task before dispatch begins.

Multi-Agent

Claude Code, Codex, or any CLI agent. Prefix-matched detection works with platform-specific binaries.

Built-in Skills

5 templates: general-worker, frontend, backend, reviewer, researcher. Scaffold custom skills in seconds.

Services Registry

Centralized commands, ports, healthchecks in ide.yml. Injected into dispatch prompts for agent awareness.

File-Based Send

Long messages auto-route through dispatch files. No paste-mode issues with any agent TUI.

Live Dashboard

Real-time mission monitoring at localhost:6060

localhost:6060/project/my-app
session
2h 15m
tasks
12/12 done
agents
4 active
validation
100%
milestones
M1 done
M2 active 3/5
M3 locked
agents
Backend82%5 tasks
Frontend71%4 tasks
Validator45%3 tasks
recent events
2m task 007 completed by Backend
3m M2 activated
5m M1 validation passed
6m dispatched 008 to Frontend

How it works

Phase 01

Planning

The lead agent analyzes your mission, creates milestones, tasks, and a validation contract with testable assertions.

Phase 02

Execution

Tasks dispatch to skill-matched agents. Milestone gating ensures sequential phases. Knowledge accumulates as agents work.

Phase 03

Validation

An independent validator checks each assertion. Failed checks auto-create remediation tasks. The milestone loops until all pass.

Phase 04

Complete

All milestones validated. Mission marked complete. PR auto-created. Metrics and learnings persisted for next time.

Orchestrator

  • Mission lifecycle: planning → complete
  • Milestone gating with auto-progression
  • Skill-matched dispatch
  • Stall detection and retry with backoff
  • Agent heartbeat telemetry

Validation

  • Assertion-based contracts
  • Independent validator dispatch
  • Auto-remediation on failure
  • Coverage invariant enforcement
  • Blocked assertion tracking

Developer experience

  • Single command to start
  • Web dashboard at localhost:6060
  • REST API + SSE events
  • TUI widgets in tmux
  • Open source

Get started

One config. Multiple agents. Fully autonomous.