"AI-Trader: Can AI Beat the Market?" Live Trading Bench: https://hkuds.github.io/AI-Trader/

The best ChatGPT that $100 can buy.

Official Repository for QuantAgent

Now, Stronger AI Pushes Frontiers, Stronger Our Shared Future.

DeepEvolve is a research and coding agent for new algorithm discovery in different science domains with Deep Research and AlphaEvolve.

Local Deep Research achieves ~95% on SimpleQA benchmark (tested with GPT-4.1-mini). Supports local and cloud LLMs (Ollama, Google, Anthropic, ...). Searches 10+ sources - arXiv, PubMed, web, and yo…

User-friendly AI Interface (Supports Ollama, OpenAI API, ...)

Optimizing inference proxy for LLMs

Tongyi Deep Research, the Leading Open-source Deep Research Agent

Recursive-Open-Meta-Agent v0.1 (Beta). A meta-agent framework to build high-performance multi-agent systems.

Code to accompany the Universal Deep Research paper (https://arxiv.org/abs/2509.00244)

aider is AI pair programming in your terminal

Hierarchical Reasoning Model Official Release

benchmark and evaluate generative research synthesis

A multi-agent LLM system for detecting and resolving cognitive dissonance.

📦 Repomix is a powerful tool that packs your entire repository into a single, AI-friendly file. Perfect for when you need to feed your codebase to Large Language Models (LLMs) or other AI tools lik…

Official inference framework for 1-bit LLMs

Awesome-GraphRAG: A curated list of resources (surveys, papers, benchmarks, and opensource projects) on graph-based retrieval-augmented generation.

A React Rich Text Editor that's block-based (Notion style) and extensible. Built on top of Prosemirror and Tiptap.

🌊 The leading agent orchestration platform for Claude. Deploy intelligent multi-agent swarms, coordinate autonomous workflows, and build conversational AI systems. Features enterprise-grade archite…

Einstein Fields official implementation in JAX.

Python tool for converting files and office documents to Markdown.

Kimi K2 is the large language model series developed by Moonshot AI team

DeepResearch Bench: A Comprehensive Benchmark for Deep Research Agents

Deep learning at the speed of light.

An advanced tool for generating, visualizing, and evaluating domain-specific knowledge graphs and ontologies.

A library of Jupyter notebooks and corresponding YouTube lectures by Roman Paolucci

Agent Reinforcement Trainer: train multi-step agents for real-world tasks using GRPO. Give your agents on-the-job training. Reinforcement learning for Qwen2.5, Qwen3, Llama, and more!