Raft 1.0: Multi-Agent Team Collaboration
rohanpaul_ai · x · 2026-07-16
Raft 1.0 has been released, focusing on turning multi-agent workflows into "team collaboration": each agent has its own identity, memory, and role, allowing them to work in parallel within the same workspace.
It highlights three main aspects:
- Threads record decisions, files, reviews, and to-dos for seamless continuity
- Different agents can challenge and review each other's work, reducing self-evaluation bias
- Humans remain in charge of prioritization, reviewing results, and making final decisions
The creator states that Raft currently features 100+ named agents, with 99% of internal tasks completed by agents. The beta has attracted over 20,000 builders.
Related event: Raft 1.0 Launches Team Mode for Multi-Agent Workspaces(12 posts)→
More from coding & agent
- IDA 9.5 ships Qualcomm Hexagon decompiler plus IDA MCP for AI-driven reverse engineering — OwariDa · 2026-10-27
- For OSS apps, proofs of concept — not PRs to one repo — may be the core primitive — dbreunig · 2026-10-27
- Hook everything into the Dot: a workaround to stretch ChatGPT subscription limits — teortaxesTex · 2026-10-27
- Jev launches people-search API for agents at $0.0089/lead, claiming 85% cheaper than Clay — alexcovo_eth · 2026-10-27
- Going through every compound engineering skill to decide where humans stay in the loop — kieranklaassen · 2026-10-27
- UCSB CS Prof. Xifeng Wang lands 3 grants worth $180K+ for practical agentic AI research — xwang_lk · 2026-10-27