
AWE
adaptive agents for dynamic web penetration testing

adaptive agents for dynamic web penetration testing

Modular security toolkit for autonomous agents providing static analysis, configuration auditing, runtime monitoring, and supply chain verification…

Securekit is a protocol-agnostic security kernel that enforces zero-trust, sandboxed execution for AI tool use. It sits between any LLM or agent…

Security Scanner for Agent Skills

Execution-Layer Security (ELS) for AI agents — policy-enforced shell with audit.

A secure* runtime for autonomous AI agents. Policy from plain-English constitutions. (*https://ironcurtain.dev)

A self-hosted sandbox for red teams to test payloads against modern detection before deployment. MCP integration lets an LLM agent drive analysis end…


Kernel-level eBPF sandbox for securing LLM agent tool calls made through the Model Context Protocol (MCP)

Autonomous AI pentesting agents — real-time reconnaissance, vulnerability detection, and exploitation orchestration. Go + TypeScript.

A benchmark for evaluating AI agents on fixing real-world security vulnerabilities.

Android Full-Stack Device Control Platform: WebRTC/H.264 remote desktop, UI/OCR/image-matching automation, one-click MITM, built-in Frida,…

Security scanner for AI agent skills. Detect vulnerabilities, malicious patterns, security risks, prompt injection, data exfiltration, and…

Millisecond microVM sandbox forking for AI agents on Kubernetes. Firecracker VMs that restore from memory snapshots in milliseconds, fork a running…

Agent Skill for operating renef.io — Android ARM64 dynamic instrumentation: hook native/Java, patch memory, trace syscalls, bypass SSL pinning/root…

A security-first MCP server that empowers AI agents to perform automated reverse engineering, malware analysis, forensics, vulnerability research,…

A local sandbox for your AI agents

Ultrafast CLI on Apple Silicon macOS for fast, sandboxed development and LLM agents.