# rl-env-use

> Open-source tool that builds verified RL environments and hillclimbed prompts from real cases mined from the web by Browser Use agents.

rl-env-use is an open-source project from Browser Use that turns a one-line skill description into a verified reinforcement learning environment. Browser Use agents mine real cases from the web, and the tool pairs the resulting dataset with a hillclimbed system prompt for the model being trained. It is MIT licensed and installs from the GitHub repository.

## What It Is

rl-env-use builds RL environments for any domain from real cases. It follows the workflow in Anthropic's "Automating eval design and hillclimbing", with one change: the tasks come from real cases that Browser Use agents find on the web. The README describes the goal as environments that frontier models do not saturate.

## How the Workflow Runs

- Browser Use agents find source materials (such as a trial protocol or a 10-Q) and the outcome published later.
- Gold answers are computed by code, and tasks that a frontier-model panel solves are rewritten to be harder.
- Bad tasks are rejected, including leaked answers, memorized outcomes and ambiguous prompts.
- A model's system prompt is hillclimbed using a train/test split, a noise floor and paired confidence intervals.
- The dataset can be exported for an RL trainer or served in code with `Env`.

## Example Results

The shipped example, envs/trial-forecast, contains 35 forecasts from 29 ClinicalTrials.gov trials whose results were posted after the models' training data. The README reports that a climbed Qwen 3.6 35B-A3B rose from 0.53 to 0.78 on held-out tasks, level with Opus 5.5. It notes that always answering 50% scores 0.75, so most of the gain is calibration.

## Setup Path

It can be set up by asking Claude Code, Codex or OpenCode to read install.md and SKILL.md. Manual install needs Python 3.11+, optionally Node.js 18+ for HTML reports, and Browser Use and OpenRouter API keys. Commands such as `rl-env-use create` and `rl-env-use climb` run the build and prompt-climb steps.

## Features
- Mines real cases from the web with Browser Use agents
- Writes hard tasks with code-computed gold answers
- Rewrites tasks that a frontier-model panel solves
- Rejects leaked answers, memorized outcomes and ambiguous prompts
- Hillclimbs system prompts with train/test split, noise floor and paired confidence intervals
- Exports datasets for RL trainers
- Serves environments in code via Env
- Optional HTML reports

## Integrations
Browser Use, OpenRouter, Claude Code, Codex, OpenCode, ClinicalTrials.gov

## Platforms
API, DEVELOPER_SDK, CLI

## Pricing
Open Source

## Links
- Website: https://github.com/browser-use/rl-env-use
- Repository: https://github.com/browser-use/rl-env-use
- EveryDev.ai: https://www.everydev.ai/tools/rl-env-use