Multi-agent Claude Code sessions are powerful but opaque. You can't see what agents are doing, which tasks are stuck, or what they're costing. TeamClaude adds a live dashboard and structured sprints: - Agent topology with status and live terminal views - Task board (list/kanban) with real-time tracking - Inter-agent message feed with protocol detection - Token cost tracking with model-aware pricing - Review loops with auto-escalation npx teamclaude init

Intercom — Startups get 90% off Intercom + 1 year of Fin AI Agent free

Startups get 90% off Intercom + 1 year of Fin AI Agent free

Hey Product Hunt! I'm Albert, the maker of TeamClaude. I built this because I kept running into the same problem: spinning up multi-agent Claude Code sessions and having zero visibility into what's actually happening. Agents would get stuck, duplicate work, or burn tokens on dead ends — and I wouldn't know until it was too late. TeamClaude gives you a real-time dashboard that shows exactly what each agent is doing, a structured sprint workflow with manager/engineer review loops, and token cost tracking so you know what you're spending. The key insight: AI agents need the same things human teams need — clear task assignments, review cycles, and someone watching the board. It's fully open source (MIT), works with a single npx command, and optionally integrates with tmux for live terminal views of each agent. Would love to hear your feedback — especially if you're running multi-agent coding workflows. What's your biggest pain point?

Intercom — Startups get 90% off Intercom + 1 year of Fin AI Agent free

Startups get 90% off Intercom + 1 year of Fin AI Agent free

TeamClaude

Real-time observability for Claude Code agent teams

Real-time observability for Claude Code agent teams