Search

Autonomous AI penetration testing CLI agent with a built-in exploit engine

Independent fail-closed second fuse for AI agents: runtime guard + signed receipts + incident reports

Process execution guard for agentic systems

Deterministic guardrail layer and edge-AI MLOps pipeline for autonomous AI agents.

Typosquat detector for AI coding agent dependencies

Track untrusted tool output before it enters prompts or actions. Python port of @mukundakatta/tool-result-taint.

Local-first safety runtime for AI coding agents

Human-in-the-loop approval firewall for Python agent tool calls

Pinta AI runtime guard adaptor for Python agents (OpenTelemetry spans + tool-call guard)

GEPA reflective prompt evolution optimizer for superred agent targets

Runtime validation middleware for AI agent tool-calls

Action Policy Engine for AI agents: policy-as-code for tool-calls — evaluate, enforce (block/warn/approve), and trace agent actions, with the same policy asserted in CI. Plus local guardrails and an offline judge. Pure-Python, zero dependencies.

Apache Airflow provider for Darkmoon: trigger autonomous AI pentest campaigns and consume their findings from a DAG (Darkmoon Pro Dashboard API).

A lightweight Node.js wrapper for routing HTTP(S) traffic through Tor, including optional ControlPort circuit rotation.

Task-scoped authorization for AI agents: compile user intent into a least-authority policy and enforce it at every tool call. Hermes Agent plugin.

Enterprise Security Monitoring SDK for AI Agents - Secure any AI agent in just 3 lines of code with real-time threat detection, behavioral analysis, and separate logging and threat reporting for comprehensive security monitoring

A Zero-Trust AI agent framework built on microkernel security principles and capability-based access control.

💠 The security scanner for AI agents. 5-layer verification for MCP servers & skills. Zero dependencies.

Typed Python client for the 17711.xyz Domain Security API: pay-per-call, settled in USDC via x402.

Correctover CCS official site — MCP security & AI agent authorization. Runtime conformance verification with Ed25519-signed evidence receipts, IETF draft-correctover-ccs-05.