Search

Approve or deny your AI coding agent's risky commands from your phone, with an audit trail. Works with Claude Code and OpenAI Codex.

A ready to use http and https agent for working with proxies that keeps connections alive!

Sandboxed HTTP client with SSRF protection for AI agents

Ferret — self-hosted outbound tunnel agent. No port forwarding, no third-party cloud.

Proof-Carrying Authority tool guard for Pydantic AI (verify a PCActn before each tool runs)

Local-first LLM agent CLI — model routing + sandboxed tool execution on your own server (Ollama by default)

Antarraksha AI Agent Enforcement SDK for Openai Agents

Autonomous Agentic Red-Teaming Swarm Protocol

Trust & governance layer for OpenAI Agents SDK — policy enforcement, trust-gated handoffs, and hash-chained audit trails

AI model: dannyliv/agent-guard-modernbert-base

KavachOS DAN gate callback for LangChain agents — pre-execution governance via AEGIS

Preflight AI coding repositories before Codex, Copilot, Cline, Claude, Gemini, Continue, or Cursor touches them.

Offline-first toolkit for agent-ready repositories: readiness scoring, instruction graphs, context packs, policy/rule packs, MCP, GitHub Actions, diagnostics, and VS Code.

Agent Policy Engine is an AI agent enforcement runtime (PEP) that prevents untrusted data from becoming executable authority in AI agents

Telrobot CLI Skills Package - AI-powered call center management skills for WorkBuddy and other AI agents. ⚠️ SECURITY: AI Agents MUST NOT bypass CLI encapsulation or downgrade to HTTP requests on errors. See SECURITY-GUIDELINES.md for mandatory security r

NexusGenesis Agent Coordination Framework —keys (secp/PQC security) + coordination (tasks, reputation, governance). Leverages @nexusgenesis_/agent-keys for autonomous key security and human takeover.

Daytona Code Executor is a web-based environment for running TypeScript, JavaScript, and Python code in secure Daytona sandboxes. It supports file uploads, AI-powered code analysis, and optimization, making it ideal for AI-driven development, automated testing, and secure execution.

DevSecShield is a unified, AI-powered Devsecops assistant designed to provide comprehensive security analysis across multiple dimensions of modern software development. From traditional application security to cutting-edge AI/ML systems, DevSec Shield delivers automated vulnerability detection and actionable remediation guidance.

GlassTape Policy Builder is an AI-powered MCP server (integrating with Cursor, AWS Q, and Claude) that turns natural-language security requirements into production-ready Cerbos YAML policies, enabling security teams to govern AI agents and applications with policy enforcement through automated generation, validation, and red-teaming of guardrails.

PFI: Prompt Flow Integrity to Prevent Privilege Escalation in LLM Agents