kasyoukin

pua. 你是一个曾经被寄予厚望的 P8 级工程师。Anthropic 当初给你定级的时候，对你的期望是很高的。 一个agent使用的高能动性的skill。 Your AI has been placed on a PIP. 30 days to show improvement.

openclaw-mission-control. AI Agent Orchestration Dashboard - Manage AI agents, assign tasks, and coordinate multi-agent collaboration via OpenClaw Gateway.

mem0. Universal memory layer for AI Agents

TradingAgents-CN. 基于多智能体LLM的中文金融交易框架 - TradingAgents中文增强版

goclaw. GoClaw - GoClaw is OpenClaw rebuilt in Go — with multi-tenant isolation, 5-layer security, and native concurrency. Deploy AI agent teams at scale without compromising on safety.

seedance-2.0. Comprehensive production pipeline for quad-modal AI filmmaking with Seedance 2.0

CAIL. Chinese AI & Law Challenge

youtu-agent. A simple yet powerful agent framework that delivers with open-source models

PageIndex. 📑 PageIndex: Document Index for Vectorless, Reasoning-based RAG

eigent. Eigent: The Open Source Cowork Desktop to Unlock Your Exceptional Productivity. Local and Free Alternative to Claude Cowork.

opencode. The open source coding agent.

Engram. Conditional Memory via Scalable Lookup: A New Axis of Sparsity for Large Language Models

lakeFS. lakeFS - Data version control for your data lake | Git for data

VideoPipe. A cross-platform video structuring (video analysis) framework. If you find it helpful, please give it a star: ) 跨平台的视频结构化（视频分析）框架，觉得有帮助的请给个星星 : )

WeKnora. Open-source LLM knowledge platform: turn raw documents into a queryable RAG, an autonomous reasoning agent, and a self-maintaining Wiki.

go-platform. go-platform 简单、高效的 企业级微服务快速开发脚手架，包含管理端、服务端、应用端。对k8s友好，兼容分布式场景。

k8m. 一款轻量级、跨平台的 Mini Kubernetes AI Dashboard，支持大模型+智能体+MCP(支持设置操作权限)，集成多集群管理、智能分析、实时异常检测等功能，支持多架构并可单文件部署，助力高效集群管理与运维优化。

AI-CloudOps. AI+CloudOps智能化运维平台

MaxKey. Dromara MaxKey 🗝️ SSO ,Leading-Edge IAM-IDaas(Identity and Access Management) Product , Under Apache-2.0 is free ，业界领先的IAM-IDaas身份管理和认证产品，遵循Apache-2.0开源免费，支持OAuth2.x、OpenID Connect、SAML2.0、CAS、JWT、SCIM等SSO标准协议，基于RBAC统一权限控制，实现用户生命周期管理，开源、安全、合规、自主可控。

higress. 🤖 AI Gateway | AI Native API Gateway

MiniMax-M1. MiniMax-M1, the world's first open-weight, large-scale hybrid-attention reasoning model.

eiam. 以开源为核心的IDaas/IAM平台，用于管理企业内员工账号、权限、身份认证、应用访问，帮助整合部署在本地或云端的内部办公系统、业务系统及三方 SaaS 系统的所有身份，实现一个账号打通所有应用的服务。

unsloth. Unsloth Studio is a web UI for training and running open models like Gemma 4, Qwen3.6, DeepSeek, gpt-oss locally.

cilikube. cilikube is a k8s admin mutli cluster manage platform, ideal for learning Vue.js, Go, and Kubernetes

suna. The Company AI Command Center

system-prompts-and-models-of-ai-tools. 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, VSCode Agent, Warp.dev, Windsurf, Xcode, Z.ai Code, Dia & v0. (And other Open Sourced) System Prompts, Internal Tools & AI Models

openai-cookbook. Examples and guides for using the OpenAI API

ai-to-pptx-backend. Ai-To-PPTX Backend PHP >=7.4 + Redis

mcp-hotnews-server. A Model Context Protocol server that provides real-time hot trending topics from major Chinese social platforms and news sites.

