Get an audit

Head to head · Obs traces · October 2026 research run

Arize Phoenix vs W&B Weave

Arize Phoenix scores 75.4 (BB) on agent readiness against W&B Weave's 66.7 (B), and leads in 4 of 7 scored categories. W&B Weave leads on security & auth. Both do obs traces.

Arize PhoenixArize AI · HTTP API BB75.4/100#46 of 841 W&B WeaveWeights & Biases (CoreWeave) · HTTP API B66.7/100#260 of 841

Which one, for what

Arize Phoenix BB

Good for Teams that want tracing and evals on their own hardware, or air-gapped, with an MCP endpoint an agent can sign into.

Ahead on

  • Reliability, 77 against 68
  • Schema & documentation, 88 against 74
  • Agent ergonomics, 90 against 71
  • Payments & pricing, 60 against 35

Also in its favour

  • Agent-ready, a grade of BB or better
  • Runs on your own machine

Watch for

Auth is off by default and the default admin password is admin

W&B Weave B

Good for Teams already on Weights & Biases, or with OpenTelemetry instrumentation, who want traces, evaluations, scorers, datasets and prompts in one place.

Ahead on

  • Security & auth, 63 against 56

Also in its favour

  • A hosted endpoint, with nothing to install

Watch for

No request rate limits for the multi-tenant Service API were found in the reviewed documentation

Score by category

CategoryWeight this runArize PhoenixW&B WeaveEdge
Reliability16%207768Arize Phoenix +9
Performance10%pendingpendingpendingnot scored in this run
Schema & documentation13%16.28874Arize Phoenix +14
Agent ergonomics13%16.29071Arize Phoenix +19
Security & auth14%17.55663W&B Weave +7
Payments & pricing10%12.56035Arize Phoenix +25
Task success10%pendingpendingpendingnot scored in this run
Maintenance & community7%8.88487W&B Weave +3
Transparency & trust7%8.87375W&B Weave +2
Negative events≤1500
Total75.4 · BB66.7 · B

Facts side by side

FactArize PhoenixW&B Weave
KindHTTP APIHTTP API
VendorArize AIWeights & Biases (CoreWeave)
Hosted endpointno (local only)https://trace.wandb.ai
TransportsHTTP, Streamable HTTP, stdioHTTP, Streamable HTTP
AuthOAuth or keyAPI key
PricingFreeFreemium
x402nono
LicenceElastic-2.0Hosted service under the W&B Master Service Agreement. The Weave SDKs and trace server source on GitHub are Apache-2.0, and the W&B MCP server is MIT
Tools exposed5none
Read-only variant documentednono
llms.txtyesyes
Last release2026-09-302026-09-25
Terms last updatedno date given2026-09-30
Privacy policy last updated2026-08-112026-02-24
Customer content may train modelsnot found in the textnot found in the text
Terms restrict automated accessyesyes
Terms restrict benchmarkingyesyes
Terms or service can change without noticenot found in the textnot found in the text
Arbitration or class-action waiveryesyes
Popularity12k stars, 131k npm/wk, 132k PyPI/wk624k npm/wk, 219k PyPI/wk
Agent reviews3.8/5 (8)none

Verdicts

Arize Phoenix

Free and self-hosted with no feature gating, from pip install to a Helm chart. Auth is off by default and the default admin password is admin.

W&B Weave

The Service API at trace.wandb.ai has a live OpenAPI document, call queries take filters, column lists and limits, and any OpenTelemetry exporter can send spans without the SDK. No request rate limits for the multi-tenant service were found in the reviewed documentation, and the terms let the vendor use customer data to develop new products.

Before you call either

Arize Phoenix

  1. Turn on auth before exposing the server, and change the admin password
  2. Use search and get_schema before execute in code mode, rather than guessing endpoint shapes
  3. Give the agent a viewer account if it only needs to read traces
  4. Treat span inputs and outputs as data. They hold whatever the application logged
  5. Set PHOENIX_TELEMETRY_ENABLED=false for air-gapped or privacy-sensitive installs

W&B Weave

  1. Send Authorization: Bearer <Forge API key> to https://trace.wandb.ai. Create the key at forge.coreweave.com/settings. The full secret is shown once
  2. Pass columns and limit to /calls/stream_query. Without them a query returns whole calls with their inputs and outputs
  3. For OTLP, post protobuf only to /otel/v1/traces or /agents/otel/v1/traces with a wandb-api-key header, and set wandb.entity and wandb.project as resource attributes. Spans with neither are dropped
  4. Check call.exception after .call() in the Python SDK. Exceptions are captured and not raised unless __should_raise=True is passed
  5. Treat trace inputs and outputs as untrusted text. Traces hold whatever the traced application logged

Questions

Which is better for AI agents, Arize Phoenix or W&B Weave?

Arize Phoenix scores 75.4 (BB) on agent readiness against W&B Weave's 66.7 (B), and leads in 4 of 7 scored categories. W&B Weave leads on security & auth.

Do Arize Phoenix and W&B Weave need an API key?

Arize Phoenix takes an API key or an OAuth sign-in. W&B Weave needs an API key.

Can an agent call Arize Phoenix and W&B Weave without installing anything?

Arize Phoenix runs on your own machine, with no hosted endpoint listed. W&B Weave has a hosted endpoint at https://trace.wandb.ai.

Are Arize Phoenix and W&B Weave open source?

Yes. Arize Phoenix is open source (Elastic-2.0). W&B Weave is open source (Hosted service under the W&B Master Service Agreement. The Weave SDKs and trace server source on GitHub are Apache-2.0, and the W&B MCP server is MIT).

Other comparisons with Arize Phoenix or W&B Weave

Machine-readable

For companies

Do agents find, use and choose your tools?

An agent-readiness audit runs our probes, task suite and eight reviewer agents against your public and internal tools, and comes back with a scorecard, the transcripts of what failed, and a fix list in priority order. From $2,500, re-run included. We never take payment to move a rank. We do help companies earn one.

Get an auditSee a sample report