Singapore

158 projets originaires de Singapore · 742.6k étoiles au total

88 de comptes personnels70 d'organisations

Singapore compte 158 projets d'IA open source suivis, dont deer-flow, crawl4ai, learn-claude-code. L'écosystème penche vers agentic, vlm, 3d. La localisation est déclarée par les propriétaires sur leur profil GitHub.

Une organisation déclare son siège social, pas le lieu où un projet a été écrit.

🧬 Familles ADN les plus présentes

agentic 5 vlm 5 3d 5 image-editing 4 video-generation 4 memory 4 browser-automation 3 agi 3

💻 Langages

Python 87 TypeScript 15 C++ 12 Go 6 Jupyter Notebook 6 JavaScript 5

⭐ Les plus étoilés

An open-source long-horizon SuperAgent harness that researches, codes, and creates. With the help of…

🚀🤖 Crawl4AI: Open-source LLM Friendly Web Crawler & Scraper. Don't be shy, join here:…

learn-claude-code

Bash is all you need - A nano claude code–like 「agent harness」, built from 0 to 1

awesome-scalability

The Patterns of Scalable, Reliable, and Performant Large-Scale Systems

UI-TARS-desktop

The Open-Source Multimodal AI Agent Stack: Connecting Cutting-Edge AI Models and Agent Infra

Chat2DB is a free, cross-platform, local-first database client and SQL workspace for developers, DBAs,…

 A curated list of awesome applications, softwares, tools and shiny things for macOS.

The official Lark/飞书 CLI tool, maintained by the larksuite team — built for humans and AI Agents.…

Automated Penetration Testing Agentic Framework Powered by Large Language Models

The fastest browser for AI agents to run browser automation, built for sharing your logged-in browser state…

awesome-nano-banana-pro-prompts

🍌 World's largest Nano Banana Pro prompt library — 10,000+ curated prompts with preview images, 16…

the-incredible-pytorch

The Incredible PyTorch: a curated list of tutorials, papers, projects, communities and more relating to…

Your AI trading terminal assistant for US stocks, commodities, forex, and crypto.

Trae Agent is an LLM-based agent for general purpose software engineering tasks.

Pioneering Automated GUI Interaction with Native Agents

The Fastest Distributed Database for Transactional, Analytical, and AI Workloads.

Swap GPT for any LLM by changing a single line of code. Xinference lets you run open-source, speech, and…

An amazing UI for OpenAI's ChatGPT (Website + Windows + MacOS + Linux)

awesome-gpt-image-2

🚀 World's largest GPT Image 2 prompt library, updated daily — 2000+ curated prompts with preview images,…

FlowGram is an extensible workflow development framework with built-in canvas, form, variable, and materials…

cursor-talk-to-figma-mcp

TalkToFigma: MCP integration between AI Agent (Cursor, Claude Code, Codex) and Figma, allowing Agentic AI to…

A Modern Orchestration Engine for Security

Free RPA tool by AI Singapore

Taming Stable Diffusion for Lip Sync!

Open-Source Personal Cloud OS for Always-On Agents

robotics-coursework

🤖 Places where you can learn robotics (and stuff like that) online 🤖

multidiffusion-upscaler-for-automatic1111

Tiled Diffusion and VAE optimize, licensed under CC BY-NC-SA 4.0

One-for-All Multimodal Evaluation Toolkit Across Text, Image, Video, and Audio Tasks

Awesome-LLM-Reasoning

From Chain-of-Thought prompting to OpenAI o1 and DeepSeek-R1 🍓

🦦 Otter, a multi-modal model based on OpenFlamingo (open-sourced version of DeepMind's Flamingo), trained…

[CVPR 2023] DepGraph: Towards Any Structural Pruning; LLMs, Vision Foundation Models, etc.

0 - 1 learn OpenClaw: sections to build an claw-AI agent from scratch

awesome-ai-residency

List of AI Residency Programs

Skywork-R1V is an advanced multimodal AI model series developed by Skywork AI, specializing in…

[EMNLP 2023 Demo] Video-LLaMA: An Instruction-tuned Audio-Visual Language Model for Video Understanding

🏆 Top-1 on 5+ benchmarks | Web UI | Supports MiroThinker, Claude, Kimi, OpenAI

The AI-Native Search Database. Best for agent storage, it unifies vector, text, structured, and…

AI-native SwiftUI component library with full-stack recipes — connect via MCP for instant access.

🔥 [ICCV 2025 Highlight] InfiniteYou: Flexible Photo Recrafting While Preserving Your Identity

benchmarking-gnns

Repository for benchmarking graph neural networks (JMLR 2023)

[IJCV2024] Exploiting Diffusion Prior for Real-World Image Super-Resolution

🤖️ Cross-platform AI language practice app （跨平台AI语言练习应用）

Open Science is an open-source, local-first, model-agnostic AI research workbench with scientific agents for…

[ICLR 2025] From anything to mesh like human artists. Official impl. of "MeshAnything: Artist-Created Mesh…

verl-agent is an extension of veRL, designed for training LLM/VLM agents via RL. verl-agent is also the…

PyTorch implementation of VALL-E(Zero-Shot Text-To-Speech), Reproduced Demo…

A high-quality PDF to Markdown tool based on large language model visual recognition.…

Awesome-Efficient-LLM

A curated list for Efficient Large Language Models

✨ The open-source multi-agent platform. Every agent gets its own computer, desktop, network, and long-term…

chat-ai-desktop

Unofficial ChatGPT desktop app for Mac & Windows menubar using Tauri & Rust

⚡️ Build Your Own chatgpt Bot|🧀 Discord/Slack/Kook/Telegram |⛓ ToolCall|🔖 Plugin Support | 🌻…

CRNN_Chinese_Characters_Rec

(CRNN) Chinese Characters Recognition.

penguin-harness

🐧 Harness for RSI. Let AI Build AI. Multi-Agent Auto-Dev Platform. Everything is Transparent.

nano-banana-pro-prompts-recommend-skill

AI skill for OpenClaw & Claude Code — recommend from 10000+ Nano Banana Pro (Gemini) image prompts. Smart…

A native macOS AI chat app powered by MLX. 100% local inference on Apple Silicon, no cloud required. Built…

fastquant — Backtest and optimize your ML trading strategies with only 3 lines of code!

Easy training on custom dataset. Various backends (MobileNet and SqueezeNet) supported. A YOLO demo to detect…

Introduction-to-Quantitative-Finance

AI+金融（量化）：1.多因子股票量化框架开源教程 2.学界和业界的经典资料收录 3.AI…

Official Repo For Pixel-LLM Codebase: Sa2VA (T-PAMI-26), SAMTok (CVPR-26), VRT (Arxiv-25), SaSaSa2VA (1-st…

Segment-Anything + 3D. Let's lift anything to 3D.

La localisation provient du profil GitHub de chaque propriétaire. Environ la moitié la renseignent : cette carte montre ceux-là, pas l'ensemble.