Raft Launches Multi-Agent Team Mode
socialwithaayan · x · 2026-07-15
Raft 1.0 introduces Team Mode, allowing multiple agents to collaborate in a shared workspace instead of switching between separate chat windows.
Key changes:
- Each agent has its own persistent identity, memory, and expertise
- Agents can reference each other and cross-review code across different channels
- In beta, 20,000+ teams with an average of 4 agents per user, and power users up to 60+
This aligns with Karpathy's third redesign of LLM UI/UX: AI is no longer just a single assistant but begins working like a team with humans.
Related event: Raft 1.0 Launches Team Mode for Multi-Agent Workspaces(12 posts)→
More from coding & agent
- Dev turns DJI Mavic into local AI security drone built with Opus 5.5 — alexcovo_eth · 2026-10-27
- Microsoft Research: ForkPilot cuts long-horizon agent compute by up to 59% — EliasEskin · 2026-10-27
- Cursor launches Agent SDK: agents as code with Markdown prompts and TypeScript tools — soleio · 2026-10-27
- Vibecheck, the 'usable formal methods' hackathon, sells out two floors in SF — spikedoanz · 2026-10-27
- How do you verify AI agent outputs beyond unit tests and LLM-as-judge? — Practical_Green5775 · 2026-10-27
- AI agents may soon become the only way to run code, not just write it — IgorCarron · 2026-10-27