Stars
[NeurIPS 2024] Depth Anything V2. A More Capable Foundation Model for Monocular Depth Estimation
Fully animated, open-source component distribution built with React, TypeScript, Tailwind CSS, Motion, and Shadcn CLI. Browse a list of components you can install, modify, and use in your projects.
Open-Source Memory Engine for LLMs, AI Agents & Multi-Agent Systems
MemU is an open-source memory framework for AI companions
Data transformation framework for AI. Ultra performant, with incremental processing. 🌟 Star if you like it!
Democratizing Reinforcement Learning for LLMs
Tongyi Deep Research, the Leading Open-source Deep Research Agent
⚙️🦀 Build modular and scalable LLM Applications in Rust
The ultimate LLM/AI application development framework in Golang.
LLM agents built for control. Designed for real-world use. Deployed in minutes.
Implements harmful/harmless refusal removal using pure HF Transformers
TeXpert - the dataset designed to evaluate LLMs' capability to generate syntactically and logically correct LaTeX code from natural language descriptions
A collection of Compose libraries for advanced text formatting and alternative display types.
docTR (Document Text Recognition) - a seamless, high-performing & accessible library for OCR-related tasks powered by Deep Learning.
A tool to comfortably check complex LaTeX documents, e.g., dissertations.
A markup-based typesetting system that is powerful and easy to learn.
The open-source LLMOps platform: prompt playground, prompt management, LLM evaluation, and LLM observability all in one place.
🕹️ Open-source, developer-first LLMOps platform designed to streamline prompt design, version management, instant delivery, collaboration, troubleshooting, observability and more.
Test your prompts, agents, and RAGs. AI Red teaming, pentesting, and vulnerability scanning for LLMs. Compare performance of GPT, Claude, Gemini, Llama, and more. Simple declarative configs with co…
Supercharge Your LLM with the Fastest KV Cache Layer
[CVPR 2025] A Comprehensive Benchmark for Document Parsing and Evaluation
An on-premises, OCR-free unstructured data extraction, markdown conversion and benchmarking toolkit. (https://idp-leaderboard.org/)
[NeurIPS 2025] The official repo of SynLogic: Synthesizing Verifiable Reasoning Data at Scale for Learning Logical Reasoning and Beyond
使用LangGraph+DeepSeek-R1+FastAPI+Gradio实现一个带有记忆功能的流量包推荐智能客服web端用例,同时也支持gpt大模型、国产大模型(OneApi方式)、Ollama本地开源大模型、阿里通义千问大模型
A course of learning LLM inference serving on Apple Silicon for systems engineers: build a tiny vLLM + Qwen.
Python Backtesting library for trading strategies