Discover 2 open source Agent Training repositories from GitHub, each with an analysis of what it does, key features, use cases and alternatives. Agent Training projects here are most often combined with AI Agents, Machine Learning and Python. Last updated November 11, 2026.
Uni-Agent is a Python framework for bringing existing agent harnesses into reinforcement learning, with verl integration for training long-horizon agents. It unifies agent tasks and sandbox execution, and collects trajectories for evaluation and training.
ActiveHealth 63/100
EnvHarness wraps frozen benchmark environments with composable Python layers that reshape starting states and agent interactions without changing task verifiers. It helps researchers target agent weaknesses and evaluate skills or reinforcement-learning policies across benchmarks.
NewHealth 26/100