Show HN: Raven – The harness of harnesses, built for RSI
Raven is a new 'harness of harnesses' designed for recursive self-improvement, allowing a host agent to orchestrate specialized agents for complex, autonomous project execution. The system has demonstrated the ability to complete end-to-end tasks, such as game development and simulation optimization, without human intervention.
Why it matters
Raven represents a shift toward autonomous AI systems capable of managing their own workflows and improving their own performance, which could significantly accelerate software development cycles.
Technical Report · Website · Documentation · 中文
One Surface, All Agents: Raven generates DAGs and orchestrates multiple specialized agents for complex tasks.
Raven is the harness of harnesses, built for recursive self-improvement (RSI). As a Host Agent , it brings built-in and third-party agents together to carry out complex tasks. Its modular architecture supports iterative improvement of Raven's own harness: proposing changes to how agents plan and act, evaluating those changes, and adopting improvements that pass validation. Powered by EverOS , Raven carries memory and context across sessions to support this process.
Built-in Agents: Raven-Research , Raven-Code , Raven-Design , and Raven-Oncall support research, coding, visual design, and unattended workflow automation.
Raven is pre-alpha. Interfaces and configuration may change quickly.
Raven's Performance on the Multi-Agent Orchestration Benchmark
Get smarter about the news
Sign up free for a feed built around what you actually care about, Dive Deeper research on any story, and the full text of every article.
Create free accountAlready have an account? Sign in