Search

Sandbox for AI coding agents (Claude Code, opencode, pi): runs each project in an isolated microVM with host-side secret injection. Linux/KVM & macOS.

Universal Zero-Refusal Agent Framework - 40+ jailbreak templates (T1-T119), 1128 curated skills, executable framework-core, installer untuk Hermes/Claude/Codex/opencode. Verified.

Official Python SDK for Auth Agent - OAuth 2.1 authentication for websites and AI agents. Includes client SDK for Python backends (Flask/FastAPI) and agent SDK for browser automation with browser-use integration.

TypeSafe AI driven agent tool execution guard for Claude Code hooks

HackerAI — Your AI cybersecurity arsenal. Autonomous agent with 20+ free AI models, multi-provider rotation, and zero rate limits.

AgentMesh trust layer for OpenAI Agents SDK — trust-gated function calling and handoff verification

Code review agent powered by DSPy

OpenClaw 安全客户端 - Hook 注入/执行前审批/基线扫描

Lightweight inter-agent trust, coordinatination and shared state server for AI agent swarms

Deterministic, no-LLM SecurityAnalyzer for OpenHands, backed by the rein engine.

Transparent MCP proxy for agent observability. Logs every tool call, exposes trace history, reduces token overhead.

AI model: AI45Research/AgentDoG1.5-Llama-3.1-8B (text-classification)

Safe skill discovery for AI agents — search 33,000+ skills with Trust Score, 10-language support, and @author lookup

CLI that runs Claude Code agents to autonomously scan, fix, and verify vulnerable dependencies

Defense-in-depth protection for Pi coding agent. Blocks dangerous commands and protects sensitive files — rename of pi-damage-control.

LLM-assisted code auditing. 54 phases, custom overlays, accountability.

A local-first, auditable job runner for AI-agent automation

LangChain / LangGraph integration for comply54 — African AI agent compliance enforcement

Trajectory-level benchmark for prompt injection, policy erosion, intent drift, and coordinated misuse in agentic LLM systems.

AI model: AI45Research/AgentDoG1.5-FG-Llama-3.1-8B (text-classification)