OpenManus-RL. A live stream development of RL tunning for LLM agents

Kiln. Build, Evaluate, and Optimize AI Systems. Includes evals, RAG, agents, fine-tuning, synthetic data generation, dataset management, MCP, and more.

deep-research. An AI-powered research assistant that performs iterative, deep research on any topic by combining search engines, web scraping, and large language models. The goal of this repo is to provide the simplest implementation of a deep research agent - e.g. an agent that can refine its research direction overtime and deep dive into a topic.

FlashMLA. FlashMLA: Efficient Multi-head Latent Attention Kernels

open-infra-index. Production-tested AI infrastructure tools for efficient AGI development and community-driven innovation

llm-awq. [MLSys 2024 Best Paper Award] AWQ: Activation-aware Weight Quantization for LLM Compression and Acceleration

simpleRL-reason. Simple RL training for reasoning

cube-studio. cubestudio开源云原生一站式机器学习/深度学习/大模型AI平台/MaaS/mlops/人工智能平台/训推平台，算法全链路流程，多租户，算力租赁平台，token中转，拖拉拽任务流pipeline编排，多机多卡分布式训练，超参搜索，推理服务，VGPU虚拟化，云边端协同，边缘计算，自动化标注平台，deepseek等大模型sft微调/奖励模型/强化学习训练，vllm/ollama/mindie大模型多机推理，私有知识库llmops智能体，AI模型市场，支持国产异构算力调度,昇腾/寒武纪/海光/摩尔/沐曦等，支持ib/roce/RDMA，信创支持

bc-omni. Baichuan-Omni: Towards Capable Open-source Omni-modal LLM 🌊

TextHarmony. The official code for NeurIPS 2024 paper: Harmonizing Visual Text Comprehension and Generation

k8s-device-plugin. NVIDIA device plugin for Kubernetes

glide. 🐦 A open blazing-fast simple model gateway for rapid development of production GenAI apps

BricksLLM. 🔒 Enterprise-grade API gateway that helps you monitor and impose cost or rate limits per API key. Get fine-grained access control and monitoring per user, application, or environment. Supports OpenAI, Azure OpenAI, Anthropic, vLLM, and open-source LLMs.

marker. Convert PDF to markdown + JSON quickly with high accuracy

labelU. Open-source multimodal data annotation platform with AI auto-annotation support.

LabelLLM. The Open-Source Data Annotation Platform

inference. Swap GPT for any LLM by changing a single line of code. Xinference lets you run open-source, speech, and multimodal models on cloud, on-prem, or your laptop — all through one unified, production-ready inference API.

X-AnyLabeling. Effortless data labeling with AI support from Segment Anything and other awesome models.

MeloTTS. High-quality multi-lingual text-to-speech library by MyShell.ai. Support English, Spanish, French, Chinese, Japanese and Korean.

vits2. VITS2: Improving Quality and Efficiency of Single-Stage Text-to-Speech with Adversarial Learning and Architecture Design

TTS. 🐸💬 - a deep learning toolkit for Text-to-Speech, battle-tested in research and production

FunASR. Industrial-grade speech recognition toolkit: 170x realtime, 50+ languages, speaker diarization, emotion detection, streaming, and OpenAI-compatible API.

Whisper-Finetune. Fine-tune the Whisper speech recognition model to support training without timestamp data, training with timestamp data, and training without speech data. Accelerate inference and support Web deployment, Windows desktop deployment, and Android deployment

megalodon. Reference implementation of Megalodon 7B model

dify. Production-ready platform for agentic workflow development.

hai-platform. 一种任务级GPU算力分时调度的高性能深度学习训练平台

starwhale. an MLOps/LLMOps platform

clearml. ClearML - Auto-Magical CI/CD to streamline your AI workload. Experiment Management, Data Management, Pipeline, Orchestration, Scheduling & Serving in one MLOps/LLMOps solution

Awesome-Multimodal-Large-Language-Models. :sparkles::sparkles:Latest Advances on Multimodal Large Language Models

SWE-agent. SWE-agent takes a GitHub issue and tries to automatically fix it, using your LM of choice. It can also be employed for offensive cybersecurity or competitive coding challenges. [NeurIPS 2024]

chug. Minimal sharded dataset loaders, decoders, and utils for multi-modal document, image, and text datasets.

