Agent infrastructure
gym
nvidia-nemo/gym
A library providing environments and infrastructure for evaluating and improving models and agents at scale. Supports reproducible benchmarks and reinforcement-training integrations across multiple frameworks for AI researchers.
Topics
Related projects
cleanrl10.7kHigh-quality single-file deep RL library covering PPO, DQN and SAC, focused on readability and reproducible experiment management.
mlflow28.8kAn open-source AI engineering platform for tracing, evaluating, monitoring, and governing LLMs, agents, and models.
promptfoo27.1kAn open-source CLI and library for evaluating prompts and red-teaming LLM apps, with CI integration and model comparisons.
ragas16.2kAn evaluation toolkit for LLM apps offering objective metrics, test generation, and production feedback loops.
RagaAI-Catalyst16.2kAn observability and evaluation platform for LLM agents, offering tracing, debugging, analytics, and guardrails.
cubesandbox13.2kAn instant, secure MicroVM sandbox service for AI agents with millisecond startup, hardware isolation, and E2B compatibility.