Runtime security enforcement and threat hunting engine for autonomous agent fleets. Build Swarm Detection & Response (SDR) platforms with Clawdstrike.

Detect and Deny - Deterministic Function-Level Guardrails for AI Agents

Open-source AI security firewall. 81 engines for PII detection, prompt injection defense, MCP security, and egress classification. Local-first. Zero cloud dependency.

Awesome LLM security tools, research, and documents

Detect bugs that have already been fixed in one codebase and determine whether the same issues apply to the target codebase.

Free OpenClaw security scanner. 2,890+ agents audited. 3-Layer Audit Protocol. OWASP ASI 10/10 coverage. AI agent integrity layer.

An Identity, Security, and Governance Framework for the agentic internet

An always-on runtime control plane for autonomous AI agents. It enforces intent alignment, permissions, provenance, and risk controls at execution time. Built for agentic systems operating at machine speed, AVARA introduces identity, accountability, and human-in-the-loop safety into multi-agent + tool ecosystems.

Secure agentic GitHub remediations with MCP, OAuth-gated tool access, and GRC-grade evidence trails

Intent-Bound Authorization (IBA): Cryptographic protocol to prevent Intent Blindness & Confused Deputy in agentic AI. Includes 4-layer architecture, Semantic Firewall (<5ms), simulator, and ISO 42001 alignment.Intent-Bound Authorization (IBA): Making sure AI agents do what they're told, not just what they're capable of.