← Latest products

I built an integration for RL training of browser agents for everyone

Our library for RL environments + evals. This integration allows for scalable evals and training of browser agents with hosted Prime Intellect eval + training pipelines and headless browser infrastructure on Browserbase to RL train browser agents with LoRA.

LibraryOpen source

4,763 stars · GitHubexternal site

Visit github.comexternal site

Reactions (1)

Similar products

by description similarity

  1. ART

    github.com

    a new open-source RL framework for training agents

    Hacker News116 pts

  2. I RL-trained an agent that trains models with RL (for ~$1.3k)

    github.com

    RL-training an AI agent to RL-train AI agents.

    Hacker News107 pts

  3. Pardus Browser- a browser for AI agents without Chromium

    github.com

    A browser designed for agent

    Hacker News16 pts

  4. Agent-skills-eval

    github.com

    Test whether Agent Skills improve outputs

    Hacker News79 pts

  5. SkillGraph

    github.com

    Open-source agentic framework with skills instead of tools

    Hacker News19 pts