AG2 (formerly AutoGen) is a programming framework for agentic AI. Join the community at: https://discord.gg/pAbnFJrkgZ

Qwen2.5-Coder is the code version of Qwen2.5, the large language model series developed by Qwen team, Alibaba Cloud.

Reinforcement learning on general 2D physics environments in JAX

An intricately designed and formatted single-page version of the bitcoin whitepaper, available for printing as a desktop album or hanging as a wall poster.

This is the source repository containing all information necessary to reproduce the Cambridge RoboMaster platform.

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

Anthropic's educational courses

O1 Replication Journey: A Strategic Progress Report – Part I

Automate browser-based workflows with LLMs and Computer Vision

📺IPTV电视直播源更新工具🚀：包含💰央视、📡卫视、☘️广东及各省份地方台、🌊港·澳·台、🎬电影、🎥咪咕、🏀体育、🪁动画、🎮游戏、🎵音乐、🏛经典剧场；支持自定义增加频道；支持组播源、酒店源、订阅源、关键字搜索；每天自动更新两次，结果可用于TVBox等播放软件；支持工作流、Docker(amd64/arm64)、命令行、GUI运行方式 | IPTV live TV source update …

AIDE: the state-of-the-art machine learning engineer agent, generating machine learning solution code from natural language descriptions.

An Open-Source Python3 tool for recognizing layouts, tables, math formulas (LaTeX), and text in images, converting them into Markdown format. A free alternative to Mathpix, empowering seamless conv…

BrowserGym, a gym environment for web task automation in the Chromium browser.

TapeAgents is a framework that facilitates all stages of the LLM Agent development lifecycle

Official implementation of DICL (Disentangled In-Context Learning), featured in the paper Zero-shot Model-based Reinforcement Learning using Large Language Models.

Diffusion model derived evolutionary algorithm

Simple project page template for your research paper, built with Astro and Tailwind CSS

TEN Agent is the world’s first real-time multimodal agent integrated with the OpenAI Realtime API, RTC, and features weather checks, web search, vision, and RAG capabilities.

pix2tex: Using a ViT to convert images of equations into LaTeX code.

docTR (Document Text Recognition) - a seamless, high-performing & accessible library for OCR-related tasks powered by Deep Learning.

PDF to Markdown with vision models

[EMNLP 2024] A Retrieval Benchmark for Scientific Literature Search

Code for book Python Playground by Mahesh Venkitachalam (No Starch Press, USA)

抓取股票每日关键数据,计算各种指标,识别K线形态,内置多种选股策略,支持选股验证回测及自动交易，是量化投资工具。captures key daily data of stocks, calculates various stock indicators, K-line pattern recognition, has a variety of built-in stock selection…

An Open-source Large Language Model for Audit

Official Repo for ICML 2024 paper "Executable Code Actions Elicit Better LLM Agents" by Xingyao Wang, Yangyi Chen, Lifan Yuan, Yizhe Zhang, Yunzhu Li, Hao Peng, Heng Ji.

We present the first systematic study on the scaling property of raw agents instantiated by LLMs. We find that performance scales with the increase in the number of agents, using the simple(st) way…