Introducing Proliferate.
An open source Mac app for working with all your coding agents at once- Claude Code, Codex, Gemini, OpenCode, Cursor- in one workspace.
Gonna be adding more entries to the leaderboard all week - let us know if youβd like to be added too!
Check it out at https://t.co/5bkFJO2cJx. Schedule a chat for custom benchmarks and environments for your use case.
Most benchmarks test agents on short-horizon reasoning, not real-world, long-running tasks with stateful environments.
To solve this, @agenthublabs is launching Benchmarks: one-click testing for your agents on realistic, economically valuable tasks, starting with E-Commerce and CRM automations. No infra setup needed.
Try it for free at https://t.co/jqq3BUJ5K8.
Scootered all over SF with @ymkallel and @sandrtang to make this install happen.
Featuring @agenthublabs (YC S25) .
Excited to be working together to sim and eval our AI agents!
AgentHub (@agenthublabs) is the missing layer in the AI agent stack: simulation and evaluation for complex agents.
Agents today use tools, APIs, browsers, file systems, and more - AgentHub builds realistic sandbox environments and the infra to easily test them.
AgentHub just launched on @ycombinator's Launch YC!
π» AgentHub π - The Staging Environment for your AI Agents. We help you evaluate and improve your agents. Check it out: https://t.co/LPw9tD4Z7K