Tamper Evident Python Packages

keel-verifier

Independent verifier for signed AI audit exports and Permit-spec evidence

tamper-signal

Tamper Signal: signed receipts for vibe-coded data pipelines. Proves nobody changed your data, and shows the exact link if they did.

halo-record

Tamper-evident runtime records for AI agents. Hash-chained, dependency-free, verifiable by anyone.

epi-recorder

Tamper-evident evidence infrastructure for AI agents. Capture, seal, verify, and audit AI decisions in a single portable .epi file.

atb-sdk

ATB bundle reader and verifier SDK

aetherproof

Tamper-evident cryptographic receipts for AI outputs - offline-verifiable (SHA-256 + Ed25519). Supports EU AI Act Article 12 record-keeping. Prototype of Signet.

provedex

Cryptographic evidence layer for AI agents. Ed25519-signed, SHA-256-chained audit logs anyone can verify offline.

ai-audit-trail

Cryptographically verifiable audit trail for AI systems — Ed25519 signed, hash-chained Decision Receipts with ISO 42001 / NIST AI RMF compliance. No blockchain, no SaaS.

colorless-audit

Authorize, gate, and prove every action your AI agent takes — tamper-evident, zero-dependency runtime trust layer for AI agents.

agent-pd

A police department for your Claude Code agents — a logging-only hook + CLI that audits the main agent and every subagent and reports rule offenses (permission bypass, out-of-scope & credential access, self-permissioning, disallowed tools, redundant, off-task) with quoted evidence. Catch-and-report, never blocks.

cortex-persist

Tamper-evident memory & decision lineage for AI agents. Cryptographic proof of what your agent knew. Powered by a hybrid Python/Rust (Direct-Silicon) core.

ragcompliance

Audit trail middleware for RAG pipelines in regulated industries

qp-capsule

Capsule Protocol Specification (CPS) — tamper-evident audit records for AI operations. Create, seal, verify, and chain Capsules in Python.

provara-protocol

Tamper-evident memory protocol for humans and AI agents. Ed25519 + SHA-256 + event sourcing. 74 tests. One dependency. Apache 2.0.

notaryos

Cryptographic receipt system for AI agent accountability. Tamper-evident, hash-chained receipts with Ed25519/HMAC signing.

audit-stream

Append-only governance event stream for the Kinetic Gain portfolio. Hash-chained for tamper-evidence, SSE for live tailing, REST for queries. Every portfolio repo is a producer.

provedex-pipecat

Cryptographic evidence layer for AI agents. Ed25519-signed, SHA-256-chained audit logs anyone can verify offline.

deponent

A governed sovereign agent kernel — make any local AI agent testify. Deny-by-default gate, macOS Seatbelt jail, tamper-evident hash-chained ledger, verifiable receipts. Apache-2.0, zero deps.

uatp

Signed receipts for AI-agent actions. Verifiable memory without trusting the runtime.

provedex-langchain

LangChain BaseCallbackHandler that signs every LLM and tool callback via the Provedex sidecar. Covers LangGraph by inheritance.

provara

MCP server — 10 tools, Ed25519 signing, deterministic state

maatora

Cryptographic, tamper-evident audit log for AI agents: canonical JSON, Ed25519 signing, Merkle log, FastAPI ingest, LangGraph middleware, Postgres store, HTML rendering.

lokryn-merkle-tree

Merkle tree and hash chain utilities for building tamper-evident audit logs in Python

sealvera

AI Decision Audit Logging — tamper-evident audit trails for any AI agent