microsoft/PyRITThe Python Risk Identification Tool for generative AI (PyRIT) is an open source framework built to empower security professionals and engineers to proactively identify risks in generative AI systems.
Python · TypeScript★ 4,5732026年10月3日
npm · Go · crates.io96卓越健康指数
microsoft/agent-governance-toolkitAI Agent Governance Toolkit — Policy enforcement, zero-trust identity, execution sandboxing, and reliability engineering for autonomous AI agents. Covers 10/10 OWASP Agentic Top 10.
Python★ 6,138↓ 14.7K/月2026年8月28日
cvs-health/uqlm[JMLR 2026] "UQLM: A Python Package for Uncertainty Quantification in Large Language Models"
Python★ 1,200↓ 1,591/月2026年9月19日
preloop/preloopThe open-source AI agent control plane: MCP firewall, model gateway with budgets, human approvals, runtime observability, and audit trails
Python · TypeScript★ 62↓ 364/月2026年9月18日
sattyamjjain/agent-audit-kitStatic scanner for MCP-connected AI agent pipelines. 348 rules across 14 categories, 14 compliance frameworks, OWASP Agentic 10/10 + MCP 10/10, GitHub Action, SARIF, public CVE-to-rule ledger.
Python★ 13↓ 4,551/月2026年9月15日
Python★ 155↓ 2,902/月2026年8月25日
cordum-io/cordumThe action firewall for AI agents. Enforce policy and human approval before risky tool calls, shell commands, workflows, and production changes, with auditable evidence.
Go · TypeScript · Python★ 505↓ 14/月2026年9月17日
node9-ai/node9-proxyThe Execution Security Layer for the Agentic Era. Providing deterministic "Sudo" governance and audit logs for autonomous AI agents.
TypeScript★ 211↓ 7,422/月2026年9月13日
PyPI · npm · crates.io +186优秀健康指数
QWED-AI/qwed-verificationOpen-source AI verification infrastructure for deterministic verification of LLM outputs, tool calls, code, schemas, and agent state before production execution.
Python★ 58↓ 764/月2026年9月18日
issdandavis/SCBE-AETHERMOOREGeometric AI governance and evaluation framework with a 14-layer security pipeline, semantic projection, and reproducible benchmark lanes.
Python · TypeScript★ 6↓ 4,607/月2026年8月26日
IgorGanapolsky/ThumbGateThumbGate Pre-Action Checks self-improve from ranked lessons and repeated failures, hard-block detected secret leaks, and block matches in strict mode.
JavaScript · HTML★ 26↓ 2,369/月2026年9月11日
JKHeadley/instarPersistent Claude Code agents with scheduling, sessions, memory, and Telegram.
TypeScript★ 84↓ 41.5K/月2026年10月21日
PrismorSec/prismor Self-hosted runtime control plane for AI agents. Observe or HITL approve or Block rogue tool calls before it executes: secret leaks, prompt injection, supply chain etc in a local dashboard. Agent agnostic (Claude, codex, langchain etc.)
Python★ 343↓ 2,863/月2026年9月11日
AltairaLabs/PromptKitTest, red-team, and deploy LLM applications with confidence. Multi-provider support (OpenAI, Anthropic, Gemini), MCP integration, self-play testing, and production SDK.
Go★ 92026年9月20日
lua-ai-global/governanceZero-dependency TypeScript SDK for AI agent governance: policy enforcement, injection detection, tamper-evident audit, and standards mapping (EU AI Act, OWASP, NIST, ISO 42001)
TypeScript★ 26↓ 18.7K/月2026年9月13日
Cogensec/agentegrityThe open standard for AI agent integrity. Evaluate, enforce, and prove that autonomous agents are adversarially coherent, environmentally portable, and verifiably assured.
Python · TypeScript★ 3↓ 156/月2026年9月18日
alizahidraja/isnadGrade every agent, scraper and model in a claim's chain — provenance, trust scoring and audit evidence for LLM pipelines
Python★ 53↓ 2,089/月2026年10月21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
mauhpr/agentlintReal-time guardrails for AI coding agents. 77 rules across 8 packs covering code quality, security, and infrastructure safety. Inline ignore directives, path exemptions, hook timing, and session summaries.
Python★ 32↓ 9,332/月2026年10月1日
Sahil170595/quantfitQuantize an LLM and check it still refuses what it should — a GPU-aware quantization CLI that measures the safety drift of the quantization it just performed.
Python★ 1↓ 2,468/月2026年10月12日
Python★ 0↓ 9,632/月2026年9月8日
fathom-lab/styxxVerification for the agent era. Your coding agent's PR summary cannot lie about its diff - one CI line. Plus the research: the first map of which AI minds can read each other. Every claim machine-verified against committed receipts, negatives included. pip install styxx
Python · HTML★ 15↓ 575/月2026年10月19日
gumieri/nenyaA lightweight, highly secure AI API Gateway/Proxy written in Go. Acts as transparent middleware between local AI coding clients (OpenCode/Pi/Cursor) and upstream LLM providers (Gemini, DeepSeek, Zhipu z.ai).
Go★ 282026年9月13日
provael/provaelProvael — red-team open Vision-Language-Action (VLA) robot policies in simulation and report an Attack Success Rate (ASR). Prove it. Prevail.
Python★ 6↓ 2,516/月2026年9月11日
Keesan12/martin-loopMake AI coding agents safe to scale autonomously: assign work, cap spend, enforce policy, verify output, roll back failures, learn from loops, and prove ROI across every repo.
TypeScript · JavaScript★ 51↓ 2,344/月2026年9月11日
OrlojHQ/orlojAn orchestration runtime for multi-agent AI systems. Declare agents, tools, and policies as YAML; Orloj schedules, executes, routes, and governs them for production-grade operation.
Go · TypeScript★ 1212026年9月18日
Python · TypeScript★ 1↓ 239/月2026年9月18日
tuliplabs-ai/tulip-agentsThe agent framework where the model never holds the trigger — every consequential action clears your policy first, waits for a human when it matters, and lands on a record you can verify. Build on it, or put it around the agent you already have.
Python★ 1↓ 5,295/月2026年10月8日
voku/agent-loop♾️ Umbrella php package and unified CLI for the governed agentic-coding loop: board (kanban), learning, and recall-compiler.
PHP★ 4↓ 3,672/月2026年9月18日
Python★ 48↓ 1,793/月2026年9月10日