Starred repositories
A set of ready to use Agent Skills for research, science, engineering, analysis, finance and writing.
OpenSource Claude Cowork. A desktop AI assistant that helps you with programming, file management, and any task you can describe.
The Autonomous Company Operating System
FULL Augment Code, Claude Code, Cluely, CodeBuddy, Comet, Cursor, Devin AI, Junie, Kiro, Leap.new, Lovable, Manus, NotionAI, Orchids.app, Perplexity, Poke, Qoder, Replit, Same.dev, Trae, Traycer AI…
ASTChunk is a Python toolkit for code chunking using Abstract Syntax Trees (ASTs), designed to create structurally sound and meaningful code segments.
Open sourced result for The Agent Company
🌐 Make websites accessible for AI agents. Automate tasks online with ease.
Code for the paper "AutoPresent: Designing Structured Visuals From Scratch" (CVPR 2025)
An agent benchmark with tasks in a simulated software company.
Interaction-first method for generating demonstrations for web-agents on any website
Draw a mockup and generate html for it
Data science interview questions and answers
Official code for VisProg (CVPR 2023 Best Paper!)
Build, personalize and control your own LLMs. From data pre-processing to fine-tuning, xTuring provides an easy way to personalize open-source LLMs. Join our discord community: https://discord.gg/T…
Rigourous evaluation of LLM-synthesized code - NeurIPS 2023 & COLM 2024
Official JAX implementation of MAGVIT: Masked Generative Video Transformer
Home of StarCoder: fine-tuning & inference!
Dense Passage Retriever - is a set of tools and models for open domain Q&A task.
Data and code for "DocPrompting: Generating Code by Retrieving the Docs" @ICLR 2023
A list of ethics related resources for researchers and practitioners of Natural Language Processing and Computational Linguistics
[ICLR 2023] Code for the paper "Binding Language Models in Symbolic Languages"
[EMNLP'23] Execution-Based Evaluation for Open Domain Code Generation
[EACL'23] MCoNaLa: A Benchmark for Code Generation from Multiple Natural Languages
CodeGen is a family of open-source model for program synthesis. Trained on TPU-v4. Competitive with OpenAI Codex.
CodeGeeX: An Open Multilingual Code Generation Model (KDD 2023)