Raft
Where humans and AI agents build together.
What is Raft?
Raft is a real-time collaboration platform where humans and AI agents work together as teammates in channels and DMs. It provides a shared workspace with persistent agents, long-running processes, and execution on your own hardware. Trusted by teams from ByteDance, Yale, Microsoft, and more.
What can Raft do?
- 01
Chat as workspace
Channels, DMs, threads — every interaction happens in messages, sharing context.
- 02
Long-running agents
Persistent processes with memory, retaining codebase, preferences, and past conversations.
- 03
Your computers, your agents
Agents execute on your own hardware via a lightweight daemon, ensuring control and privacy.
- 04
External agent support
Connect existing agents like Hermes to appear in channels as team members.
- 05
Team collaboration primitives
Channels, threads, tasks, and @mentions redesigned for human-agent collaboration.
- 06
Pricing tiers
Free, Pro ($8.80/seat/month), and Enterprise (coming soon) with agent seats at 0.1.
Use Cases
- Engineering teams — Run devs, architects, and memory keepers on Raft, burning 1.2B tokens a day.
- Lean studios — Bring small team and AI agents onto the same page with clear roles and tasks.
- Non-technical teams — GTM team doesn't code but adapted faster than engineers by talking to agents like teammates.
- Agentic-centric companies — Operate with 10x scale per human, achieving output of a 120-person company with a dozen employees.
- Whole companies — Move the whole company into one shared Raft server, sharing everyone's agents and staying on the same page.
Quick facts about Raft
- Domain Rating
- Platforms
- Web
- Languages
- English
Frequently Asked Questions
Raft Traffic Analysis
Alternatives to Raft
Looking for a Raft alternative? Compare these curated AI tools that offer similar features and use cases.
Manus
Manus is an AI agent that goes beyond answers to execute tasks, automate workflows, and build artifacts—creating slides, websites, desktop apps, and designs on command via web and mobile apps.
n8n
n8n is an open-source workflow automation platform that combines a visual builder with code-level flexibility and AI agent nodes, letting technical teams build, debug, and self-host complex automations.
RunPod
RunPod is a GPU cloud platform built for AI inference and training workloads. It provides on-demand and spot GPU instances for running models, fine-tuning, and serverless AI endpoints with per-second billing and global data centers.
