Open-source trust infrastructure

Trust state that can recover.

EvidenceBound is a framework-agnostic runtime for binding agent outputs to evidence, provenance and policy — then verifying, invalidating and selectively recovering state without blindly continuing from stale trust.

Apache-2.0Open source
v0.3.0Published source release
Python 3.10–3.13CI-tested release source
Architecture

From evidence change to bounded recovery.

The core separates historical integrity from current applicability. A checkpoint can remain intact while becoming unsafe to reuse because evidence, provenance or policy changed.

01

Bind

Outputs are bound to evidence, provenance and versioned policy.

02

Verify

Deterministic verification produces explicit ALLOW, REVIEW_REQUIRED or BLOCK outcomes.

03

Invalidate

Changed, stale, missing or refuted evidence is handled explicitly rather than silently reused.

04

Contain

Dependency analysis computes the exact affected descendants and preserves unrelated branches.

05

Recover

Consequential actions fail closed until path-specific re-verification succeeds.

Public engineering evidence

Inspect the system, not the pitch.

EvidenceBound is pre-1.0. Claims on this page are intentionally limited to public source, documented behavior and reproducible engineering evidence.

Release

v0.3.0 source release

Tagged public source with Python 3.10–3.13 CI, clean-room installation, typing/build checks, benchmark acceptance, pip-audit and Bandit gates.

Trust artifacts

Deterministic & signed receipts

Checkpoint-binding proof receipts with provider-neutral signing contracts and an optional Ed25519 reference provider on current main.

Recovery

Durable restart semantics

Provider-neutral persistence plus crash-consistent SQLite restart/replay reference implementation on current main.

Interoperability

EBCJ-1 conformance

Language-neutral canonicalization vectors and property-based invariants support deterministic cross-runtime work.

Supply chain

SBOM & build attestations

Current main includes checksum/SBOM generation and trusted-main provenance and SBOM attestations.

Integration

Google ADK compatibility lane

Credential-free lifecycle compatibility CI against exactly Google ADK 2.7.0, without blanket framework compatibility claims.

Security model

Explicit trust boundaries.

EvidenceBound is designed to make reuse and recovery decisions inspectable. It does not convert cryptographic integrity into a claim that an upstream source is truthful.

What the runtime is built to enforce

  • Evidence, provenance and policy binding.
  • Deterministic tamper and applicability checks.
  • Exact dependency blast-radius computation.
  • Fail-closed gates for consequential actions.
  • Selective recovery with explicit re-verification.

What it does not claim

  • It is not a truth oracle for malicious upstream sources.
  • It does not detect every arbitrary runtime compromise.
  • It does not guarantee secure key custody or immutable storage.
  • It does not guarantee AI Act or other legal compliance.
  • It does not replace adversarial-ML or red-team systems.
Maintainer & collaboration

Built for independent scrutiny and serious integration.

RV

Ruslan Vrublevskyi

Maintainer · EvidenceBound Core

AI systems and trust-infrastructure builder based in Kyiv, Ukraine. Current EvidenceBound work focuses on provenance-bound agent state, deterministic verification, selective recovery, interoperability and externally verifiable engineering evidence.

Research & consortium collaboration

EvidenceBound is most useful as a complementary runtime-assurance layer alongside monitoring, red-team, adversarial-ML and security validation systems.

Runtime assuranceAgentic / autonomous AI
Post-detection containmentDependency-bound recovery
Verification & benchmarkingReproducible assurance artifacts
Open-source interoperabilityCross-runtime conformance
Independent validationSecurity review / external adoption