Skip to content
W&B Weave → EvalGuard

Keep your Weave calls. Add security and compliance. 

Weights & Biases Weave is a great LLM tracing + evaluation platform. EvalGuard imports your Weave calls — op names, token usage (OpenAI and Anthropic naming), cost, and exceptions all carry over — and puts a 300+-plugin red-team platform, a real-time input + output firewall, a BYOK gateway, and a SOC 2 evidence engine on the same data. No sign-up needed to run your first import.

SOC 2 evidence engineISO 42001 mappedEU AI ActGDPR

Honest positioning

Where Weave stops, EvalGuard keeps going

Weave is a first-class tracing + eval tool with a clean call tree and the W&B ecosystem behind it. EvalGuard overlaps on tracing and evals, then extends into the hosted security platform, runtime firewall, AI gateway, and compliance work you'd otherwise buy separately.

CapabilityW&B WeaveEvalGuard
LLM call tracing (trace tree) YesYes — OTLP + OpenInference ingestion, governed
Evaluation + scorers YesYes — 200+ scorers (LLM-as-judge, pairwise, rubric)
Native token / cost tracking YesYes — per-org cost ledger + budgets
Open source & self-hostingApache-2.0 incl. the trace server; no packaged self-host recipe in-repoYes — Apache-2.0 core, self-host available
Red-team & security scansSecurity scorers (prompt-injection, Presidio PII, Bedrock); no attack generatorYes — 300+ attack plugins + 100+ adversarial strategies
Runtime LLM firewall / guardrailsYes — guardrail scorers (prompt-injection, Presidio PII, Bedrock) + MonitorsYes — real-time input + output firewall
AI gateway / BYOK proxyYes — completions proxy + custom providers with key custodyYes — BYOK gateway, 15 proxied providers, similarity response cache, firewall on the same hop
SOC 2 evidence automationNot a documented product featureYes — live evidence engine + audit log

W&B Weave claims on this page were verified against their source github.com/wandb/weave @ c28011c940 (2026-08-07) — on 2026-08-10. Capabilities move; check their current docs before you decide. “SOC 2 evidence automation” describes a product capability, not any vendor’s own certification status.

Migration path

Bring your calls in one command

Everything stays local until you choose to run it — we never touch your W&B project. Export your calls, then convert them to neutral-shape spans with the EvalGuard CLI.

1
Export your Weave calls to JSON
# Python: calls = client.get_calls(include_costs=True) # pd.DataFrame([c.to_dict() for c in calls]).to_json('weave-calls.json', orient='records')
2
Convert to neutral spans with the CLI
npx @evalguard/cli import:traces --from weave weave-calls.json --output spans.json
3
Then red-team the app itself — keyless, no account
npx @evalguard/cli init --template security-scan # scaffolds a scan config npx @evalguard/cli scan:local <that-config> # no API key needed

Token usage keyed by model, per-model cost (with include_costs), and exceptions all map over — a failed call becomes an error span, a normal one stays ok. Then layer on red team, a runtime firewall, and a SOC 2 evidence engine.

Want a hand with the migration?

Send us your Weave export and we'll help you map it and validate the first import. Free.