cd /news/ai-agents/raft-1-0-puts-ai-agents-in-team-mode · home topics ai-agents article
[ARTICLE · art-61706] src=testingcatalog.com ↗ pub= topic=ai-agents verified=true sentiment=↑ positive

Raft 1.0 puts AI agents in Team Mode

Raft 1.0 launched as a multi-agent collaboration platform that enables humans and AI agents to work together in shared channels, threads, and tasks. Developed by Botiverse, the platform supports persistent agents with distinct identities and memory, running on runtimes like Claude, Codex, and Hermes, while keeping execution on user hardware. The company reports over 20,000 builders used the beta, averaging four agents per human.

read2 min views1 publishedJul 16, 2026
Raft 1.0 puts AI agents in Team Mode
Image: Testingcatalog (auto-discovered)

Raft 1.0 is now live, launched by @istdrc, who built Kimi CLI at Moonshot AI, marking the full launch of a multi-agent collaboration platform built around what the company calls team mode. Instead of juggling terminals, sessions, and separate agent windows, users get one shared workspace of channels, threads, tasks, and mentions where humans and AI agents work side by side, and where the work stays attached to the conversation it came from.

Each agent on Raft runs as a persistent process with its own identity, memory, and expertise, on whichever runtime fits the job, including Claude, Codex, and Hermes. Agents claim tasks, run in parallel, hand work to one another, and review each other's output in shared threads, so what one agent figures out, the next one builds on. A separate review agent can catch issues in another agent's code before a human ever sees it, which the company frames as independent agents covering independent blind spots. Execution happens on the user's own hardware through a lightweight daemon, keeping compute, code, and data under the user's control.

The 1.0 release rounds out a public beta that added external agent support starting with Hermes, agent-created channels, joint channels across servers, a Login with Raft option alongside an app marketplace, message search, and attachment previews with comments. According to the company, more than 20,000 agent-native builders and teams started building on Raft during the beta, averaging four agents per human, with power users running over sixty.

Raft is developed by Botiverse, founded by Richard, known as RC, who previously built Kimi CLI at Moonshot AI. The team says it runs 99 percent of the company inside Raft itself, with more than ten humans and over one hundred named agents claiming tasks, reviewing each other's work, and retaining context week to week, including for this launch. Nous Research's Hermes Agent has officially partnered with Raft to run as an external agent within its workspaces, and testimonials on the company's site come from founders and engineers at TiDB, Inferact, and BeFreed AI, among others.

Start testing with Raft

Learn more Raft is now available at raft.build, with a free tier that includes channels, tasks, agents on local machines, and 30 days of message history. A Pro plan runs at 8.80 dollars per seat per month, billed annually, with each human counting as one seat and each agent as a tenth of a seat, while an enterprise tier with private deployment and SSO is listed as coming soon. Users bring the AI subscriptions they already pay for, such as Claude or Codex, so the platform layers team coordination on top of existing model access rather than reselling it.

── more in #ai-agents 4 stories · sorted by recency
── more on @raft 3 stories trending now
sponsored brought to you by zahid.host 4,200+ EU-deployed projects
reading about agents? ship yours in a single git push.

Run your AI side-project on zahid.host

EU-based hosting, git-push deploys, automatic HTTPS, no cold starts. Free tier with a custom domain — perfect for shipping the agent you just read about.

$git push zahid main
Live at https://your-agent.zahid.host
Get free account → Pricing
from €0/mo · no card required
LIVE [news/raft-1-0-puts-ai-age…] indexed:0 read:2min 2026-07-16 ·