tamper-evident 开源项目推荐（493 个）

codenotary /immudb

immudb - 基于零信任的不可变数据库，支持 SQL/键值/文档模型，防篡改，具备数据变更历史

sipyourdrink-ltd /bernstein

用于CLI编码代理（Claude Code、Codex、Gemini CLI、+40 more）的审计级多代理编排。HMAC链式审计日志、签署的代理卡、每个工件的血统、空隙部署。你的合规团队会批准的协调者。https://bernstein.run

MaxHu-xuan /artifactproof

Verify that the PowerPoint you are about to deliver is exactly the PPTX that passed QA—locally, offline, and with tamper-evident evidence.

Cygnux-Labs /Tracekit

面向 AI 代理的防篡改追踪、策略门禁和交叉校验：查看代理做了什么以及为什么。

proninyaroslav /blink-comparison

Simplifies comparing photos of tamper-evident seals and patterns using your eyes

scalar-labs /scalardl

Scalable and practical Byzantine fault detection middleware for transactional database systems

moonrunnerkc /swarm-orchestrator

审核 AI 编码代理为了看起来完成而采取的捷径的拉取请求：放松测试、吞下错误、假重命名，总共 11 次检查。默认会标记为人类，或者如果你开启合并，会阻止合并。还可以把目标变成清单，只有在每次检定通过后才接受补丁。

BBVA /qed

The scalable, auditable and high-performance tamper-evident log project

bkuan001 /halo-record

Tamper-evident audit trails for AI agents: hash-chained Runtime Records, dependency-free, verifiable by anyone.

RomaLytar /yammi-audit-log

Laravel audit log & change history with real actor attribution (user / job / command / scheduler), cross-model change traces, time machine, tamper-evident hash chain, GDPR reports, anomaly detection, Slack/webhook alerts, multi-tenancy and an optional dashboard.

Cygnux-Labs /Tracekit-box

Micro-VM sandbox for AI agents: isolated, gated and auditable, to prove what your agents did

Cygnux-Labs /PCM-protocol

Proof-Carrying Messages: a protocol for AI agents whose claims carry evidence the receiver checks offline

radotsvetkov /akmon

Tamper-evident evidence and verification layer for AI agents. Verify any agent's session offline with just openssl. No cloud, no lock-in.

Sigillion-AI /sigillion

Lossless, local, provable memory for AI agents: every Claude Code session kept on your own computer, word for word, compressed and sealed, after compaction and after the 30-day transcript deletion. Claude Code first, every model next, then legal and finance. The waitlist, the releases, the website. Steddy Nova SRL.

Dicklesworthstone /franken_accounting

Universal, evidence-native double-entry accounting system of record in Rust on FrankenGraphDB: bitemporal, append-only with first-class restatements, exact money algebra, counterfactual branches, in-database forensic analytics, outsider-verifiable proofs, and an agent-first CLI/MCP surface for CPAs, regulators, litigators, and investigators.

b1rdmania /legalise

Open-source governance infrastructure for AI-assisted legal work

varmabudharaju /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.

TraceFold /tracefold

AI agents should not make irreversible changes. TraceFold escrows the inverse before an effect lands, or refuses it, and issues receipts anyone can verify offline.

alexahern0808 /RecallWeave

A local-first agent memory lifecycle engine: typed memories in an append-only, integrity-chained log with dedupe, conflict detection, forgetting, compaction, verification, query, and portable export.

anivar /decern

Deterministic authorization + tamper-evident audit for AI agents, humans, and workloads — one principal type, safety invariants machine-checked by an SMT solver (cvc5), every decision independently verifiable offline. Pure Rust.