sandstorm
Run Claude agents in secure cloud sandboxes — via API, CLI, or Slack. One call. Full agent. Zero infrastructure.
HYSEN LABS DIRECTORY
Capability tag · curated repositories and deep analysis.
Run Claude agents in secure cloud sandboxes — via API, CLI, or Slack. One call. Full agent. Zero infrastructure.
VexJoy AI Agent with Intelligent Routing - /do routes plain-English requests to the right specialist agent and gates the work with reviews, tests, and a learning loop.
Agent workflows with full observability and time travel: watch every step live, rewind, fork, replay any run. Claude Code, Codex, Gemini, any model or harness. The same workflow runs across Claude Code, Codex, Pi, AI SDK models, and remote sandboxes.
The agent responsible for conducting the agent evaluation
A bot plugin for LLM chat with multi-model integration, extensibility, and various output formats.
Python and TypeScript SDKs for verifiable evidence of AI agent actions. Signed receipts, policy enforcement, audit trails. Works with LangChain, CrewAI, MCP.
Accessibility review agents for Claude Code, GitHub Copilot, and Claude Desktop. Eleven specialists that enforce WCAG 2.2 AA compliance so AI coding tools stop generating inaccessible code.
[ICML 2026] Let LLMs invent and evolve languages for efficient reasoning.
Swift clients for AI providers. You can make requests straight to the provider or proxied through our abuse protection backend
Job OK: an evidence-driven job-search Agent Skill for Chinese-speaking job seekers, supporting strength discovery, job matching, resume optimization, interview training, and application tracking.
A productivity kit for solo entrepreneurs - automated 58 tasks without employees, releasing 38 ready-to-use AI agent skills (plus 19 execution scripts).
ExploitBench measures how far AI agents climb, from reaching vulnerable code, to triggering the bug, to building exploit primitives, to arbitrary code execution.
Your personal voice assistant based on OpenAI ChatGPT.
Claude Code skill for OWASP security best practices (2025-2026). Includes Top 10:2025, ASVS 5.0, Agentic AI security, and 20+ language-specific security quirks.
Ghost Security's collection of AppSec skills for AI coding agents
Universal mobile devtool for Agents & Humans - control iOS Simulators, Android Emulators, and real devices from a single dashboard and CLI
Run LLM prompts from your shell
pool is Poolside’s coding agent that runs in your terminal or integrates with any ACP-compatible editor
Give Claude Code's ultracode mode to ANY model you already pay for. A tiny local proxy + one config.json. Point your AI at AGENTS.md and it sets itself up.
An uncensored, fully offline AI-girlfriend harem: OpenClaw/Claude Code plus a local LLM, GPT-SoVITS voice, ComfyUI image generation, Live2D, a desktop pet, SillyTavern character-card import, and a frontend. Dual channels for QQ and Telegram, with dynamic 8GB VRAM scheduling and mem0/Qdrant; can run fully offline.