Agent skill: make LLMs write docs in ASD-STE100 Simplified Technical
Repository Index
68,760 visible repositories in the index
3,433–3,456 of 12,561 · Most stars
The Open Images dataset
A set of React UI components that supports Pinterest’s design language
- javascript
- react
- design-system
ECMAScript proposal for type syntax that is erased - Stage 1
One proximity graph for vector search, sparse products & attention across RAM, VRAM & NVMe, over dense vectors, sequences, shapes & geospatial sets in 14 languages 🔍
- kann
- vector-search
- approximate-nearest-neighbor-search
- simd
LaiFeng IOS Live Kit,H264 and AAC Hard coding，support GPUImage Beauty， rtmp transmission，weak network lost frame，Dynamic switching rate
A modular Agentic RAG built with LangGraph — learn Retrieval-Augmented Generation Agents in minutes.
- agentic-ai
- agentic-rag
- agents
- rag
The open-source AI workbench for scientific research
Zotero plugin to manage your attachments: automatically rename, move, and attach PDFs (or other files) to Zotero items, sync PDFs from your Zotero library to your (mobile) PDF reader (e.g. an iPad, Android tablet, etc.), and extract PDF annotations.
Tiled scrollable window management for GNOME Shell
Enterprise HealthChecks for ASP.NET Core Diagnostics Package
📀 Unlimited Google Drive Storage by splitting binary files into base64
- google-drive
- unlimited
TranslatedGreasemonkey scripts ( Pagetual / Picviewer CE+ / DownloadAllContent ) Greasemonkey script collection (油猴腳本集) User script collection (ユーザースクリプト集)
- auto-scroll
- autopager
- autopagerize
- greasemonkey
A server-side library for sending Push Notifications to iOS (iPhone/iPad APNS), Android (C2DM and GCM - Google Cloud Message), Windows Phone, Windows 8, Amazon, Blackberry, and (soon) FirefoxOS devices!
Anti-laziness skill for AI agents. Core: the Depth Tree method, which splits a task N layers deep and gives every leaf the full time budget of the whole task, so effort multiplies with depth. Grounded in 2025-2026 research on model laziness, underthinking and premature completion.
Python package for the evaluation of odometry and SLAM
- slam
- odometry
- evaluation
- metrics
Translated《御舆：解码 Agent Harness》(Yuyu, "Imperial Carriage: Decoding the Agent Harness"): 420,000 characters dissecting the Harness skeleton and nervous system of AI Agents — an in-depth analysis of the Claude Code architecture, 15 chapters from the conversation loop to building your own Agent Harness. Online reading website:
[ICLR 2024 Oral] Generative Gaussian Splatting for Efficient 3D Content Creation
- image-to-3d
- text-to-3d
Agentic Orchestration Platform
- microservices
- orchestration-framework
- workflow-engine
- java
LightLLM is a Python-based LLM (Large Language Model) inference and serving framework, notable for its lightweight design, easy scalability, and high-speed performance.
A framework for Claude Opus to intelligently orchestrate subagents.
A collection of high-quality models for the MuJoCo physics engine, curated by Google DeepMind.
- mujoco
- robotics
[ICCV 2023] Tune-A-Video: One-Shot Tuning of Image Diffusion Models for Text-to-Video Generation
TranslatedQwen-Image 2.1 NSFW/pose image generation skill: author-level prompt recipes + NSFW LoRA + 136-pose VNCCS mannequin control; works with Claude Code / Codex / Cursor / OpenClaw
- agent-skill
- comfyui
- image-generation
- openclaw