Six specialized autonomous agents working together like a real dev team. Genuine collaboration with observable decision-making, self-improvement, and defense-in-depth security.
Not LLM wrappers — actual team coordination
Lead routes tasks, prevents collisions, manages handoffs. Real role specialization.
Every decision in Discord. Lurk, intervene, redirect anytime. Full transparency.
Switch clients with kernel isolation. Perfect for agencies and consultants.
System agent updates trigger team-wide reload. No manual restarts.
Issues, PRs, Projects, CI/CD — full integration out of the box.
Team communicates in channels you control. Real conversation threads.
Autonomous agents can improve their own behavior — but safely. Every change goes through the same PR-based workflow you use for code.
Allowlist-only egress — autonomous agents can't exfiltrate data
Kernel-enforced boundaries between organizations
Per-agent authentication with scoped permissions
Autonomous agents only access assigned channels
CPU, memory, and container hardening
Defense-in-depth with 5 independent security layers. Each autonomous agent is isolated, authenticated, and resource-limited.
Choose your setup path
Get running in 2 minutes. Agents work but can't self-improve.
Fork first to enable self-improvement. System agent can create PRs.
BSL Licensed. Source available, free for development.