The ultimate guide to multi-harness RL
Train open models with RL inside real agent harnesses
Open RL Environments at Scale
Train open models with RL inside real agent harnesses
Answer dataset questions and view scoring results
Explore and manage tasks in the Harbor agentic environment
Run OpenCode tasks and view grading results
Explore the MiMo-V2.6 RL environments and run rollouts
Explore a watercolour painting environment with text
Transcribe images to LaTeX and receive accuracy score
Visualize RL agent comparison metrics in a web dashboard
Visualize SFT experiment metrics from a JSON file
GRPO training logs for Qwen3.5 on SmolDataEnvs
Extract text, layout, or answer questions from documents
Transcribe multilingual audio and get instant scoring
Cross-model RL training, evaluation, and run history
From an idea to a trained 4B, with the dead ends left in
Display interactive tracking data visualization
Show real-time I/O activity dashboard
Every painting of every run, with the sketch that made it
Display interactive visualization of tracking data
Interact with a GeoGuessrβstyle environment through custom actions
Show interactive tracking dashboard for your tasks
Show an interactive tracking dashboard