Search

Deterministic triage of an AI agent's changes — see what it actually touched before you merge.

AEAP Composition Boundary Adapter for the Microsoft Agent Framework. Thin wrapper that attaches the Runtime Decision Point to agent middleware and workflow execution.

AI Agent Governance Toolkit — Policy enforcement, zero-trust identity, execution sandboxing, and reliability engineering for autonomous AI agents. Covers 10/10 OWASP Agentic Top 10.

AI Agent Governance Toolkit — Policy enforcement, zero-trust identity, execution sandboxing, and reliability engineering for autonomous AI agents. Covers 10/10 OWASP Agentic Top 10.

A CodeQL tool to automatically execute code scanning.

Production-hardened Python redaction for structured logs, LLM agent payloads, and AWS-signed URLs.

Autonomous cybersecurity execution agent for the terminal.

Parallel multi-agent pipeline for code analysis and transformation.

Run AI coding agents (Claude Code, OpenCode) safely inside sandboxed Docker containers with audit logging

Entropy0 Trust Control Plane tool for LangChain agents — evaluate domains and URLs before your agent fetches content from them.

Privent DLP nodes for n8n: session-scoped tokenization, risk scoring, and safe detokenization for AI agent workflows

探驪 Tanli - 自主紅隊測試 Agent(LLM + Web 雙軌安全評估)

Gate OpenAI Agents SDK tool calls behind a signed Fidacy verdict. Wraps the tool's execute, so a denied payment never runs and the agent gets a refusal it can reason about.

Open-source in-process governance for AI agent frameworks: Cedar-governed model/tool calls via build_middleware()/GovernedAgent, plus the Cedar engine, request/decision shapes, PEP<->control-plane protocol client, and Ed25519 PEP identity they run on.

AI model: AI45Research/AgentDoG1.5-FG-Qwen3.5-0.8B (text-classification)

Tonic Textual PII redaction tools and guardrails for the OpenAI Agents SDK

CncertAgent local WSS log cache, offline analysis, submission, and API adapter toolkit.

A team of AI agents that reviews and improves your code automatically

Autonomous red team for MCP servers. Sends adversarial payloads to your tools, proves exploitation, reports what's broken. 53 attack patterns across 6 categories. Zero dependencies. npx decoy-redteam

Model Context Protocol (MCP) server in Go for ThreatBook TDP (微步在线威胁检测平台): 105 OpenAPI endpoints + 4 diagnostics as typed MCP tools - alert triage, incident forensics, log hunting, threat intel & SOC automation.