Use Claude Code as the foundation for coding infrastructure, allowing you to decide how to interact with the model while enjoying updates from Anthropic.

BrowseComp-Plus: A More Fair and Transparent Evaluation Benchmark of Deep-Research Agent

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

DeepResearchAgent is a hierarchical multi-agent system designed not only for deep research tasks but also for general-purpose task solving. The framework leverages a top-level planning agent to coo…

A collection of notebooks/recipes showcasing some fun and effective ways of using Claude.

DeepResearch Bench: A Comprehensive Benchmark for Deep Research Agents

Get started with building Fullstack Agents using Gemini 2.5 and LangGraph

LLM Frontend for Power Users.

Scalable toolkit for efficient model reinforcement

My learning notes for ML SYS.

Official Repository of "Learning to Reason under Off-Policy Guidance"

II-Researcher: a new open-source framework designed to aid building search / research agents

Model Context Protocol Servers

🌐 Make websites accessible for AI agents. Automate tasks online with ease.

"Your Fully-Automated Personal AI Assistant"

aider is AI pair programming in your terminal

Private chat with local GPT with document, images, video, etc. 100% private, Apache 2.0. Supports oLLaMa, Mixtral, llama.cpp, and more. Demo: https://gpt.h2o.ai/ https://gpt-docs.h2o.ai/

An API standard for single-agent reinforcement learning environments, with popular reference environments and related utilities (formerly Gym)

An AI-powered research assistant that performs iterative, deep research on any topic by combining search engines, web scraping, and large language models. The goal of this repo is to provide the si…

🤗 smolagents: a barebones library for agents that think in code.

[EMNLP 2025] OmniThink: Expanding Knowledge Boundaries in Machine Writing through Thinking

SGLang is a fast serving framework for large language models and vision language models.

🔍 Search-o1: Agentic Search-Enhanced Large Reasoning Models [EMNLP 2025]

Unified Efficient Fine-Tuning of 100+ LLMs & VLMs (ACL 2024)

🐝 The First Self-Improving Agentic Solution

Educational framework exploring ergonomic, lightweight multi-agent orchestration. Managed by OpenAI Solution team.

React app for inspecting, building and debugging with the Realtime API

Node.js + JavaScript reference client for the Realtime API (beta)