Asian_Psyduck

InfiEpisteme. InfiEpisteme 📜 — Talk to Claude Code, get a research paper. 19 Markdown skills orchestrate the full pipeline: literature survey → ideation → experiments → writing → cross-model review. No framework, no lock-in — pure .md skills runnable by any LLM agent.

MAgent. A Platform for Many-Agent Reinforcement Learning

CopT. CopT: Contrastive On-Policy Thinking with Continuous Spaces for General and Agentic Reasoning

EnvScaler. The official implementation of "EnvScaler: Scaling Tool-Interactive Environments for LLM Agent via Programmatic Synthesis".

QuantGPT. Agent-driven alpha factory — LLM autonomously designs, backtests, and submits factors to WorldQuant BRAIN

RS-MLLM. Python

opentrader. 🤖 Open-source crypto trading bot | 📈 DCA & GRID strategies | ✨ UI | ⭐ Star to support the project!

Dentist. Python

SkillCenter. Python

OpenCLI. Make Any Website into CLI & Use your logged-in browser by AI agent.

benchbench. A package dedicated for running benchmark agreement testing

qlib. Qlib is an AI-oriented Quant investment platform that aims to use AI tech to empower Quant Research, from exploring ideas to implementing productions. Qlib supports diverse ML modeling paradigms, including supervised learning, market dynamics modeling, and RL, and is now equipped with https://github.com/microsoft/RD-Agent to automate R&D process.

dr-claw. A Super AI Lab with massive AI Doctors as Assistants. Best IDE for Research via AI Power.

pi-autoresearch. Autonomous experiment loop extension for pi

agentforge-v5. AgentForge v5.0 - The Agent writes it, runs it, fixes it, ships it.

TyphoFormer. 🏆(SIGSPATIAL'25 Best Short Paper Award) LLM-Augmented Spatial-Temporal Transformer for Typhoon Track Prediction

emmy. Benchmark and deploy optimized LLM models on GPU servers with vLLM or SGLang. Chose from a list of optimized recipes for popular models or create your own with custom configurations. Run benchmarks across different GPU types and configurations, track results, and share experiments with the community.

harbor. Framework for evaluating and improving agents

Hanpoetry. Python

open-problem-atlas. A living, machine-readable atlas of open problems for researchers, AI agents, and theorem provers.

PaperFarm. Let AI agents run experiments in any repo while you sleep.

Fast-CAD. TeX

crust. 🌟 Open Source AI Agent Security Infrastructure — intercepts and blocks dangerous agent behaviors before they happen. Just one command! Join us to build safer Human-AI Symbiosis!

shatianming5.github.io. SCSS

opencode-rl. Python

geolive. GeoLive transforms your browser into a real-time geographic intelligence command center. Just open it and watch the planet breathe.

tau2-bench. τ-Bench: A Benchmark for Tool-Agent-User Interaction in Real-World Domains

howaiworks. How AI Works is a self-contained, static website that walks through the entire history of artificial intelligence and machine learning through 50 interactive model demos spanning over 200 years.

LangSkills. Python

zhihu-scraper. 高性能知乎内容提取器：基于 curl_cffi 纯协议引擎，支持智能降级 Playwright。高保真提取文章、图片、数学公式，支持 Markdown + SQLite 双记录，内置炫酷 TUI 交互面板

OpenCode-FSM-Runner. Python

nanobot. Lightweight, open-source AI agent for your tools, chats, and workflows.

Dia-LLaMA. This is the official GitHub repository of the paper "Dia-LLaMA: Towards Large Language Model-driven CT Report Generation"

SAR-LoRA-DINO. Code for SAR-LoRA-DINO

RD-Agent. Research and development (R&D) is crucial for the enhancement of industrial productivity, especially in the AI era, where the core aspects of R&D are mainly focused on data and models. We are committed to automating these high-value generic R&D processes through R&D-Agent, which lets AI drive data-driven AI. 🔗https://aka.ms/RD-Agent-Tech-Report

LightRAG. [EMNLP2025] "LightRAG: Simple and Fast Retrieval-Augmented Generation"

agent-lightning. The absolute trainer to light up AI agents.

unreal-mcp. Enable AI assistant clients like Cursor, Windsurf and Claude Desktop to control Unreal Engine through natural language using the Model Context Protocol (MCP).

textgrad. TextGrad: Automatic ''Differentiation'' via Text -- using large language models to backpropagate textual gradients. Published in Nature.

freqtrade. Free, open source crypto trading bot

chatgpt-rs. this repository have been move at https://github.com/map-A/reverse-api

ICCV25-MCP. [ICCV 2025] Official Repository for "Multi-Cache Enhanced Prototype Learning for Test-Time Generalization of Vision-Language Models"

BrainNetworkTransformer. The open-source implementation of the NeurIPS 2022 paper Brain Network Transformer.

TradingAgents. TradingAgents: Multi-Agents LLM Financial Trading Framework

Agent_market. Python

PheroViz. Python

exsclaim. A toolkit for the automatic construction of self-labeled materials imaging datasets from scientific literature

PosterGen. Official Repository for PosterGen - CVPR Findings 2026

PyGIP. A Python package for Graph Intellectual Property Protection.

Transformer-Explainability. [CVPR 2021] Official PyTorch implementation for Transformer Interpretability Beyond Attention Visualization, a novel method to visualize classifications by Transformer based networks.

activitynet-qa. An VideoQA dataset based on the videos from ActivityNet

LGGPT. [IJCV 2025] Smaller But Better: Unifying Layout Generation with Smaller Large Language Models

Awesome-Generative-Models-for-OCR. [arXiv 25] OCRGenBench: A Comprehensive Benchmark for Evaluating OCR Generative Capabilities

ATOM. ATOM: A Framework of Detecting Query-Based Model Extraction Attacks for Graph Neural Networks

Awesome-Dataset-Reduction. A curated list of awesome papers on dataset reduction, including dataset distillation (dataset condensation) and dataset pruning (coreset selection).