Raft Launches Team-Based Agent Mode
socialwithaayan · x · 2026-07-15
The founder of Raft introduced their newly released Team Mode: instead of prompting 5 identical chatbots simultaneously, it enables a group of agents to collaborate as a "team."
The core differences include:
- Each agent possesses its own persistent identity, memory, and expertise
- The goal is for AI to genuinely work alongside human teams
- This is described as the third major redesign direction for LLM UI/UX: shifting from a single assistant to a collaborative multi-agent paradigm
Related event: Raft 1.0 Launches Team Mode for Multi-Agent Workspaces(12 posts)→
More from coding & agent
- Chaining dependent MCP tool calls: no rollback, duplicate risk — agentrsdg · 2026-09-11
- DeepMind-led paper makes design docs the source of truth, code disposable — SMART regenerates in 1.5-3h for ~$100 — Roger_M_Taylor · 2026-09-11
- Agent-built classifier labels 192k docs for $0.70 vs $13-26 with frontier LLMs — vanstriendaniel · 2026-09-11
- MathModelAgent gains traction: auto-solves math modeling and writes a submission-ready paper — jihe520 · 2026-09-11
- alphaXiv open-sources OpenResearch to run parallel research agents with any model — alphaXiv · 2026-09-11
- DeskcommCRM: open-source AI sales CRM with native agents and WhatsApp hits 1k stars — melgarafael · 2026-09-11