Raft 1.0 brings agent “team mode” to one workspace
hey_abusiddik · x · 2026-07-24
Raft 1.0 launches with a “team mode” for agents
RC, the creator of Kimi CLI at Moonshot, says he has spent the last four months building Raft in public and is now shipping Raft 1.0.
The product is designed to address a common pain point in agent workflows: when you run multiple agents, you end up juggling terminals, sessions, and skills yourself and can easily lose context. Raft’s answer is a single workspace where agents behave more like a team you message, while you stay in control.
The post frames the broader trend as moving from a single assistant to a coordinated set of specialized agents that can collaborate, review one another’s work, and retain context over time.
Related event: Ex-Moonshot Dev Launches Raft 1.0 for Multi-Agent Collaboration(7 posts)→
More from coding & agent
- Thorsten Ball on working with agents: run more evals, automate everything, use the best models — omarsar0 · 2026-10-27
- DeepMind paper: LLMs can't sample randomly on their own — pass random numbers from code instead — rohanpaul_ai · 2026-10-27
- BELL: Open-Source Stack Combines Browserbase, Eve, iMessage and Stripe Link for Personal Agents — jeff_weinstein · 2026-10-27
- Legora runs 2,000 parallel agent evals on Modal Sandboxes for legal AI — blelbach · 2026-10-27
- Two engineers rebuilt a FedEx supplier's billing core in 3.5 months vs an estimated 7-8 — alex_verem · 2026-10-27
- GPT-6.1 Terra scores 48 on AA Coding Agent Index at one-third the cost of GPT-5.6 Terra — ArtificialAnlys · 2026-10-27