Explore the directory

An open agent operating system providing a CLI, HTTP API and a set of first-party capsules for building an inspectable, composable environment to run agents.

• Agent frameworks

A curated list of LLM API providers offering permanent free tiers for text inference, with base URLs, supported models, context limits and rate limits for each.

• Curated lists

An open-source SDK for building and running AI agents in Python and TypeScript, providing lifecycle controls, tools, MCP support, multi-agent patterns, memory, tracing and evals in-process.

• Agent frameworks

An all-in-one Android device control platform combining on-device services with a Python client for UI automation, remote desktop, traffic capture, reverse engineering and AI agent or MCP integration.

• Testing
• Mobile

A PyTorch library that enables accessible large language models through 8-bit and 4-bit quantization, cutting memory use for inference and training.

• Models
• Inference

An LLM post-training framework for reinforcement-learning scaling, connecting Megatron training with SGLang rollout and flexible custom data-generation pipelines.

• Models

An open-source, general-purpose autonomous agent driven by large language models, built from a dispatcher, planner and actor that break down and execute tasks in a sandboxed tool server.

• Agent frameworks

A portable C99 inference engine that runs the 2.78-trillion-parameter Kimi K3 model on a single CPU with no GPU, BLAS library or ML framework.

• Inference

A hosted Model Context Protocol server that lets AI agents run thousands of Apify scrapers, crawlers and automation tools to extract data from any website.

• MCP servers
• Browser automation

A terminal monitor for Claude Code usage that reads official rate-limit data, forecasts token consumption against plan resets, and keeps an opt-in local usage history.

• Desktop utilities

A Rust library for building modular, scalable LLM-powered applications, with a unified interface across more than 20 model providers and 10 vector stores.

• Agent frameworks

A cross-platform Flutter app for viewing server status charts and managing servers over SSH, including SFTP, Docker and process control, backed by an optional companion monitoring agent.

• Terminals
• Monitoring

A searchable library of more than 5,000 ready-to-use AI prompts, with a browser extension and website for copying prompts into any chat tool.

• Curated lists

A safe, private runtime for fleets of autonomous AI agents that enforces file, process and network access through kernel-level sandboxing and policy checks.

• Agent frameworks
• Containers

An open-source, code-first Go toolkit for building, evaluating and deploying AI agents, optimized for Gemini but model- and deployment-agnostic.

• Agent frameworks

An open-weight, 2.8-trillion-parameter multimodal mixture-of-experts model built for long-horizon coding, agentic knowledge work and reasoning, with a one-million-token context window.

• Models

A Python library for building online model-serving systems, turning inference scripts into REST APIs with Docker packaging and serving optimizations.

• Inference

An AI-agent skill that generates browser-editable presentations across 12 visual themes and more than 1000 layouts, letting a user tweak layout, color and content live before exporting to PPTX, PDF or HTML.

• Agent skills
• Design tools

A hands-on course that builds a production-grade retrieval-augmented-generation research assistant from scratch, called the arXiv Paper Curator, teaching keyword search first and then hybrid and agentic retrieval.

• RAG
• Tutorials

A curated collection of copy-paste ChatGPT prompts from top-rated GPTs, alongside prompt-engineering frameworks, papers and leaked system prompts, weighted toward treating prompting as an engineering discipline.

• Curated lists

A local-first, agentic HTML editor where a local coding-agent CLI writes the HTML from more than 70 skill templates across nine deliverable surfaces such as magazines, decks, posters and social cards, with sandboxed preview and one-click export.

• Agent skills
• Design tools

A collection of standalone examples for Apple's MLX machine-learning framework, covering text, image, video, audio and multimodal models such as LLaMA, Mistral, Stable Diffusion, Whisper and CLIP.

• Tutorials

A continuously updated, Chinese-language curated list of large-language-model resources, organized by topic such as data processing, fine-tuning, reinforcement learning, inference, evaluation, RAG, agents, MCP and small language models.

• Curated lists

A single control-plane process that deploys, routes, secures and observes A2A-speaking AI agents behind one gateway, with an LLM router that never exposes a real API key to an agent.

• Agent frameworks
• LLM gateways