W&B Weave by Weights & Biases (CoreWeave)
Tracing, evaluation and monitoring of LLM apps and agents, logged from Python or TypeScript code.
LLM observability and evals Official MCP server Open source
＋ Build a stack with W&B Weave Website Official pricing GitHub
Price
Free (open source)
hosted plans from $60/mo
Free tier
Yes
Free plan: $0/mo, 1 GB/mo Weave data ingestion
SDK downloads
—
npm weave · PyPI weave
Pricing
| Free tier | Free plan: $0/mo, 1 GB/mo Weave data ingestion |
|---|---|
| Cheapest paid plan | $60 a month |
| Usage price | Pro: 1.5 GB/mo included, additional data ingestion $0.10/MB; Enterprise: additional data ingestion $0.20/MB |
| Good to know | wandb.ai/site/pricing now redirects to CoreWeave Forge pricing. Weave SDK is open source; the hosted service is billed by data ingestion. |
From the official pricing page, checked Oct 10, 2026. Prices change: confirm before you buy.
Use it from an agent
| MCP server | Official: https://docs.wandb.ai/platform/mcp-server |
|---|---|
| npm | npm install weave |
| PyPI | pip install weave |
Alternatives to W&B Weave
| API | Free | Price | SDK downloads / wk | GitHub stars | MCP |
|---|---|---|---|---|---|
| Opik Platform for tracing, testing, and evaluating AI agents and LLM applications. |
25k spans/month, 60-day retention | Free plan · paid from $19/mo | — | — | |
| Pydantic Logfire Observability platform for AI agents, services, and infrastructure with tracing, logging, and metrics. |
10 million spans, logs, or metrics per month | Free plan · paid from $49/mo | — | — | |
| Arize AX Observability and evaluation platform for AI agents and LLM applications. |
10 issues/month, 25k trace spans/month, 1 GB... | Free plan · paid from $50/mo | — | — | |
| Arthur AI Monitor AI model performance and ship trustworthy agents with governance and observability. |
4 use cases, 7-day data retention, 5k jobs,... | Free plan · paid from $60/mo | — | — | |
| Braintrust Observability platform for AI applications with tracing, evaluation, and storage infrastructure. |
1 GB processed data/month, 10k scores/month,... | Free plan · paid from $249/mo | — | — | |
| Confident AI LLM evaluation and observability platform for testing and monitoring AI applications. |
Free Forever: 5 test runs/week, 1 GB-month... | Free plan · paid from $200/mo | — | — |