Our library for RL environments + evals

Multimodal Retrieval-augmented Generation Framework Built by Tongyi Lab, Alibaba Group.

Coding Agent singularly focused efficiency and context curation. Reduces API costs by 50-80% vs other agent AND improves the code quality at the same time. Uses Hash Anchored edits, massively paral…

Open Source framework for voice and multimodal conversational AI

Official skills for the GLM family of models.

TimesFM (Time Series Foundation Model) is a pretrained time-series foundation model developed by Google Research for time-series forecasting.

BISHENG is an open LLM devops platform for next generation Enterprise AI applications. Powerful and comprehensive features include: GenAI workflow, RAG, Agent, Unified model management, Evaluation,…

Sparse Transition Matrix-Accelerated Trie Index for Constrained Decoding (https://arxiv.org/abs/2602.22647)

SyGra - Graph-oriented Synthetic data generation Pipeline

Implementing a ChatGPT-like LLM from scratch, step by step

Convert PowerPoint files into semantically rich text using vision language models

Implementation of the SSR algorithm of the paper "LLMs Reproduce Human Purchase Intent via Semantic Similarity Elicitation of Likert Ratings"

A massively multilingual modern encoder language model

PDF scientific paper translation with preserved formats - 基于 AI 完整保留排版的 PDF 文档全文双语翻译，支持 Google/DeepL/Ollama/OpenAI 等服务，提供 CLI/GUI/Docker

Cleanlab's open-source library is the standard data-centric AI package for data quality and machine learning with messy, real-world data and labels.

Official Code of Memento: Fine-tuning LLM Agents without Fine-tuning LLMs

Course to get into Large Language Models (LLMs) with roadmaps and Colab notebooks.

A one stop repository for generative AI research updates, interview resources, notebooks and much more!

A powerful tool for creating fine-tuning datasets for LLM

[ACL 2025 Industry Track (Oral)] Sentiment Reasoning for Healthcare

Full-stack framework for building Multi-Agent Systems with memory, knowledge and reasoning.

HumanLayer enables AI agents to communicate with humans in tool-based and async workflows. Guarantee human oversight of high-stakes function calls with approval workflows across slack, email and mo…

streamline the fine-tuning process for multimodal models: PaliGemma 2, Florence-2, and Qwen2.5-VL

Fast and High-Quality Zero-Shot Text-to-Speech with Flow Matching