Explore the directory

An MCP server that gives an AI assistant terminal control, filesystem search and diff-based file editing, plus in-memory code execution and support for Excel, PDF and Word files.

• MCP servers

A CPU/GPU inference engine for large language models that exploits activation locality to run fast local inference on consumer-grade hardware.

• Inference

A multi-device agent framework that decomposes tasks into a dynamic DAG (Galaxy) and coordinates per-device agents (UFO2) across heterogeneous platforms over a unified agent protocol.

• Agent frameworks
• Workflow automation

An async embedded framework for Rust, using compile-time task scheduling and hardware abstraction layers to write embedded code without a traditional RTOS.

• Libraries

A context-engineering and spec-driven development system that runs AI coding agents through a five-step discuss, plan, execute, verify and ship loop to keep long sessions from losing quality.

• Agent skills

A curated, community-sourced collection of more than 2000 prompts for OpenAI's GPT Image 2 model, organized by use case, style and subject, with a searchable web gallery.

• Curated lists

A local-first, cross-platform desktop app that packages DeepSeek Harness as an installed application, managing agent presets, model providers, sessions and PPTX export in one place.

• Coding agents

A Python library for anomaly and outlier detection across tabular, time-series, graph, text, image and audio data, with more than 60 detectors and a benchmark-backed orchestration engine.

• Libraries

A reference library, not a working application, of production-tested patterns for Claude Code: auto-activating skills, hooks, specialized agents and a dev-docs system, drawn from six months of use on a TypeScript microservices project.

• Agent skills

A high-performance, production-ready open-source RLHF framework built on Ray and vLLM, with a unified agent-based design for scalable reinforcement learning from human feedback.

• Models

A retrieval system that renders web pages, PDFs and images as screenshots and searches over the images directly, keeping visual structure such as tables and charts that text extraction would lose.

• RAG

A Chinese-language, systematic learning guide for AI agent engineering and research, modeled on JavaGuide, covering agent systems, context engineering, RAG, evaluation and reinforcement learning post-training, oriented toward interview preparation.

• Tutorials

A collection of more than 45 tips for using Claude Code, from basic slash commands to advanced workflows such as git worktrees, containerized self-hosting and a custom status line, plus a dx plugin of everyday developer skills.

• Tutorials

A curated, actively updated list of practical resources on using large language models, based on a survey paper, including an evolutionary tree of notable models and their usage restrictions.

• Curated lists
• Papers

.NET bindings for the Chromium Embedded Framework, letting a WPF or Windows Forms application embed a Chromium browser control.

• Desktop
• Libraries

A self-hostable, lightweight server and website monitoring tool that checks system status, HTTP certificates, TCP and ping, runs scheduled tasks, and offers a web terminal with push alerts.

• Monitoring

A distributed relational database built on the Paxos protocol for high availability and linear scalability, with MySQL compatibility and built-in real-time analytics.

• Databases

An open-source meta-harness that gives a common orchestration layer over coding agents such as Claude Code, Codex and Cursor, letting them be swapped or combined, governed by policy, and run from any device.

• Coding agents

A script-driven, programmer-oriented 3D CAD modeller that compiles a description file into a solid model, using constructive solid geometry and 2D-outline extrusion rather than interactive sculpting.

• Design tools

An open-source, multi-provider terminal coding agent written in Rust, offering a TUI pair-programming experience with a plugin system, chat forking and memory consolidation.

• Coding agents
• Terminals

A set of eight SDKs sharing one C++ core that run LLMs, vision, speech and image-generation models locally on phones, browsers, desktops and servers, routing each call to the best engine the device has.

• Inference

A curated collection of prompts and image-generation styles for the Nano Banana Pro AI image model, sourced from social media, Replicate and prompt engineers, organized by use case.

• Curated lists

A read-path sync engine for Postgres that replicates data out to clients over a low-level HTTP API, handling partial replication and fan-out so applications and AI agents can work from synced local data.

• Databases

An open-source music generation model that plans a song's melody and chords symbolically before rendering a complete track with vocals and accompaniment from lyrics and a style prompt.

• Generative media