betars

hermes-agent. The agent that grows with you

awesome-gpt-image-2. Prompt as Code | GPT-Image2 工业级提示词引擎与模板库，470+ 个案例逆向工程，20+ 套工业级模板，并提炼出Skills，持续更新中

claude-code-best-practice. from vibe coding to agentic engineering - practice makes claude perfect

gstack. Use Garry Tan's exact Claude Code setup: 23 opinionated tools that serve as CEO, Designer, Eng Manager, Release Manager, Doc Engineer, and QA

poly-maker. An automated market making bot for the Polymarket Prediction Market that provides liquidity by maintaining orders on both sides of the order book with customizable parameters

nautilus_trader. Production-grade Rust-native trading engine with deterministic event-driven architecture

storefront-demo-nextjs. Algolia DevCon 2022 - Algolia powered storefront demo in React / Next.js

vuepress-theme-vdoing. 🚀一款简洁高效的VuePress知识管理&博客(blog)主题

DockerTarBuilder. 它是一个工作流。可快速构建指定架构/平台的docker镜像

NMSL. Abstraction your words——never mind the scandal and liber

dify. Build Agentic workflows, RAG pipelines, with rich AI model and tool support on one collaborative workspace. Deploy on cloud, VPC, or self-hosted, so teams move from prototype to production without rebuilding the stack.

firecrawl. The API to search, scrape, and interact with the web at scale. 🔥

F5-TTS. Official code for "F5-TTS: A Fairytaler that Fakes Fluent and Faithful Speech with Flow Matching"

Awesome-Dify-Workflow. 分享一些好用的 Dify DSL 工作流程，自用、学习两相宜。 Sharing some Dify workflows.

docker-registry-mirrors. 多平台容器镜像代理服务,支持 Docker Hub, GitHub, Google, k8s, Quay, Microsoft 等镜像仓库.

fastapi-amis-admin. FastAPI-Amis-Admin is a high-performance, efficient and easily extensible FastAPI admin framework. Inspired by django-admin, and has as many powerful functions as django-admin.

docker-xiaoya. 💡 Use Docker Compose to deploy Xiaoya services in a more elegant way, supports one-click deployment of Alist + Emby + Jellyfin, full-platform support, Linux/Windows/Mac/Synology, X86/Arm architecture

xiaoya-alist. 小雅Alist的相关周边

MiService. XiaoMi Cloud Service for mi.com

clash_for_windows_pkg. A Windows/macOS/Linux GUI based on Clash

LLM101n. LLM101n: Let's build a Storyteller

mdx-notes. ⛷ Cross-platform note-taking software, public layout editor, using MDX ⛷ 跨平台笔记软件，公众号排版编辑器，使用MDX来排版

ms-swift. Use PEFT or Full-parameter to CPT/SFT/DPO/GRPO 600+ LLMs (Qwen3.6, DeepSeek-V4, GLM-5.1, InternLM3, Llama4, ...) and 300+ MLLMs (Qwen3-VL, Qwen3-Omni, InternVL3.5, Ovis2.5, GLM4.5v, Gemma4, Llava, Phi4, ...) (AAAI 2025).

LlamaFactory. Unified Efficient Fine-Tuning of 100+ LLMs & VLMs (ACL 2024)

WeChatApi. wechathook、WeChatApi、微信Api、微信hook、微信接口、python微信接口、java微信Api、3.9.10.19、4.0、4.x、x64

fetch-in-chunks. A utility for fetching large files in chunks with support for parallel downloads and progress tracking.

WeChatFerry. 微信机器人，可接入DeepSeek、Gemini、ChatGPT、ChatGLM、讯飞星火、Tigerbot等大模型。微信 hook WeChat Robot Hook.

