开源项目目录

fastify

fastify-vite

★ 1,127

用于 Vite 集成的 Fastify 插件。该存储库也是 @fastify/vue 和 @fastify/react 的所在地。

microsoft

onnxruntime-genai

★ 1,127

该项目围绕「microsoft/onnxruntime-genai」构建，面向真实业务场景提供可复用的开源实践方案，支持稳定落地与可扩展的项目实践。

Dobiasd

frugally-deep

★ 1,127

A lightweight header-only library for using Keras (TensorFlow) models in C++.

elliothux

open-compute

★ 1,127

Self-hosted Cloudflare Workers-compatible platform with KV, D1, R2, Durable Objects, Queues, and Workflows in one Rust binary.

KroMiose

nekro-agent

★ 1,127

NekroAgent 是一个面向多人互动场景的跨平台 Agent 框架，集 Claude Code 沙盒执行、工作区编排、长期记忆、结构化 MCP 管理与可视化控制台于一体，兼具高扩展性、多模态交互、实时状态推送和自动化运行能力。项目支持 QQ、Discord、Telegram、Minecraft、BilibiliLive、WeChat、Email、SSE(SDK) 等多种平台接入，应用于构建高智能聊天机器人，可扩展为具备代码执行、工具调用、插件协作和复杂任务处理能力的通用 Agent 系统

protofire

solhint

★ 1,126

Solhint is an open-source project to provide a linting utility for Solidity code.

agentrq

agentrq

★ 1,125

AgentRQ: Human-in-loop realtime conversational task manager for AI Agents. Self-hosted! Control your own agents from wherever you want Mobile, Web, Desktop. Designed to work well with your own Claude subscriptions and any harness with ACP support.

flagos-ai

FlagGems

★ 1,124

FlagGems 是一个用于以 Triton 语言实现的大型语言模型的运算符库。

vndee

llm-sandbox

★ 1,124

Lightweight and portable LLM sandbox runtime (code interpreter) Python library.

tuan3w

obsidian-template

★ 1,124

Starter templates for Obsidian

PRIME-RL

TTRL

★ 1,124

[NeurIPS 2025] TTRL: Test-Time Reinforcement Learning

XiaoLuoLYG

GOD

★ 1,124

Govern, Observe, Direct - a real-time control room for agent societies

alexgreensh

attention-span

★ 1,124

Make your agents talk human. ADHD-friendly output styles for Claude Code, Codex, and others. So you can pay attention, not tokens.

mateaix

mateclaw

★ 1,123

🤖 MateClaw — Your second brain with Multi-Agent Orchestration, MCP Protocol, Skills & Memory, Dream, and Multi-Channel Support. Built on Spring AI Alibaba.

whisper-money

whisper-money

★ 1,123

Understand your personal finances. Forget Excels, try Whisper Money.

HarryR

z80ai

★ 1,123

Z80-μLM is a 2-bit quantized language model small enough to run on an 8-bit Z80 processor. Train conversational models in Python, export them as CP/M .COM binaries, and chat with your vintage computer.

coji

natural-japanese

★ 1,123

仕事の日本語を、読みやすくわかりやすく書く・直すための Agent Skill です。

nobodywho-ooo

nobodywho

★ 1,122

NobodyWho is an inference engine that lets you run LLMs locally and efficiently on any device.

localgpt-app

localgpt

★ 1,122

Local AI assistant, dreaming explorable worlds.

TencentCloudBase

CloudBase-AI-Toolkit

★ 1,122

Backend for AI coding agents on CloudBase — database, auth, functions via Plugin, Skills & MCP.