Rl Environments Python Packages

harbor-rewardkit

Framework for evaluating and improving agents

repo2rlenv

Turn any repository into verifiable RL environments for coding agents - Harbor tasks you can train on, evaluate and share on the Hugging Face Hub

harbor-langsmith

Framework for evaluating and improving agents

harbor-atif2otel

Framework for evaluating and improving agents

bohrin

Check the checker: an open standard for testing the graders of RL environments, with proof before every accusation.

agentsynth-ai

Outcome-verified agent trajectories, benchmarks, and RL environments — with a live leaderboard and a CI gate for your agents. Offline-first, MIT.

helx

Interoperating between (Deep) Reiforcement Learning libraries

tasksmith

Turn any repository into verifiable RL environments for coding agents - Harbor tasks you can train on, evaluate and share on the Hugging Face Hub

envrax

Gymnasium-style API standard for RL environment creation in JAX

crucible-rl

Turn any real software into a replayable RL environment for training AI agents — deterministic replay, verifiable rewards, TRL & verifiers adapters.

mobile-env-rl

A Universal Platform for Training and Evaluation of Mobile Interaction

verifiable-labs-envs

Open-source SDK (Apache-2.0): RL environments, conformal calibration, a TRL-compatible reward function, the Lean 4 formal track, and the verifiable/vlabs CLI.

vlabs-calibrate

Open-source SDK (Apache-2.0): RL environments, conformal calibration, a TRL-compatible reward function, the Lean 4 formal track, and the verifiable/vlabs CLI.

verifiable-labs

Open-source SDK (Apache-2.0): RL environments, conformal calibration, a TRL-compatible reward function, the Lean 4 formal track, and the verifiable/vlabs CLI.

rl-envdoctor

Adversarial QA for LLM-RL environments: find out what reward an empty answer earns. Model-free, zero API cost.

helx-base

Interoperating between (Deep) Reiforcement Learning libraries

verifiable-labs-code-humaneval-multiturn

Open-source SDK (Apache-2.0): RL environments, conformal calibration, a TRL-compatible reward function, the Lean 4 formal track, and the verifiable/vlabs CLI.

verifiable-labs-code-humaneval

Open-source SDK (Apache-2.0): RL environments, conformal calibration, a TRL-compatible reward function, the Lean 4 formal track, and the verifiable/vlabs CLI.