# browser-use/rl-env-use

> Builds RL environments for any domain from real cases that Browser Use agents mine from the web, then hillclimbs a model's system prompt on a train/test split. Aimed at people training or evaluating LLM agents on tasks frontier models do not saturate.

- Magnitude: 3.3 out of 10 — Early signal
- Stars: 146 total · +0 stars measured 2026-10-23, 00:37–08:17 UTC, ≈ 11 by evening
- Star trust: star growth looks organic
- Category: AI agents · Language: HTML · License: MIT · Created: 2026-10-21 · Last push: 2026-10-21
- GitHub: https://github.com/browser-use/rl-env-use · Page: https://gitnova.dev/en/r/browser-use/rl-env-use

## Useful for

- Build an RL environment for predicting clinical trial outcomes from ClinicalTrials.gov registrations
- Hillclimb a model's system prompt with a train/test split and paired confidence intervals
- Export the mined dataset for an RL trainer or serve it in code via Env

## Why it’s here

- Star-counter measurements on 2026-10-23 (UTC), 00:37–08:17: 146 → 146 stars (+0). This is the change over that interval.
- Estimated end-of-day forecast: about +11 stars, using observed gains and the previous day.
- The repository is 2 days old and already has 146 stars. With less than two weeks of history, there's no usual pace to compare the spike against yet.
- Top new repositories this week: #161.

## Star trust

Star growth looks organic.

Star-trust labels are heuristics based on the repository’s behavior, not a check of every stargazer.

## Numbers

- Forks: 9
- Issues and pull requests: 6
- Watchers: 0
- Average over the last week: 49 per day
- Usual pace: too little history (under two weeks)
- Stars in the last hour (measured): 0

## Stars per day, last 3 days (oldest → newest, today is partial)

2026-10-21 … 2026-10-23: 110, 26, 0

## Magnitude by day, last 2 days

10-22 5.1, 10-23 3.7

## Spotted in now

- Top new repositories this week: #161

## More in this category

1. **Graphify-Labs/graphify** — 6.8 · Breakout · AI agents · Python · +458 stars measured 2026-10-23, 00:37–08:15 UTC, ≈ 1,319 by evening
   Turns any codebase, docs, SQL schemas, configs, and PDFs into a queryable knowledge graph. Works as a /graphify skill in Claude Code, Cursor, Codex, and Gemini CLI with local deterministic AST parsing.
   Full card: https://gitnova.dev/en/r/Graphify-Labs/graphify.md
2. **NVIDIA/OpenShell** — 6.5 · Breakout · AI agents · Rust · +340 stars measured 2026-10-23, 00:37–08:15 UTC, ≈ 972 by evening
   A safe, private runtime for autonomous AI agents: isolated sandbox containers governed by declarative YAML policies restricting filesystem, network, and process access. Manages credential injection for agents like Claude, Codex, OpenCode,…
   Full card: https://gitnova.dev/en/r/NVIDIA/OpenShell.md
3. **omnara-ai/omnara** — 5.9 · Breakout · AI agents · Go · +12 stars measured 2026-10-23, 00:37–08:15 UTC, ≈ 73 by evening
   Omnara is an open-source, self-hostable platform for running managed AI agents on any model and any machine, with tools, secrets, permissions, and streaming built in. It serves as an alternative to Claude Managed Agents and OpenAI's…
   Full card: https://gitnova.dev/en/r/omnara-ai/omnara.md
4. **google-research/harness2** — 5.9 · Cooling · AI agents · Python · +236 stars measured 2026-10-23, 00:37–08:15 UTC, ≈ 699 by evening
   A framework for recursive optimization of AI agent harnesses (prompts, tools, memory, skills) without fine-tuning model weights, with JobBench, LAB and WorkBuddy-Bench benchmarks.
   Full card: https://gitnova.dev/en/r/google-research/harness2.md
5. **DietrichGebert/ponytail** — 5.8 · Breakout · AI agents · JavaScript · +627 stars measured 2026-10-23, 00:37–08:15 UTC, ≈ 1,814 by evening
   A skill for AI coding agents (Claude Code, Codex, Copilot CLI, OpenCode) that enforces writing only the minimum necessary code via a laziness ladder: YAGNI, reuse, stdlib, native features. Benchmarks show ~54% less code and ~20% cheaper…
   Full card: https://gitnova.dev/en/r/DietrichGebert/ponytail.md

---

Magnitude (0–10) measures how fast and how unusually interest in a repository is growing right now. It is not a quality score.
Days are UTC. “So far today” is a fact; “expected by the end of the day” is a forecast.
Summaries and use cases are written by an LLM (DeepSeek V4.1 Flash) from the README and may be inaccurate: verify specific claims (benchmarks, speed, hardware) in the repository itself.
Data as of 2026-10-23 08:28 UTC, updated every 30 minutes.