🧱 easy and fast microVMs for running untrusted workloads

Sandbox0 is the open-source sandbox for AI agents.

Generate draw.io diagrams from natural language — 6 presets, vision self-check + up to 5-round refinement, codebase-to-diagram, 10,000+ official shapes & 321 AI/LLM brand logos. Exports PNG/SVG/PDF…

Universal SEO skill for Claude Code. 25 sub-skills + 18 sub-agents covering technical SEO, E-E-A-T, schema, GEO/AEO, backlinks, local SEO, maps intelligence, semantic clustering, e-commerce SEO, in…

Security scanner for AI agent skills. Detect vulnerabilities, malicious patterns, and security risks.

Self-Hosting Guide. Learn all about locally hosting (on premises & private web servers) and managing software applications by yourself or your organization. Including Cloud, LLMs, WireGuard, Automa…

⚒️ The open source dark software factory for expert engineers.

Context window optimization for AI coding agents. Sandboxes tool output, 98% reduction. 15 platforms

Anthropic API reverse proxy with prompt-cache injection and request body transforms

This gateway is a standalone service that proxies LLM requests with API key management, budget enforcement, usage tracking, and OpenAI-compatible endpoints.

Composable transformations of Python+NumPy programs: differentiate, vectorize, JIT to GPU/TPU, and more

SkillOpt is a text-space optimizer that trains reusable natural-language skills for frozen LLM agents through trajectory-driven edits, validation-gated updates, and deployable best_skill.md artifacts.

PostgreSQL connection pooler, load balancer and database sharder.

DeepLearning AI's centralized hub for course materials and resources.

Multi-agent RL training framework for DL models and LLMs

A multi-backend sandboxing framework for running untrusted code with controlled host capabilities built on Hyperlight.

Interact with your documents using the power of GPT, 100% privately, no data leaks

Skills for threat modeling, scanning, triage, patching, plus an autonomous scanning harness you can /customize

Self-hosted AI workspace.

Build and run agents you can see, understand and trust.

Open-source devcontainers: works with any IDE and lets you use any cloud, kubernetes or just localhost docker.

agent-sandbox enables easy management of isolated, stateful, singleton workloads, ideal for use cases like AI agent runtimes.

Secure, Fast, and Extensible Sandbox runtime for AI agents.

Self-contained UV scripts for data & ML tasks — OCR, vision, audio & more — run one in a command, locally or on Hugging Face Jobs. Built for humans and agents.

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

MCP Gateway is a reverse proxy and management layer for MCP servers, enabling scalable, session-aware stateful routing and lifecycle management of MCP servers in Kubernetes environments.

Miso TTS is an 8 billion, highly emotive text-to-speech model

Fully automatic censorship removal for language models

利用AI大模型，一键生成高清短视频 Generate short videos with one click using AI LLM.