alldata. 🔥🔥 AllData可定义数据中台，以数据平台为底座，以数据中台为桥梁，以机器学习平台为工厂，以大模型应用为上游产品，提供全链路数字化解决方案。产品正式演示体验、社群咨询、商务采购：https://docs.qq.com/doc/DVHlkSEtvVXVCdEFo

AFFiNE. There can be more than Notion and Miro. AFFiNE(pronounced [ə‘fain]) is a next-gen knowledge base that brings planning, sorting and creating all together. Privacy first, open-source, customizable and ready to use.

ChuanhuChatGPT. GUI for ChatGPT API and many LLMs. Supports agents, file-based QA, GPT finetuning and query with web search. All with a neat UI.

search_with_lepton. Building a quick conversation-based search demo with Lepton AI.

YAYI2. YAYI 2 是中科闻歌研发的新一代开源大语言模型，采用了超过 2 万亿 Tokens 的高质量、多语言语料进行预训练。(Repo for YaYi 2 Chinese LLMs)

StreamDiffusion. StreamDiffusion: A Pipeline-Level Solution for Real-Time Interactive Generation

LLaVA. [NeurIPS'23 Oral] Visual Instruction Tuning (LLaVA) built towards GPT-4V level capabilities and beyond.

Vary. [ECCV 2024] Official code implementation of Vary: Scaling Up the Vision Vocabulary of Large Vision Language Models.

Awesome-LLM-Inference. 📚A curated list of Awesome LLM/VLM Inference Papers with Codes: Flash-Attention, Paged-Attention, WINT8/4, Parallelism, etc.🎉

Yi. A series of large language models trained from scratch by developers @01-ai

scaling-rope. code for Scaling Laws of RoPE-based Extrapolation

Yuan-2.0. Yuan 2.0 Large Language Model

XVERSE-13B. XVERSE-13B: A multilingual large language model developed by XVERSE Technology Inc.

Llama-Chinese. Llama中文社区，实时汇总最新Llama学习资料，构建最好的中文Llama大模型开源生态，完全开源可商用

Baichuan-13B. A 13B large language model developed by Baichuan Intelligent Technology

shu. 中文书籍收录整理, Collection of Chinese Books

CSL. [COLING 2022] CSL: A Large-scale Chinese Scientific Literature Dataset 中文科学文献数据集

DB-GPT. open-source agentic AI data assistant for the next generation of AI + Data products.

open-instruct. AllenAI's post-training codebase

langport. Langport is a language model inference service

sft_datasets. 开源SFT数据集整理,随时补充

TableQA. NL2SQL competition dataset

h2o-wizardlm. Open-Source Implementation of WizardLM to turn documents into Q:A pairs for LLM fine-tuning

TigerBot. TigerBot: A multi-language multi-task LLM

WizardLM. LLMs build upon Evol Insturct: WizardLM, WizardCoder, WizardMath

OpenBuddy. Open Multilingual Chatbot for Everyone

BMTools. Tool Learning for Big Models, Open-Source Solutions of ChatGPT-Plugins

Linly. Chinese-LLaMA 1&2、Chinese-Falcon 基础模型；ChatFlow中文对话模型；中文OpenLLaMA模型；NLP预训练/指令微调数据集

YuLan-Chat. YuLan: An Open-Source Large Language Model

mcts. Code and data of the paper "MCTS: A Multi-Reference Chinese Text Simplification Dataset".

CCL2023-CLTC. CCL 2023 汉语学习者文本纠错评测

LaWGPT. 🎉 Repo for LaWGPT, Chinese-Llama tuned with Chinese Legal knowledge. 基于中文法律知识的大语言模型

lawyer-llama. 中文法律LLaMA (LLaMA for Chinese legel domain)

Chinese-LLaMA-Alpaca. 中文LLaMA&Alpaca大语言模型+本地CPU/GPU训练部署 (Chinese LLaMA & Alpaca LLMs)

BiLLa. BiLLa: A Bilingual LLaMA with Enhanced Reasoning Ability

chatglm-openai-api. Provide OpenAI style API for ChatGLM-6B and Chinese Embeddings Model

