A sealed file for every agent run

EPI turns an AI agent run into a portable .epi evidence file: steps, hashes, Ed25519 seal, optional policy analysis, optional SCITT / timestamp. You verify offline — no dashboard required to trust the seal.

The loop

1. Record — record() or wrap OpenAI / LangChain / LiteLLM while the agent runs.
2. Seal — SHA-256 of members + Ed25519 over the canonical manifest → one .epi.
3. Verify — epi verify or browser private check (file not uploaded).
4. View — epi view opens a forensic timeline in any browser.

Three different questions

What a .epi is

Envelope-v2 polyglot: valid HTML + ZIP payload. Contains manifest.json, hash-chained steps.jsonl, environment, optional analysis, embedded viewer. Change one byte and the signature fails.

Verify modes

• Claims / insurers — epi verify file.epi --policy strict (org-pinned sealer required).
• Offline CLI (dev) — epi verify file.epi · unpinned identity is WARN · UNVERIFIED IDENTITY.
• Private browser — file stays in the tab · /verify/
• Full report — upload to EPI servers · plan quota · deeper hosted report.

See also on this site

• Trust model — seal · identity · policy · SCITT notes
• Integrations — OpenAI, LangChain, pytest, …
• Use cases — where agent decisions need a file

Depth (GitHub)

• Complete product guide
• Policy & fault analyzer
• Known limitations
• Pilot guide

Try on home Open verify tool →