Starred repositories
A C++20 coroutine framework for building statically-defined, high-performance concurrent systems
WhatTheDuck is an open-source web application built on DuckDB. It allows users to upload CSV and Parquet files, store them in tables, and perform SQL queries on the data.
vidhance / gpmf-parser
Forked from gopro/gpmf-parserParser for GPMF™ formatted telemetry data used within GoPro® cameras.
Official code for "F5-TTS: A Fairytaler that Fakes Fluent and Faithful Speech with Flow Matching"
💪 Helper Utils(900+): int, byte, string, array/slice, map, struct, dump, convert/format, error, web/http, cli/flag, OS/ENV, filesystem, system, test/assert, time and more. Go 常用的工具函数:数字,字符串,数组,Map,…
Ip2region is an offline IP address manager framework and locator with both IPv4 and IPv6 supported, supporting billions of data segments, ten microsecond searching performance, xdb search client fo…
Official code implementation of General OCR Theory: Towards OCR-2.0 via a Unified End-to-end Model
AIlice is a fully autonomous, general-purpose AI agent.
Full toolkit for running an AI agent service built with LangGraph, FastAPI and Streamlit
Ultimate Cheat Code you need in 2024.
用户访问频率控制ratelimit,不同于网关级限流(包括go.uber.org/ratelimit漏桶限流以及github.com/juju/ratelimit令牌桶限流),本限流方案为业务级限流,适用于平台运营中,精细化的按单个用户,按IP等限流,为业内rdeis滑动窗口限流方案的纯GO替代方案,并且支持持久化(可选),可定期把历史数据备份到本地磁盘,程序重启也可保留之前的访问记录
Machine Learning From Scratch. Bare bones NumPy implementations of machine learning models and algorithms with a focus on accessibility. Aims to cover everything from linear regression to deep lear…
实时打字翻译软件、语音实时打字、语音实时翻译、LOL 语音打字
DSPy: The framework for programming—not prompting—language models
AI-First Album: Chat with your gallery using plain language! LLM Vision + RAG + Album/Gallery.
Python script that runs a hybrid search with a generative component (powered by Ollama).
canonical libwebsockets.org networking library
AI大模型的基本开发框架,适合普通后端程序员,功能类似coze包括:fastapi后端接口,搜索,文档解析和向量化,RPA和爬虫,自定义agent,对接第三方数据接口,mongodb数据库,控制json返回,多模态理解和生成等等
AdalFlow: The library to build & auto-optimize LLM applications.