Lists (13)
Stars
Your own personal AI assistant. Any OS. Any Platform. The lobster way. 🦞
TreeSearch: Structure-aware document retrieval without embeddings.
本项目旨在分享大模型相关技术原理以及实战经验（大模型工程化、大模型应用落地）
Open source LangGraph Platform alternative - Self-hosted AI agent backend with FastAPI and PostgreSQL. Zero vendor lock-in, full control over your agent infrastructure.
Deep Agents is an agent harness built on langchain and langgraph. Deep Agents are equipped with a planning tool, a filesystem backend, and the ability to spawn subagents - making them well-equipped…
基于PaddleOCR重构，并且脱离PaddlePaddle深度学习训练框架的轻量级OCR，推理速度超快 —— A lightweight OCR system based on PaddleOCR, decoupled from the PaddlePaddle deep learning training framework, with ultra-fast inference speed.
Faker is a Python package that generates fake data for you.
🚀🤖 Crawl4AI: Open-source LLM Friendly Web Crawler & Scraper. Don't be shy, join here: https://discord.gg/jP8KfhDhyN
A version of verl to support diverse tool use
AISystem 主要是指AI系统，包括AI芯片、AI编译器、AI推理和训练框架等AI全栈底层技术
An implementation of iterative deep research using the OpenAI Agents SDK
verl: Volcano Engine Reinforcement Learning for LLMs
A modular, primitive-first, python-first PyTorch library for Reinforcement Learning.
Sky-T1: Train your own O1 preview model within $450
Fully local web research and report writing assistant
🪢 Open source LLM engineering platform: LLM Observability, metrics, evals, prompt management, playground, datasets. Integrates with OpenTelemetry, Langchain, OpenAI SDK, LiteLLM, and more. 🍊YC W23
Fully open reproduction of DeepSeek-R1
Qwen3-VL is the multimodal large language model series developed by Qwen team, Alibaba Cloud.
Multi-lingual large voice generation model, providing inference, training and deployment full-stack ability.
tiktoken is a fast BPE tokeniser for use with OpenAI's models.
Python3 package for Chinese/English OCR,use paddleocr-v5 onnx model(~20MB), with ultra-fast inference speed. 基于ppocr-v5-onnx模型推理，中英文OCR开源SOTA，推理速度超快。
Chinese version of CLIP which achieves Chinese cross-modal retrieval and representation generation.
Python tool for converting files and office documents to Markdown.
Text classification repository built with Torch, featuring training tricks, acceleration methods, and model optimization techniques like distillation, compression, and pruning. Supports single-labe…
心理健康大模型 (LLM x Mental Health), Pre & Post-training & Dataset & Evaluation & Depoly & RAG, with InternLM / Qwen / Baichuan / DeepSeek / Mixtral / LLama / GLM series models
Build and run agents you can see, understand and trust.
[GenAI Application Development Framework] 🚀 Build GenAI application quick and easy 💬 Easy to interact with GenAI agent in code using structure data and chained-calls syntax 🧩 Use Event-Driven Flow …