NGCBot. 一个基于✨HOOK机制的微信机器人，支持🌱安全新闻定时推送【FreeBuf，先知，安全客，奇安信攻防社区】，👯Kfc文案，⚡漏洞查询，⚡手机号归属地查询，⚡知识库查询，🎉星座查询，⚡天气查询，🌱摸鱼日历，⚡微步威胁情报查询， 🐛视频，⚡图片，👯帮助菜单。📫 支持积分功能，⚡支持自动拉人，，🌱自动群发，👯Ai回复（国内主流AI模型，扣子，FastGpt，Dify全面支持！），⚡视频号解析，😄自定义程度丰富，小白也可轻松上手！

indie-hacker-tools. 收录独立开发者出海技术栈和工具

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

InternLM. Official release of InternLM series (InternLM, InternLM2, InternLM2.5, InternLM3).

vue-fabric-editor. 快图设计-基于fabric.js和Vue的开源图片编辑器，可自定义字体、素材、设计模板。fabric.js and Vue based image editor, can customize fonts, materials, design templates.

Baichuan-7B. A large-scale 7B pretraining language model developed by BaiChuan-Inc.

customizable-gpt-chatbot. Veldra — talk an agent into existence, then watch it grow. A self-hostable, local-first agent platform: describe what you need in plain language and it compiles a working agent tools, MCP, RAG, teams. The more you use it, the better it gets agents learn from your feedback and reshape as you talk.

KgCLUE. KgCLUE: 大规模中文开源知识图谱问答

xircuits. Simple visual programming environment for jupyterlab

jsmind. a mind mapping library built by javascript

babyagi. Python

segment-anything. The repository provides code for running inference with the SegmentAnything Model (SAM), links for downloading the trained model checkpoints, and example notebooks that show how to use the model.

React-Landing-Page-Template. A simple react one page landing page templates for startups/companies

summarizepaper. An AI-powered arXiv paper summarization website with a virtual assistant for answering questions.

qdrant-client. Python client for Qdrant vector search engine

DocsGPT. Private AI platform for agents, assistants and enterprise search. Built-in Agent Builder, Deep research, Document analysis, Multi-model support, and API connectivity for agents.

trlx. A repo for distributed training of language models with Reinforcement Learning via Human Feedback (RLHF)

researchgpt. A LLM based research assistant that allows you to have a conversation with a research paper

CBoard. An easy to use, self-service open BI reporting and BI dashboard platform.

lectures. Oxford Deep NLP 2017 course

reinforcement-learning-an-introduction. Python Implementation of Reinforcement Learning: An Introduction

wxBot. Deprecated

end-to-end-for-chinese-plate-recognition. 多标签分类,端到端的中文车牌识别基于mxnet, End-to-End Chinese plate recognition base on mxnet

SeetaFaceEngine. C++

stockholm. 一个股票数据（沪深）爬虫和选股策略测试框架

caffe. Caffe: a fast open framework for deep learning.

deepdetect. Deep Learning Server and CLI for Torch and TensorRT

ccv. C-based/Cached/Core Computer Vision Library, A Modern Computer Vision Library

AgeGenderDeepLearning. Jupyter Notebook

OpenCV_Rectangle_Detection. Alters the default rectangle detection algorithm in OpenCV to filter out found rectangles

tensorflow. An Open Source Machine Learning Framework for Everyone

SqueezeNet. SqueezeNet: AlexNet-level accuracy with 50x fewer parameters

DataAugmentation. Image data augmentation tool for training of image recognition algorithm

opencv. Open Source Computer Vision Library

fast-rcnn. Fast R-CNN

awesome-deep-learning. A curated list of awesome Deep Learning tutorials, projects and communities.

libfacedetection. An open source library for face detection in images. The face detection speed can reach 1000FPS.

awesome-rl. Reinforcement learning resources curated

mxnet. Lightweight, Portable, Flexible Distributed/Mobile Deep Learning with Dynamic, Mutation-aware Dataflow Dep Scheduler; for Python, R, Julia, Scala, Go, Javascript and more

the-art-of-command-line. Master the command line, in one page

Face-Resources.