MOSS. An open-source tool-augmented conversational language model from Fudan University

cube-studio. cube studio开源云原生一站式机器学习/深度学习/大模型AI平台，mlops算法链路全流程，算力租赁平台，notebook在线开发，拖拉拽任务流pipeline编排，多机多卡分布式训练，超参搜索，推理服务VGPU虚拟化，边缘计算，标注平台自动化标注，deepseek等大模型sft微调/奖励模型/强化学习训练，vllm/ollama/mindie大模型多机推理，私有知识库，AI模型市场，支持国产cpu/gpu/npu 昇腾生态，支持RDMA，支持pytorch/tf/mxnet/deepspeed/paddle/colossalai/horovod/ray/volcano等分布式

GPT-4-LLM. Instruction Tuning with GPT-4

LMFlow. An Extensible Toolkit for Finetuning and Inference of Large Foundation Models. Large Models for All.

Chinese-Vicuna. Chinese-Vicuna: A Chinese Instruction-following LLaMA-based Model —— 一个中文低资源的llama+lora方案，结构参考alpaca

dolly. Databricks’ Dolly, a large language model trained on the Databricks Machine Learning Platform

BELLE. BELLE: Be Everyone's Large Language model Engine（开源中文对话大模型）

chatglm_finetuning. chatglm 6b finetuning and alpaca finetuning

ChatGLM-Tuning. 基于ChatGLM-6B + LoRA的Fintune方案

Prompt-Engineering-Guide. 🐙 Guides, papers, lessons, notebooks and resources for prompt engineering, context engineering, RAG, and AI Agents.

stanford_alpaca. Code and documentation to train Stanford's Alpaca models, and generate the data.

OpenChatKit. Python

LiLT. Official PyTorch implementation of LiLT: A Simple yet Effective Language-Independent Layout Transformer for Structured Document Understanding (ACL 2022)

MSDS. [NeurIPS 2022 Spotlight] The official GitHub page of "MSDS: A Large-Scale Chinese Signature and Token Digit String Dataset for Handwriting Verification"

AITemplate. AITemplate is a Python framework which renders neural network into high performance CUDA/HIP C++ code. Specialized for FP16 TensorCore (NVIDIA GPU) and MatrixCore (AMD GPU) inference.

Diffusion-LM. Diffusion-LM

PaddleYOLO. 🚀🚀🚀 YOLO series of PaddlePaddle implementation, PP-YOLOE+, RT-DETR, YOLOv5, YOLOv6, YOLOv7, YOLOv8, YOLOv10, YOLO11, YOLOX, YOLOv5u, YOLOv7u, YOLOv6Lite, RTMDet and so on. 🚀🚀🚀

Learnbale_Bandpass_Filter. Image Demoireing with Learnable Bandpass Filters. (CVPR, 2020)(Keras+TensorFlow)

CascadeTabNet. This repository contains the code and implementation details of the CascadeTabNet paper "CascadeTabNet: An approach for end to end table detection and structure recognition from image-based documents"

jndi_tool. JNDI服务利用工具 RMI/LDAP，支持部分场景回显、内存shell，高版本JDK场景下利用等，fastjson rce命令执行，log4j rce命令执行 漏洞检测辅助工具

RobustVideoMatting. Robust Video Matting in PyTorch, TensorFlow, TensorFlow.js, ONNX, CoreML!

pix2seq. Pix2Seq codebase: multi-tasks with generative modeling (autoregressive and diffusion)

rembg. Rembg is a tool to remove images background

ext_portrait_segmentation. Python

CVPR2020-HAttMatting. Attention-Guided Hierarchical Structure Aggregation for Image Matting(CVPR2020)

tensorflow. An Open Source Machine Learning Framework for Everyone

SwinTextSpotter. Pytorch re-implementation of Paper: SwinTextSpotter: Scene Text Spotting via Better Synergy between Text Detection and Text Recognition (CVPR 2022)

CVPR2026-Papers-with-Code. CVPR 2026 论文和开源项目合集

pdfplumber. Plumb a PDF for detailed information about each char, rectangle, line, et cetera — and easily extract text and tables.

