Search

Score AWS IAM policies for risk before granting access. Deterministic + LLM-narrative scoring as an API, CLI, and GitHub Action.

Deterministic governance adapter for AG2 (AutoGen fork) — policy enforcement, PII detection, cost tracking, per-agent kill switch, governed speaker selection, and structured audit evidence. No LLM in the governance path.

CrewAI integration for Interven AI firewall. Scan every tool call your CrewAI agents make — block malicious requests, redact PII/secrets, route risky actions to human approval.

An open-source, BYOK semantic firewall for autonomous AI agents.

AgentDNA: Verifiable and Auditable AI Agents

A pi extension that brings Claude Code-style autonomous sub-agents to pi. Friendly fork of @tintinweb/pi-subagents.

Runtime risk scoring for AI agent tool calls. Detect privilege escalation, baseline deviations, and data exfiltration inline — under 1ms, zero dependencies, no LLM.

LlamaIndex integration for the Chio protocol -- capability-scoped FunctionTool and QueryEngineTool with vector-collection scoping

Aegis ATV — Action Firewall + cryptographic audit chain for Claude Code (and OpenClaw, preview)

Trust enforcement adapter for LangChain and LangGraph — powered by CapiscIO

Agentic LLM vulnerability scanner

Antarraksha AI Agent Enforcement SDK for Crewai

Error with more than just a message, stacktrace parsing.

Red-team your AI agents: a CLI that fires authorized attacks at LLM and agent targets.

LLM/agent observability for behavior deviations, guardrails, and telemetry

TypeScript package for AppSec AI Agent management

Python SDK for AI Agent Safety Filter - validate AI agent actions against policies

Inline PII, credential, and regulated-data classifier for AI agent I/O. Dual-layer: deterministic regex + optional semantic Guard. Library + CLI. Python port of @opena2a/aicomply.

Terminal AI Agent Library — TAP IR + Model-Specific Compilation

AgentKeeper Agent Runtime SDK for app-embedded TypeScript agents.