The universal bridge between agents and environments — evaluate, RL-train, and trace any agent, in any sandbox, on any model.
Like Agentix-Project/Agentix, 0 likes 0 Bookmark Agentix-Project/Agentix, 0 bookmarks 0 Research infra for creating RL environments, post-training, and evals.
Like benchflow-ai/benchflow, 0 likes 0 Bookmark benchflow-ai/benchflow, 0 bookmarks 0 Scalable, Composable Reinforcement Learning for Real-World Agents with Bedrock AgentCore.
Like awslabs/agentcore-rl-toolkit, 0 likes 0 Bookmark awslabs/agentcore-rl-toolkit, 0 bookmarks 0 AgentX python SDK. Build multi-agent AI workforce. Run evaluation. Trace your agent. Full Observability.
Like AgentX-ai/AgentX-Python, 0 likes 0 Bookmark AgentX-ai/AgentX-Python, 0 bookmarks 0 Creating realistic RL environments requires collaboration between researchers, engineers, and domain experts across many dimensions: artifacts, environments tools, dynamism of the environment, reproducibility, and more. There is no open source framework for building these environments effectively. Until now.
Like scaleapi/agentenv-framework, 0 likes 0 Bookmark scaleapi/agentenv-framework, 0 bookmarks 0 Evaluate and improve models and agents using environments
Like NVIDIA-NeMo/Gym, 0 likes 0 Bookmark NVIDIA-NeMo/Gym, 0 bookmarks 0 RL environments + evals for AI agents. Define once, train anything.
Like hud-evals/hud-python, 0 likes 0 Bookmark hud-evals/hud-python, 0 bookmarks 0 Framework for evaluating and improving agents
Like harbor-framework/harbor, 0 likes 0 Bookmark harbor-framework/harbor, 0 bookmarks 0 Drive OSS standards and tools for data curation and evaluation creation for state of the art AI agents
Like The-AI-Alliance/cube-harness, 0 likes 0 Bookmark The-AI-Alliance/cube-harness, 0 bookmarks 0 
