Agent building and orchestration

Docker Compose Agents
Build and orchestrate AI agents using Docker Compose
Coding assistants and Workspaces
VS Code AI Toolkit
Develop AI agents and apps using the lightweight VS Code extension.
Evaluation and monitoring

LM evaluation harness
Benchmark models with LM evaluation harness for reproducible, large-scale LLM evaluation.
Weave
Weave
Debug, evaluate, and improve LLM applications with real-time observability and experimentation.




















