An official Okta-maintained Model Context Protocol (MCP) server that securely integrates LLM agents with Okta Admin Management APIs for natural-language-driven automation of users, groups, applications, and policies management.
A lightweight self-hosted MCP server connecting LLM-based AI agents to Red Hat Lightspeed enterprise services, supporting 9 toolsets including Image Builder, Vulnerability, Advisor, and Inventory.
An enterprise-oriented benchmark suite for evaluating web agent safety and trustworthiness, featuring 375 tasks across GitLab, SuiteCRM, and ShoppingAdmin with six policy dimensions to measure task completion under compliance constraints. Accepted by ICLR 2025.
An open-source framework for large language model evaluations from the UK AI Safety Institute, featuring a modular Datasets/Solvers/Scorers architecture, multi-model/tool support, sandboxed execution, and 100+ pre-built benchmarks.
Hybrid static analysis tool combining SAST with local LLM agents for automated dead code removal, security vulnerability detection, and code quality gates. Features confidence scoring and LibCST-based safe removal, supporting Python, TypeScript/TSX, and Go.
Open-source platform for testing LLM and agentic apps with AI-powered test generation, adversarial red-teaming, and 60+ evaluation metrics for RAG hallucination detection and conversation consistency verification.
A local-first AI workspace built on Rust and Tauri, acting as an AI coworker for secure, supervised automation on any folder. Supports multiple LLM backends, MCP protocol extension, and multimodal file processing.
Secure, cloud-sandboxed Recursive Language Models (RLM) framework with DSPy and Modal for long-context code and document processing, offering Web UI, CLI, HTTP API, WebSocket, and MCP Server interfaces.
A security-first, local-first operating system for personal AI agents with 30+ LLM providers and 14 messaging channels, fully self-hosted. Built on Electron + React + Node.js 24+, primarily supporting macOS.
An autonomous AI-powered penetration testing framework featuring ReAct agents, 40+ integrated security tools, and automated compliance reporting.
Page 1 / 2 · 17 total
Get the latest AI tools and trends delivered straight to your inbox. No spam, just intelligence.
