wandb/weave

Health v2 · maintenance only

Adoption not part of the score

1124 stars · 166 forks observed · 2026-09-03

What it is AI-extracted, prompt v1, taxonomy v1, 2026-08-30, confidence not recorded

Weave is a Python/TypeScript toolkit by Weights & Biases for developing AI-powered applications, providing LLM tracing, agent observability, and evaluation tooling. It instruments LLM calls and arbitrary functions via decorators and OTel-compatible spans, logging inputs, outputs, and traces to the W&B platform.

Use cases

• trace and debug LLM calls and function inputs/outputs
• observe multi-turn agents built with OpenAI Agents SDK or Claude Agent SDK
• evaluate LLM app responses with LLM judges and custom scorers
• evaluate a RAG application
• send OpenTelemetry spans from an agent to a UI
• collect metrics and feedback about LLM applications in production

When to choose

• you need observability and tracing for LLM apps or agents
• you want rigorous, comparable evaluations with scorers and LLM judges
• you already use the Weights & Biases ecosystem
• you want autopatching integrations for popular agent SDKs

When to avoid

• you need fully self-hosted telemetry with no external service dependency
• your project is not LLM/AI related
• you cannot send data to the W&B cloud platform

Facets

library · maturity active

monitoring tracing testing analytics llm-inference agent-framework large-language-models machine-learning developer-tools monitoring python cross-platform llm-observability llm-evaluation tracing opentelemetry weights-and-biases genai-toolkit ai-agents nodejs

Member repositories

For agents

markdown · JSON · MCP: product_card(name="wandb/weave")