Rul1an/assayOpen evidence profile for MCP tool actions. Enforce configured tool-call policies and record decisions and observations in offline-verifiable bundles. Optional Linux kernel controls. No hosted backend required.
Rust · Python · Shell★ 13↓ 4,222/月2026年10月13日
Python★ 480↓ 5,294/月2026年9月11日
TypeScript★ 14↓ 5,984/月2026年9月6日
rajudandigam/agent-inspectLocal evidence debugger and trajectory-test toolkit for TypeScript AI agents: inspect causal runs, catch wrong tool paths in CI, and share safe offline evidence.
TypeScript★ 546↓ 23.7K/月2026年9月10日
Dicklesworthstone/asupersyncAsync runtime for Rust where correctness is structural: region-owned tasks, cancel-correct protocols, capability-gated effects, and deterministic replay testing
Rust★ 285↓ 252K/月2026年10月20日
sectum-ai/sectum-aiAI data-isolation verification — prove no user or customer can reach another's data across 13 AI surfaces, with tamper-evident evidence anyone can verify.
Python★ 62026年9月9日
b7n0de/proofbundleOffline cryptographic receipts for AI evaluation results — Ed25519 + RFC 6962 Merkle + optional SD-JWT. Integrity, not truth
Python★ 2↓ 1,203/月2026年9月13日
jyt6640/persona-harnessContinuously refine your project’s engineering philosophy — and keep AI coding agents honest with evidence-backed completion.
TypeScript · JavaScript★ 23↓ 8,820/月2026年9月8日
getveritio/veritioProtocol-first OSS evidence layer for application audit trails, consent history, DSAR workflows, retention, and compliance exports.
TypeScript · Go · Python★ 0↓ 265/月2026年9月19日
Python · TypeScript★ 3↓ 6,367/月2026年10月21日
JavaScript · Python★ 9↓ 2,146/月2026年10月11日
sensigo-hq/realmOpen-source workflow engine for AI agents. An agent calls Realm over MCP, or realm agent drives a model from the CLI. Steps run in order, agent answers are checked against the schema a step declares, human gates pause the run until answered, and each finished step is recorded.
TypeScript★ 2↓ 3,003/月2026年10月21日
armanfatemi/nulliusMost tools check the code your agent wrote. nullius checks how it got there — citations, session journals, weakened tests.
TypeScript★ 5↓ 3,661/月2026年10月14日
kontourai/flow-agentsPortable workflow engine, runtime adapters, hooks, and kits that bring evidence-gated process discipline to agent tools.
JavaScript · Shell · TypeScript★ 1↓ 4,867/月2026年9月6日
noeos/verification-engineDeterministic offline-first TypeScript engine and CLI for hash-linked integrity evidence and auditable diagnostics.
TypeScript · JavaScript★ 0↓ 4,431/月2026年10月10日
LambdaTest/evidence-cliAn open, framework-agnostic format for what a test run produced — the .evidence pack, and the library + CLI that validate and seal it.
TypeScript · CSS★ 33↓ 94.9K/月2026年10月21日
Python★ 12026年9月8日
rozmiarD/SCLiteSchema-backed contract layer for governed AI/security workflows: intent, policy decisions, approvals, execution receipts, evidence, and replayable audit traces.
Python★ 3↓ 237/月2026年9月10日
fissible/attestTamper-evident signed evidence chains for application events. Optional OpenTimestamps anchoring.
PHP★ 0↓ 3,951/月2026年10月19日
gmemmy/agent-scenario-loopThe scenario is the asset; runners are swappable. Define mobile app journeys once, run them through any agent, device, or profiler, and preserve stable evidence that tells agents and humans whether behavior improved, regressed, or can't be trusted yet.
TypeScript★ 3↓ 302/月2026年9月10日
npm · PyPI · crates.io +165良好健康指数
muthuishere/citenexusEvidence-first, multilingual, S3-native RAG — answers only from cited evidence (exact quote, page, bbox) and abstains when the evidence is weak, missing or conflicting. The guarantee is "no ungrounded claim". Byte-identical core across Python, Go and JavaScript. Docs: https://muthuishere.github.io/citenexus/
Python · Go · Rust★ 0↓ 409/月2026年10月21日
Python★ 1↓ 3,630/月2026年10月10日
YuClawLab/yuclaw-brainEvidence-First Financial AI — the Science Trust Layer for Financial AI. Open-source, runs on your own hardware. Every claim traces to an SEC filing; every method is locked before the data arrives; every result is kept in a public, hash-linked record built to be recomputed by anyone. Research & education only — not investment advice. Apache-2.0.
Python★ 4↓ 649/月2026年9月18日
Go★ 02026年9月12日
ictseoyoungmin/HADARAPortable agentic development workbench for evidence-backed, resumable AI-assisted software workflows.
TypeScript★ 0↓ 316/月2026年9月14日
crates.io · npm · PyPI56中等健康指数
Rust · Shell · TeX★ 1↓ 9,156/月2026年9月17日
JavaScript★ 0↓ 437/月2026年9月15日
tersignhq/tersign-jsTypeScript SDK + MCP server for Tersign, the evidence layer for the agent economy — counter-signed EIP-712 receipts, hash-chained action and disclosure records, refunds, disputes, venue-ready evidence envelopes. npm: tersign
TypeScript★ 1↓ 2,139/月2026年9月14日
kordloom/loomsealAn open format for evidence someone else can check. One signed, chained, anchored file, verified offline by a free Apache-2.0 tool with no account and no server.
HTML · Go · Python★ 12026年9月20日
JavaScript · TypeScript★ 0↓ 29.7K/月2026年9月15日