Explore the directory

A low-code Python tool for building multi-agent large language model applications, covering prototyping, data-driven iteration, one-click deployment and cross-platform scaling.

• Agent frameworks

A privacy-focused, self-hosted AI workspace combining chat, a multi-agent team feature with human review, a visual workflow builder and Telegram integration, running on a user's own infrastructure and model choice.

• Inference

A collection of ready-to-use DESIGN.md files, each describing a brand's visual language, that Claude Design can expand into a full scaffolded UI design system in one step.

• Design tools
• Curated lists

A library for mechanistic interpretability of GPT-style language models that exposes a model's internal activations so they can be cached, edited, removed or replaced while the model runs.

• Libraries

A Python framework for building, running and evaluating LLM agents with full support for the Model Context Protocol, including sampling and elicitation, plus an interactive terminal and multiple model providers.

• Agent frameworks

A local hub that gives AI chat clients such as OpenClaw, Claude Desktop or Cursor shared, persistent notes, files, reminders and tools through the Model Context Protocol, or can be used on its own through a built-in web chat.

• MCP servers
• Agent memory

The official Rust SDK for the Model Context Protocol, built on the Tokio async runtime, providing client and server implementations plus a macro crate for defining MCP tools.

• MCP servers

A high-performance inference engine for 4-bit diffusion models, based on the SVDQuant quantization method, supporting FLUX and Qwen-Image models with ComfyUI integration.

• Inference
• Generative media

A curated collection of production-ready AI agent templates for the OpenClaw ecosystem, each a copy-paste SOUL.md configuration file spanning categories such as productivity, marketing, DevOps and customer support.

• Curated lists

A runtime library that makes per-step model, budget and policy decisions inside an AI agent's execution loop, aiming to cut cost and latency while preserving output quality.

• LLM gateways

A free, open-source GUI for the Windows Subsystem for Linux, and for native Linux and macOS virtual machines on a Mac, covering distro install, backup, configuration and remote access without memorizing wsl.exe flags.

• Desktop utilities

A PyTorch library of vector and scalar quantization techniques, transcribed from DeepMind's TensorFlow implementation, used for models such as VQ-VAE-2 and Jukebox.

• Libraries

An open-source, task-oriented AI agent productivity platform organized around per-project workspaces, with traceable long-term memory, per-task cost tracking and automatic routing between models.

• Agent frameworks

A Model Context Protocol server that exposes Ghidra's reverse-engineering capabilities as tools for AI agents, covering disassembly annotation, structure creation, script execution and cross-binary documentation transfer.

• MCP servers
• Security

A lightweight companion Docker container that backs up Docker volumes on a schedule or on demand to local storage or to S3, WebDAV, Azure Blob, Dropbox, Google Drive, or SSH destinations.

• Containers

A memory framework for LLMs, inspired by human long-term memory, that indexes documents as a knowledge graph so agents can retrieve across multiple hops and integrate new knowledge continually.

• Agent memory
• RAG

A large curated list of game development resources covering engines, math, physics, animation, networking, and tooling across multiple programming languages.

• Curated lists

An Agent Skill that gives AI agents a supply-chain research method for spotting stocks and funds tied to technology-hype cycles, tracing a hot theme down to its supply bottlenecks before ranking research candidates.

• Agent skills

A coding agent CLI that ships full-stack projects, features, fixes and tests while building a per-developer profile of coding preferences from every accepted, rejected or edited suggestion.

• Coding agents

A real-time operating system for embedded systems, scaling from 8-bit to 64-bit microcontrollers with POSIX and ANSI standards compliance.

• Libraries

An open-source web app builder that uses local CLI coding agents such as Claude Code, Codex, Gemini CLI or Cursor Agent to generate a working application from a natural-language description and preview it live.

• Coding agents

An independent, open-source local workspace that lets ChatGPT read and edit files, run tests, keep terminals open and delegate split tasks to multiple workers, while staying within the provider's usage rules.

• Coding agents

A Chinese translation of the book Build a Large Language Model (From Scratch), covering how GPT-style large language models are designed, trained and applied, together with its accompanying practice code.

• Tutorials
• Books

A collection of reusable Agent Skills for AI coding, research and workflow agents, grouped by category and each packaged with a SKILL.md file explaining when and how to use it.

• Agent skills