Keep your feedback scores. Add security and compliance.
TruLens is a great open-source feedback-function evaluation framework — the RAG triad and more. EvalGuard imports your TruLens records — inputs, outputs, token cost, and every feedback function score 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.
Honest positioning
Where TruLens stops, EvalGuard keeps going
TruLens is a first-class open-source eval framework — feedback functions and the RAG triad are genuinely good. EvalGuard overlaps on evals and feedback scoring, then extends into the hosted security platform, runtime firewall, AI gateway, and compliance work you'd otherwise buy separately.
| Capability | TruLens | EvalGuard |
|---|---|---|
| Feedback functions (RAG triad) | Yes | Yes — 200+ scorers incl. groundedness/relevance |
| Record + feedback logging | Yes | Yes — governed traces + eval runs |
| Token / cost tracking | Yes | Yes — per-org cost ledger + budgets |
| Open source & self-hosting | MIT; maintained by Snowflake's AI Observability team | Yes — Apache-2.0 core, self-host available |
| Red-team & security scans | Moderation / PII / toxicity feedback functions; no attack generator | Yes — 300+ attack plugins + 100+ adversarial strategies |
| Runtime LLM firewall / guardrails | Yes — @block_input / @block_output / @context_filter | Yes — real-time input + output firewall |
| AI gateway / BYOK proxy | None at 3fb807e (2026-06-02); not re-checked since | Yes — BYOK gateway, 15 proxied providers, similarity response cache |
| SOC 2 evidence automation | Not a documented product feature | Yes — live evidence engine + audit log |
TruLens claims on this page were verified against their source — github.com/truera/trulens @ 3fb807e (2026-06-02) — 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.
That commit is from June, so the gateway row says what was true at it rather than claiming to know today's answer.
Migration path
Bring your records in one command
Everything stays local until you choose to run it — we never touch your TruLens database. Export your records, then convert them to neutral-shape spans with the EvalGuard CLI.
# Python: records, _ = session.get_records_and_feedback()
# records.to_json('trulens-records.json', orient='records')npx @evalguard/cli import:traces --from trulens trulens-records.json --output spans.jsonnpx @evalguard/cli init --template security-scan # scaffolds a scan config
npx @evalguard/cli scan:local <that-config> # no API key neededEvery feedback function becomes a trulens.feedback.<name> score, token cost lands from cost_json, and a record error becomes an error span. Then layer on red team, a runtime firewall, and a SOC 2 evidence engine.
Want a hand with the migration?
Send us your TruLens export and we'll help you map it and validate the first import. Free.