Hugging Face Hub adds RL Environment category with 153 agent-ready environments
mervenoyann · x · 2026-10-17
Hugging Face's Hub now hosts RL environments as a first-class dataset category: 153 environments filterable by type, runnable with Harbor, Verifiers, OpenEnv and NeMo Gym. Trending entries include terminal-bench-2.1 (171k downloads), openai-math, ProgramGym, Nemotron-RL-ReasoningGym-v1, and PrimeIntellect's Multi-SWE-bench/Scale-SWE-Verified, covering math, coding and terminal agent training.
More from coding & agent
- Palo Alto Networks ships Cortex XCOR: AI SRE agent diagnoses alerts in under 3 minutes — shashib · 2026-10-17
- HF dev begs OpenAI/Anthropic to fix agents picking the wrong Chrome window — NielsRogge · 2026-10-17
- An agent negotiated a 3PL contract in 3 days, end to end — aarthir · 2026-10-17
- Gemini 3 vs Opus 4.5 vs GPT-5.1 vs Grok 4: same-prompt 3D diorama showdown — cedric_chee · 2026-10-17
- Reverse-engineering OpenAI Atlas browser's system prompt with Claude Code — DionysianAgent · 2026-10-17
- AI stock prompt series: find non-US accounts discussing US stocks early — bigaiguy · 2026-10-17