Search

Runtime governance for AI agents — deterministic fail-closed enforcement. Wraps any agent tool and blocks dangerous calls before execution. Zero LLM calls, zero cloud dependencies, works offline.

AI model: mradermacher/AgentDoG-FG-Llama3.1-8B-i1-GGUF

FailSafe governance adapter for Microsoft Agent Governance Toolkit

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

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.

SWT3 AI Witness SDK: cryptographic attestation for AI inference

It is a comprehensive resource hub compiling all LLM papers accepted at the International Conference on Learning Representations (ICLR) in 2024.

LLM-App is a library for creating responsive AI applications leveraging OpenAI/Hugging Face APIs to provide responses to user queries based on live data sources. Build your own LLM application in 30 lines of code, no vector database required.

Convention over configuration for agentic development teams. The Spring Boot of Claude Code governance.

Opus-led code review-and-fix pipeline for Claude Code (native agent teams, no external API calls).

Cryptographic identity, trust chains, and E2E encrypted messaging for AI agents

Capability-based safety gates for LLM agents. The model proposes; signet authorizes.

A working reference for running AI agents with Kanban discipline. Operating model, knowledge system, persona files, and board CLI extracted from a production multi-agent delivery system.

This repository represents the transition from behavioral safety to Neural Forensics. It provides the infrastructure to detect, audit, and mitigate high-order AI risks—such as Latent Deception, Sycophancy-Masking, and Synthetic Intimacy—directly at the mechanistic activation layer.

15 AI agents for Claude Code — full development lifecycle from product thinking to production monitoring

AI-Haklab: Agente de automatización para Pentest en Termux. Basado en i-Haklab v3.11, optimiza flujos de seguridad, escaneo de vulnerabilidades y ejecución de exploits.

AI-powered penetration testing tool using CrewAI with Human-in-the-loop design

AI Agent Governance for TypeScript — policy enforcement, scoring, compliance, and audit for AI agents

Let AI agents like ChatGPT & Claude use real-world local/remote tools you approve via browser extension + optional MCP server

Shared memory and identity for your AI agents — Git-native, self-hosted, no vendor lock-in