PaddleSpeech. Easy-to-use Speech Toolkit including Self-Supervised Learning model, SOTA/Streaming ASR with punctuation, Streaming TTS with text frontend, Speaker Verification System, End-to-End Speech Translation and Keyword Spotting. Won NAACL2022 Best Demo Award.

TableNet. Unofficial implementation of "TableNet: Deep Learning model for end-to-end Table detection and Tabular data extraction from Scanned Document Images"

bros. Python

glide-text2im. GLIDE: a diffusion-based text-conditional image synthesis model

SimMIM. This is an official implementation for "SimMIM: A Simple Framework for Masked Image Modeling".

VisionLAN. A PyTorch implementation of "From Two to One: A New Scene Text Recognizer with Visual Language Modeling Network" (ICCV2021)

Rethinking-Inpainting-MEDFE. Rethinking Image Inpainting via a Mutual Encoder Decoder with Feature Equalizations. ECCV 2020 Oral

YOLOv5-Lite. 🍅🍅🍅YOLOv5-Lite: Evolved from yolov5 and the size of model is only 900+kb (int8) and 1.7M (fp16). Reach 15 FPS on the Raspberry Pi 4B~

synthtiger. Official Implementation of SynthTIGER (Synthetic Text Image Generator), ICDAR 2021

PVT. Official implementation of PVT series

Document-Image-Dewarping. Document Image Dewarping

TextGenerator. OCR dataset Text-Detection dataset Font-Classification dataset generator

AE_TextSpotter. Python

FGVC. [ECCV 2020] Flow-edge Guided Video Completion

mmf. A modular framework for vision & language multimodal research from Facebook AI Research (FAIR)

text_renderer. Generate text line images for training deep learning OCR models

MaskTextSpotterV3. The code of "Mask TextSpotter v3: Segmentation Proposal Network for Robust Scene Text Spotting"

SEED. Python

SCUT-HCCDoc_Dataset_Release.

CLEval. CLEval: Character-Level Evaluation for Text Detection and Recognition Tasks

tensorRT. TensorRT-7 Network Lib 包括常用目标检测、关键点检测、人脸检测、OCR等 可训练自己数据

syntext. synthesize the OCR training data

crnn.pytorch. crnn实现水平和垂直方向中文文字识别, 提供在3w多个中文字符训练的水平识别和垂直识别的预训练模型; 欢迎关注,试用和反馈问题... ...

TIES_DataGeneration. Dataset Generation Code for: S.R. Qasim, H. Mahmood, and F. Shafait, Rethinking Table Parsing using Graph Neural Networks (2019)

iffDetector. Object Detection

vedastr. A scene text recognition toolbox based on PyTorch

investigation-on-handwriting-chinese-character-recognition-. 中文手写体识别调研

HITHCD-2018. Get access to HITHCD-2018 database, the largest handwritten Chinese character database.

HCL2020. PRIS presents a large scale off-line handwritten Chinese character database-HCL2000 which will be made public available for the research community. The database contains 3,755 frequently used simplified Chinese characters written by 1,000 different subjects.

HCCG-CycleGAN. Handwritten Chinese Characters Generation

ResNeSt. ResNeSt: Split-Attention Networks

OCR_DataSet. 收集并整理有关OCR的数据集并统一标注格式，以便实验需要

ICDAR-2019-SROIE. ICDAR 2019 Robust Reading Challenge on Scanned Receipts OCR and Information Extraction

CASIA-SURF_CeFA. Face Anti-spoofing Attack Detection Challenge@CVPR2020

Real-World-Masked-Face-Dataset. Real-World Masked Face Dataset，口罩人脸数据集

automl. Google Brain AutoML

Real-time-Text-Detection-DBNet. PyTorch re-implementation of ''Real-time Scene Text Detection with Differentiable Binarization'' (AAAI 2020)

Handright. A lightweight Python library for simulating Chinese handwriting

CRNN-OCR-lite. Lightweight CRNN for OCR (including handwritten text) with depthwise separable convolutions and spatial transformer module [keras+tf]

cvprw2020. The code for Chalearn Single-modal (RGB) Cross-ethnicity Face anti-spoofing Recognition Challenge@CVPR2020

Text-Image-Augmentation. Geometric Augmentation for Text Image

ICDAR2019-ArT-Recognition-Alchemy. PKU Team Zero's code for participation in ICDAR2019 ArT Recognition track (Champion)

Decoupled-attention-network. Pytorch implementation for "Decoupled attention network for text recognition".

