Search

V8 isolate sandbox provider for Agentick — lightweight code execution via secure-exec

Secure autonomous AI agent fleet platform — Docker-isolated, multi-provider, with built-in cost controls. OpenClaw alternative for production use.

AGent Based Access Control (AGBAC) is is an open, vendor-neutral security specification that defines how AI agents securely perform actions on behalf of humans using existing IAM technologies

SkillSpector: Security scanner for AI agent skills (Claude Code, Cursor, and similar). Scans skills for vulnerabilities, malicious patterns, and security risks before installation. Supports Git repos, URLs, zips, and local directories; runs static pattern checks and optional LLM semantic analysis; outputs terminal, JSON, and Markdown reports with risk scoring.

The complete AI agent governance stack - kernel, trust mesh, runtime supervisor, and reliability engineering

Multi-tier firewall for AI agents — blocks prompt injections, jailbreaks, and scope violations; fast local tiers screen every request, only uncertain cases reach an LLM judge

Reverse proxy firewall + LLM Gateway for AI agents

Secret scanning CLI for Claude Code

CyberAI — AI-native multi-agent pentest platform

Production hardening guide for AI agents — prompt injection defense, tool sandboxing, and credential management

Python SDK for EvalGuard -- evaluate, red-team, and guard LLM applications with drop-in framework integrations

AI-powered content generation service for social posts, blog articles, emails, and multi-platform content

LangChain integration for TrustAgents - protected document loaders, retrievers, and threat scanning

A hardened, containerized environment for running Claude Code as an AI agent with access to local tools via the Model Context Protocol (MCP).

Native safety hooks for Claude Code — blocks destructive commands, enforces tool-call budgets, guards file reads, masks secrets, and audits every agent action. Fail-closed C++ daemon with extensible rule engine.

Agent Trust Protocol (ATP) — the cryptographic standard for AI agent identity, scope, and action verification. Reference implementation.

AI model: mradermacher/agentguard-2.8b-GGUF

Evidence-gated verifier for AI coding agents with local safety checks, hooks, checkpoints, deploy guards, and MCP tools.

LLM Prompt Injection Detection CLI — 3-layer detection (Vigil + DistilBERT ONNX + Rules)

The Pydantic-based Firewall for MCP Servers. Stops hallucinated tool calls, validates schemas, and sandboxes dangerous operations.