一套封面制作和x、微信公众号排版工具

Production-grade engineering skills for AI coding agents.

Open-source observability tool that uses AI agents to self-heal your software

Compress tool outputs, logs, files, and RAG chunks before they reach the LLM. 60-95% fewer tokens, same answers. Library, proxy, MCP server.

Comfortably monitor your Internet traffic 🕵️‍♂️

紫微斗数开源排盘引擎 — 基于倪海夏《天纪》体系，含完整排盘算法、四化系统、格局知识库、古籍原文数据

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.

Programmatic video for coding agents — HTML to video on your laptop. Turn HTML, CSS & data into real MP4s with pluggable render engines, 21 templates, AI soundtrack. Apache-2.0, no per-render fees.…

Pure Rust Inference Engine

Tile-Based Runtime for Ultra-Low-Latency LLM Inference

SGLang Omni: High-Performance Multi-Stage Pipeline Framework for Omni Models

🤗 ml-intern: an open-source ML engineer that reads papers, trains models, and ships ML models

🚀 An open-source, hands-on curriculum bridging the gap from basic RL concepts to LLM alignment, RLVR, and advanced Agentic systems.

AetherViz Master - 互动教育可视化建筑师，将任意教学主题转化为沉浸式3D交互网页

OpenAI-compatible proxy that stacks the free tiers of 16 LLM providers (~1.7B tokens/month) behind one /v1 endpoint — plus any custom OpenAI-compatible endpoint. Smart routing, automatic failover, …

Build your own AI SRE agents. The open source toolkit for the AI era.

VoxCPM2: Tokenizer-Free TTS for Multilingual Speech Generation, Creative Voice Design, and True-to-Life Cloning

A fast, helpful, and open-source document parser

Mooncake is the serving platform for Kimi, a leading LLM service provided by Moonshot AI.

High-performance KV cache storage for LLM inference — GPU offloading, SSD caching, and cross-node sharing via RDMA. Works with vLLM and SGLang.

面向 GEO 内容与工作流的 Skill 开源合集，持续更新中。

FlashInfer: Kernel Library for LLM Serving

Model Express is a Rust-based component meant to be placed next to existing model inference systems to speed up their startup times and improve overall performance.

HAMi-core compiles libvgpu.so, which ensures hard limit on GPU in container

Heterogeneous GPU Sharing on Kubernetes

Open-source Claude Code skills for SEO, GEO, Google Ads, Meta Ads

LyteNyte Grid monorepo: Build powerful data tables with a lightning-fast, zero-dependency React data grid (~40 KB). Headless or pre-styled. Declarative API. 150+ enterprise-grade features. Supporte…

Stealth Chromium that passes every bot detection test. Drop-in Playwright replacement with source-level fingerprint patches. 30/30 tests passed.

A unified library of SOTA model optimization techniques like quantization, distillation, pruning, neural architecture search, speculative decoding, etc. It compresses deep learning models for downs…

Standardized Distributed Generative and Predictive AI Inference Platform for Scalable, Multi-Framework Deployment on Kubernetes