Open source · execution receipts for AI agents

Vitnify your agents.

Logs tell you what your agent did. Vitnify proves it — a cryptographic receipt of every run, reproducible bit-for-bit by anyone, long after it happened.

input
chat · API
event · agent
wrapped by vitnify
the model runs, step by stepidle
vitnify records the exact logits at every step — not just the token the model picked — so the whole run recomputes bit-for-bit, and every tool call is allowed or blocked at the wall.
Receipt
········
bit-for-bit
sealing…
one run in — one receipt out
Contain what an agent may do Replay any run exactly Certify what happened Verify offline, no secrets drop-in: LangGraph · MCP

Capabilities

Everything a run needs to be provable.

vitnify isn't detection. It gives you the primitives to contain an agent, reproduce exactly what its model computed, and prove it to anyone — the receipt is an execution certificate under the hood.

Capability containment

Scope every tool an agent may touch. Ungranted actions are structurally unreachable — even to a fully compromised agent.

Deterministic replay

Re-run any past run and get the identical result. Reproduce an incident exactly, for debugging or forensics.

Bit-for-bit receipts

Bind the model's exact computation, every tool call, the results, and their order into one tamper-evident, signed object.

Offline verification

Anyone can verify a receipt with no model, no network, and no secret. Integrity is third-party checkable.

Runs bit-identical anywhere

The recompute reproduces exactly across CPU vendors and instruction sets — your proof isn't tied to one machine.

Drop-in integration

Wrap existing LangGraph and MCP agents. No changes to your agent logic, no new runtime to adopt.

Validated: three models across two architecture families reproduce bit-identically on Apple, Arm, Intel, and AMD, and hold against an 18-case attack matrix — detailed in the paper.

Open source

Built in the open. Yours to verify.

# wrap any LangGraph or MCP agent
from vitnify import Session

with Session(policy="tickets.yaml") as s:
    result = s.run(agent, task)

# -> a signed, offline-verifiable receipt
s.receipt.verify()      # True
s.receipt.recompute()   # bit-for-bit, any CPU
  • LicenseApache-2.0 — open core, no lock-in.
  • Enginevitni-tensor, a no_std Rust crate. 103 unit tests, 5 quant kernels + F32.
  • IntegrationsLangGraph and Model Context Protocol, no agent-logic changes.
  • Signinged25519 self-verifying receipts; TPM optional.
  • PaperReconstructable Execution Certificates for Tool-Using AI Agents.

Use cases

Where receipts matter.

Anywhere the honest answer to “what did the agent actually do?” has to survive scrutiny — weeks or months after the run, without taking anyone's word for it.

§

Regulated AI decisions

A lending, healthcare, or trading agent makes a call. Later a regulator or auditor asks exactly what the model computed. Replay the run and show the same logits and the same tool calls — not a screenshot of a log.

reproduce, don't trust

Incident forensics

When an agent run goes wrong, reconstruct it bit-for-bit from its receipt instead of reverse-engineering what happened from partial logs. Debug the actual run, not an approximation of it.

reproduce, don't trust

Agent-to-agent trust

One agent hands work to another. Instead of trusting it, the receiver verifies the receipt offline — no shared secret, no call home — and only builds on results it could reproduce itself.

reproduce, don't trust

Compliance evidence

A tamper-evident audit trail where one changed byte breaks the seal. Keep receipts as durable proof that a control was actually enforced at the wall — not merely written to a log that could be edited.

reproduce, don't trust

Pricing

Open core.

The engine, the receipt format, and offline verification are open source and free forever — you can always check a receipt yourself. The paid tier is for when a counterparty wants a trusted name to have vouched for it too.

Open source

Free · Apache-2.0

The SDK, the vitni-tensor engine, the receipt format, and offline self-verification. Yours to run, read, and audit.

pip install vitnify
  • Wrap LangGraph & MCP agents
  • Bit-for-bit deterministic replay
  • Signed, offline-verifiable receipts
  • Verify yourself — no network, no secret

Verification Authority

Talk to us

The hosted vitnify-verified service countersigns your receipts against a pinned trust anchor, so third parties can confirm the authority vouched for them.

  • Countersigning against a pinned trust anchor
  • Third-party checkable attestation
  • Everything in Open source, included
  • Support & onboarding for your team

Verifying a receipt yourself is always free. The authority exists for the moment a counterparty wants more than your word — a name they already trust, standing behind the same math you can already check.

Blog

Blog.

Coming soon

Notes on reproducible inference, execution certificates, and what we're learning building vitnify in the open. We'd rather ship the first post than pad this page with filler.

Jobs

Jobs.

Hiring soon

No open roles yet — but that changes soon. If verifiable AI infrastructure in Rust and Python is your kind of problem, introduce yourself early and we'll keep you in the loop.

Stop hoping your logs are complete.
Start proving it.