Test your prompts, agents, and RAGs. AI Red teaming, pentesting, and vulnerability scanning for LLMs. Compare performance of GPT, Claude, Gemini, Llama, and more. Simple declarative configs with co…

Build, run and scale AI agents like API and microservices

ToolHive is an enterprise-grade platform for running and managing Model Context Protocol (MCP) servers.

SpaceXAI's coding agent harness and TUI. Fullscreen, mouse interactive, extensible.

Read-only developer endpoint scanner for on-disk package, extension, and developer-tool metadata, built to check exposure to known software supply-chain compromises.

Universal memory layer for AI Agents

Identity-aware VPN and tunneled reverse proxy for remote access based on WireGuard®.

The agent harness performance optimization system. Skills, instincts, memory, security, and research-first development for Claude Code, Codex, Opencode, Cursor and beyond.

Conductor is an event driven agentic workflow engine providing durable and highly resilient execution engine for applications and AI Agents

Open-source infrastructure for Computer-Use Agents. Sandboxes, SDKs, and benchmarks to train and evaluate AI agents that can control full desktops (macOS, Linux, Windows).

The official TypeScript SDK for Model Context Protocol servers and clients

Scheduling infrastructure for absolutely everyone.

🐫 CAMEL: The first and the best multi-agent framework. Finding the Scaling Law of Agents. https://www.camel-ai.org

Google Workspace CLI — one command-line tool for Drive, Gmail, Calendar, Sheets, Docs, Chat, Admin, and more. Dynamically built from Google Discovery Service. Includes AI agent skills.

A community-driven repository of industry and use-case analyses for agentic systems. Documents how ai agents can fail, and how those failures map to SAFE-MCP attack techniques.