Security & Governance

Defense-in-depth pattern for protecting autonomous AI agents that execute real-world actions, using layered guardrails,...

Security threat pattern covering attacks that exploit trust chains between skill registries, skill authors, and consumin...

Emerging pattern applying LLM-driven agentic code auditing to discover software vulnerabilities at scale — including nov...

A declarative authorization policy language by Amazon that expresses fine-grained access control as human-readable permi...

A three-layer real-time security framework for OpenClaw agents providing instruction-level, runtime, and system-level de...

Cloud-native endpoint detection and response (EDR) and extended detection and response (XDR) platform with $5.25B ARR, t...

MIT-licensed LLM gateway written in Go providing a unified OpenAI-compatible API for 10+ providers with two-layer respon...

METR's primary benchmark measuring frontier AI autonomous software task completion, calibrated against 140 human experts...

Observability and evaluation platform for LLM applications, providing tracing, prompt testing, and experiment comparison...

Container-based sandbox that monitors AI agent syscalls via eBPF and enforces access policies written in Cedar.

eBPF-based per-process network connection monitor for Linux by Objective Development, offering a web UI for observing an...

NVIDIA's open-source CLI and reference stack for deploying OpenClaw AI agents in hardened sandbox environments, layering...

NVIDIA's open-source Rust runtime for sandboxed AI agent execution, providing declarative YAML-policy-enforced filesyste...

Austrian indie software company founded by Christian Starkjohann, best known for Little Snitch (macOS network monitor si...

Enterprise cybersecurity platform company with $11B+ annual revenue delivering network security, cloud security (CNAPP),...

Enterprise AI gateway for routing LLM requests to 250+ providers with failover, caching, guardrails, and cost management...

Vercel's directory and CLI for discovering and installing reusable SKILL.md packages across 40+ AI coding agents.

Applies W3C Decentralized Identifiers to AI agents, giving each a cryptographic identity for tamper-evident audit trails...

A lightweight CLI and TypeScript SDK that sandboxes processes using OS-level isolation with deny-by-default file, networ...