CAIN-42 MCPGate

AGENTIC AI 75 · #4

Machine-checkable security proofs

Google reported an agentic framework generating Lean proofs of specified security properties in code underlying Signal's cryptographic protocol.

Last reviewed 2026-11-11

Agentic AI 75 / #4

LIVEMoat 4 · Execution Provenance & AttestationBundle · Code & ProofStream 5

2026 status: Vendor-reported research demonstration · Category: Formal verification

The 2026 development

Google reported an agentic framework generating Lean proofs of specified security properties in code underlying Signal's cryptographic protocol.

The governance gap

A proof is only as good as the statement it proves, and an agent can quietly weaken the statement, the assumptions or the build that produced the artifact. The chain from source to checked proof has to be reproducible.

Where CAIN-42 fits: Moat 4 — Execution Provenance & Attestation

Core question: Can we prove what actually happened? Hash-chained, signed records binding decision to execution to observable effect.

Treat the proof as evidence with a subject: bind the exact source revision, the specification, the toolchain, the checker output and the signer. CAIN's VeriCoding KEYSTONE already does this for a Python subset with Z3, and refuses a proof when the checker does not run.

How the wiring works

  1. Pin the source revision and the specification text before the agent starts.
  2. Compile the target into the checker's logic and record the compiler output digest.
  3. Run the checker; UNSAT is a proof only for the recorded statement, never for the whole application.
  4. Sign the bundle and embed a verifier that imports no CAIN code.

What is real today

LIVE A public route in this deployment exercises this mechanism today, within its stated scope.

The hosted Z3 proof covers a bounded Python subset and a stated property. It is not a Lean proof, not a whole-application proof, and not a claim about Signal.

Component in this repositoryWhat the module says it is
vericoding-gate/expr_compiler.pySafe Python-subset -> Z3 compiler.
cain/cain_z3_verifygate.pyCAIN Trust Fabric - Formal Z3 SMT Semantic Verification Gate (Phase 3)
keystone/vericoding.pyVeriCoding KEYSTONE: a real Z3 proof of a bug, Claude's rewrite, a real Z3 proof of the fix, signed.
cain/cain_proof_carrying_code.pyCAIN Proof-Carrying Code -- static admission check plus Z3-checked arithmetic contracts.

Descriptions are the first line of each module's own docstring, read without importing it. A module path is a pointer into this repository, not a hosted endpoint. Its existence is checked by the test suite; its status for this use is the label above.

Check it yourself

Commercial package

OfferProof-Carrying Change Review
BuyerCryptography teams, protocol vendors, safety-critical software
Price (proposal)$5,000–$15,000 per proof review
BundleCode & Proof — Prove the fix, not just the diff.
Operator streamStream 5 of the 10-stream operator playbook

Platform engineering, AI coding-tool vendors, security engineering is the bundle buyer. The entry offer for this bundle is Fabrication audit or long-run engineering attestation; the range is $1,500–$6,000 per audit; $2,500–$4,000/month retainer. A price on this page is a proposal, not a validated rate, and no customer is claimed.

Buy this as a product or service

CAIN-A75-004 — Proof-Carrying Change Review DELIVERABLE

A bounded engine run on the buyer's sample: findings, a written report, and a SHA-256 artifact manifest. The manifest is unsigned: it is not a signature and not an attestation.

Kind: Assessment · Price (proposal): $5,000–$15,000 per proof review · Lead time: 5 business days.

Open the product page · all 75 products

What this page does not claim

What this page is not. CAIN-42 is not affiliated with, endorsed by, integrated into, or shipped with the organisation named in the 2026 item. The item is public context; the page describes how CAIN-42 would govern that class of capability. No page here claims a customer, a partnership, a certification, a patent, or a production integration. Prices are proposals. Built by a three-person team.

← #3 Closed-loop experimental discoveryAll 75#5 Open-world multi-agent mathematical discovery →