Raft 1.0 launches with a team mode for coordinating multiple AI agents
hey_abusiddik · x · 2026-07-24
RC, the former Moonshot Kimi CLI builder, says he has been building Raft in public for four months and is now launching Raft 1.0.
The product’s pitch is a team mode for agents: instead of juggling terminals, sessions, and skills across separate tools, users get one workspace where multiple agents collaborate like a team while the human stays in control.
Related event: Ex-Moonshot Engineer Launches Raft 1.0 for Multi-Agent Collaboration(6 posts)→
More from coding & agent
- Infinitty app adds task tracking and MCP UI rendering for agents — jasonkneen · 2026-07-24
- Seven system design mistakes that keep AI agents from working reliably — goyalshaliniuk · 2026-07-24
- Markdown docs beat a vector DB for one agent’s knowledge base, at least at small scale — Old_Visual_6596 · 2026-07-24
- Built a local Qwen assistant for internal docs, now asking if companies would buy it — teriyaki_tofu1 · 2026-07-24
- Google codelab shows how to use parallel worktrees and resolve conflicts in Antigravity 2.0 — ksoonson · 2026-07-24
- Tokyo’s Agent Forge hackathon will bring AI builders together on July 25 — DavidBennett__ · 2026-07-24