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 — then adds hosted red-team scans (300+ plugins), a runtime LLM firewall, an AI 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 | Yes | Yes — Apache-2.0 core, self-host available |
| Red-team & security scans | Not offered | Yes — 300+ attack plugins with threat-feed sync |
| Runtime LLM firewall / guardrails | Not offered | Yes — real-time input + output firewall |
| AI gateway / BYOK proxy | Not offered | Yes — BYOK gateway, 15 proxied providers, semantic cache |
| SOC 2 evidence engine | Not offered | Yes — live evidence engine + audit log |
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 scan # 300+ red-team attacks on your migrated dataEvery 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.