Agent-native tracing model with sessions, steps, tools and sub-agents as first-class concepts (not generic spans)
W&B Weave is listed under LLM Eval & Observability, in the AI Models & Local Execution category on Flocci AI Tools. Agent-native tracing model with sessions, steps, tools and sub-agents as first-class concepts (not generic spans). It is freemium — a usable free tier with paid plans above it, and it lives at wandb.ai.
W&B Weave is freemium: there is a free tier you can work in and paid plans above it. It is one of 391 freemium tools in the catalog, all labelled the same way so you are never surprised by a paywall.
W&B Weave does 3 things the catalog singles out: Agent-native tracing model with sessions, steps, tools and sub-agents as first-class concepts (not generic spans); pre-built safety/quality scorers for toxicity, bias, pii and hallucination detection out of the box; built on weights & biases' existing ml-experiment infrastructure, useful for teams already on w&b.
Arize Phoenix is the closest free alternative: it sits in the same LLM Eval & Observability sub-category and is free. Braintrust, Langfuse and Promptfoo also start free. The full list is on the alternatives page.
See the full list →