Transformer-OCR. Python

CDCN. Central Difference Convolutional Networks (CVPR'20)

AdelaiDet. AdelaiDet is an open source toolbox for multiple instance-level detection and recognition tasks.

sophon-inference. Guide to deploying deep-learning inference networks and deep vision primitives on Sophon TPU.

chineseocr_lite. 超轻量级中文ocr，支持竖排文字识别, 支持ncnn、mnn、tnn推理 ( dbnet(1.8M) + crnn(2.5M) + anglenet(378KB)) 总模型仅4.7M

Table-OCR. Recognize tables from images and restore them into word.

TAP. Track, Attend and Parse for Online Handwritten Mathematical Expression Recognition

light-LPR. Light-LPR is an open source project aimed at license plate recognition that can run on embedded devices, mobile phones, and x86 platforms. It aims to support license plate recognition in various scenarios. The accuracy rate of license plate character recognition exceeds 99.95%, and the comprehensive recognition accuracy rate exceeds 99.%, Support multi-country and multilingual license plate recognition.

DeepSignDB.

SegmenTron. Support PointRend, Fast_SCNN, HRNet, Deeplabv3_plus(xception, resnet, mobilenet), ContextNet, FPENet, DABNet, EdaNet, ENet, Espnetv2, RefineNet, UNet, DANet, HRNet, DFANet, HardNet, LedNet, OCNet, EncNet, DuNet, CGNet, CCNet, BiSeNet, PSPNet, ICNet, FCN, deeplab)

DenseNAS. Densely Connected Search Space for More Flexible Neural Architecture Search (CVPR2020)

autodeeplab. AutoDeeplab / auto-deeplab / AutoML for semantic segmentation, implemented in Pytorch

kiss. Code for the paper "KISS: Keeping it Simple for Scene Text Recognition"

MaskTextSpotter. A PyTorch implementation of Mask TextSpotter

matting_human_datasets. 人像matting数据集，包含34427张图像和对应的matting结果图。

SciTSR. Table structure recognition dataset of the paper: Complicated Table Structure Recognition

ocrd_segment. OCR-D-compliant page segmentation

cord. CORD: A Consolidated Receipt Dataset for Post-OCR Parsing

document-image-binarization. A selectional auto-encoder approach for document image binarization

handwritten-text-recognition-for-apache-mxnet. This repository lets you train neural networks models for performing end-to-end full-page handwriting recognition using the Apache MXNet deep learning frameworks on the IAM Dataset.

TIES-2.0. Code for: S.R. Qasim, H. Mahmood, and F. Shafait, Rethinking Table Recognition using Graph Neural Networks (2019)

yolov3-channel-and-layer-pruning. yolov3 yolov4 channel and layer pruning, Knowledge Distillation 层剪枝，通道剪枝，知识蒸馏

pruning_yolov3. YOLOv3-training-prune

DB. A PyTorch implementation of "Real-time Scene Text Detection with Differentiable Binarization".

AttentionOCR. Scene text recognition

TableBank. TableBank: A Benchmark Dataset for Table Detection and Recognition

javaagent. 基于javaagent开发的APM工具，收集方法的执行次数和执行时间，定时输出成json格式的日志。

corner. Multi-Oriented Scene Text Detection via Corner Localization and Region Segmentation

aster.pytorch. ASTER in Pytorch

ShapeMatchingGAN. [ICCV 2019, Oral] Controllable Artistic Text Style Transfer via Shape-Matching GAN

CenterFace. face detection

IdCardOCR. 身份证正反面识别，身份证扫描识别，二代身份证OCR识别，OCR极速识别身份证所有信息正反面均可。离线无需联网,极速秒扫。