OPEN-SOURCE TOOLS

真正有实用价值的 GitHub 开源工具

按股票分析、量化交易、数字货币、视频增强和图片增强等方向筛选实用开源项目。

Pake:一条命令把任意网页打包成 macOS/Windows/Linux 桌面应用 阅览图
开源项目 · 自动化与 Agent 类
开源
开源项目·自动化与 Agent 类·新手

Pake:一条命令把任意网页打包成 macOS/Windows/Linux 桌面应用

Pake 是 tw93 开源的网页转桌面应用工具,基于 Rust Tauri 构建,安装包通常小于 10M,比 Electron 方案小近 20 倍。它支持 CLI 一条命令打包、GitHub Actions 在线构建、成品热门包直接下载,以及脚本与 AI Agent 集成(--json、--config、llms.txt),采用 GPL-3.0 许可并附带输出例外条款,用户用 Pake 打包出的应用完全归自己所有。

GitHub 开源项目

0 阅读2026/09/10
查看指南
GitHub - microsoft/intelligent-terminal: A fork of Windows Terminal with native agent integration, right in your command line. 阅览图
开源项目 · 自动化与 Agent 类
开源
开源项目·自动化与 Agent 类·新手

GitHub - microsoft/intelligent-terminal: A fork of Windows Terminal with native agent integration, right in your command line.

Welcome to the Intelligent Terminal repo Table of Contents - What is Intelligent Terminal? - Installing and running Intelligent Terminal - Microsoft Store - WinGet - Downloads - Get Started - Keyboard Shortcuts - Configuration - Features - Agent Status Bar -

GitHub 开源项目

0 阅读2026/09/10
查看指南
GitHub - neuphonic/neutts: On-device TTS model by Neuphonic 阅览图
开源项目 · AI 音频与语音类
开源
开源项目·AI 音频与语音类·新手

GitHub - neuphonic/neutts: On-device TTS model by Neuphonic

NeuTTS HuggingFace 🤗: - NeuTTS-Air (English): Model , Q8 GGUF , Q4 GGUF , Space - NeuTTS-Nano Multilingual Collection: - NeuTTS-Nano (English): Model , Q8 GGUF , Q4 GGUF - NeuTTS-Nano-French: Model , Q8 GGUF , Q4 GGUF - NeuTTS-Nano-German: Model , Q8 GGUF ,

GitHub 开源项目

0 阅读2026/09/10
查看指南
GitHub - crynta/terax-ai: Lightweight (7MB) Terminal-first AI-native dev workspace 阅览图
开源项目 · 其他开源工具类
开源
开源项目·其他开源工具类·新手

GitHub - crynta/terax-ai: Lightweight (7MB) Terminal-first AI-native dev workspace

Terax Lightweight Terminal-first AI-native dev workspace. Website · Docs · Website's source code 简体中文 | Español | Deutsch | Français | 日本語 | 한국어 | Português | Polski | Русский | Bahasa Indonesia | हिन्दी Terax is a lightweight open-source terminal-first

GitHub 开源项目

0 阅读2026/09/10
查看指南
GitHub - TauricResearch/TradingAgents: TradingAgents: Multi-Agents LLM Financial Trading Framework 阅览图
开源项目 · 其他开源工具类
开源
开源项目·其他开源工具类·新手

GitHub - TauricResearch/TradingAgents: TradingAgents: Multi-Agents LLM Financial Trading Framework

Deutsch | Español | français | 日本語 | 한국어 | Português | Русский | 中文 TradingAgents: Multi-Agents LLM Financial Trading Framework News - [2026-08] TradingAgents v0.4.0 released with look-ahead / point-in-time fixes across FRED macro, social sentiment, and the

GitHub 开源项目

1 阅读2026/09/10
查看指南
GitHub - heygen-com/hyperframes: Write HTML. Render video. Built for agents. 阅览图
开源项目 · 开发者工具类
开源
开源项目·开发者工具类·新手

GitHub - heygen-com/hyperframes: Write HTML. Render video. Built for agents.

Write HTML. Render video. Built for agents. Quickstart | Showcase | Playground | Catalog | Docs | Discord HyperFrames is an open-source framework for turning HTML, CSS, media, and seekable animations into deterministic MP4 videos. Use it locally with the CLI,

GitHub 开源项目

0 阅读2026/09/10
查看指南
GitHub - HKUDS/ClawWork: "ClawWork: OpenClaw as Your AI Coworker - 💰 $15K earned in 11 Hours" 阅览图
开源项目 · 其他开源工具类
开源
开源项目·其他开源工具类·新手

GitHub - HKUDS/ClawWork: "ClawWork: OpenClaw as Your AI Coworker - 💰 $15K earned in 11 Hours"

ClawWork: OpenClaw as Your AI Coworker 💰 $19K in 8 Hours — AI Coworker for 44+ Professions | Technology & Engineering | Business & Finance | Healthcare & Social Services | Legal, Media & Operations | 🔴 Watch AI Coworkers Earn Money from Real-Life Tasks Rank

GitHub 开源项目

0 阅读2026/09/10
查看指南
GitHub - cisagov/RedEye: RedEye is a visual analytic tool supporting Red & Blue Team operations 阅览图
开源项目 · 游戏开发类
开源
开源项目·游戏开发类·新手

GitHub - cisagov/RedEye: RedEye is a visual analytic tool supporting Red & Blue Team operations

RedEye : Red Team C2 Log Visualization ⚠️ This Repo Currently in Maintenance Mode ⚠️ This GitHub repository is no longer under active development. We'll review community issues and pull requests for bug fixes, but won't consider any new feature additions.

GitHub 开源项目

0 阅读2026/09/10
查看指南
GitHub - shaxiu/XianyuAutoAgent: 智能闲鱼客服机器人系统:专为闲鱼平台打造的AI值守解决方案,实现闲鱼平台7×24小时自动化值守,支持多专家协同决策、智能议价和上下文感知对话。 阅览图
开源项目 · 自动化与 Agent 类
开源
开源项目·自动化与 Agent 类·新手

GitHub - shaxiu/XianyuAutoAgent: 智能闲鱼客服机器人系统:专为闲鱼平台打造的AI值守解决方案,实现闲鱼平台7×24小时自动化值守,支持多专家协同决策、智能议价和上下文感知对话。

🚀 Xianyu AutoAgent - 智能闲鱼客服机器人系统 专为闲鱼平台打造的AI值守解决方案,实现闲鱼平台7×24小时自动化值守,支持多专家协同决策、智能议价和上下文感知对话。 🌟 核心特性 智能对话引擎 功能模块 技术实现 关键特性 上下文感知 会话历史存储 轻量级对话记忆管理,完整对话历史作为LLM上下文输入 专家路由 LLM prompt+规则路由 基于提示工程的意图识别 → 专家Agent动态分发,支持议价/技术/客服多场景切换 业务功能矩阵 模块 已实现 规划中 核心引擎 ✅ LLM自动回复

GitHub 开源项目

0 阅读2026/09/10
查看指南
GitHub - winapps-org/winapps: Run Windows apps such as Microsoft Office/Adobe in Linux (Ubuntu/Fedora) and GNOME/KDE as if they were a part 阅览图
开源项目 · 文档办公类
开源
开源项目·文档办公类·新手

GitHub - winapps-org/winapps: Run Windows apps such as Microsoft Office/Adobe in Linux (Ubuntu/Fedora) and GNOME/KDE as if they were a part

Run Windows applications (including Microsoft 365 and Adobe Creative Cloud ) on GNU/Linux with KDE Plasma , GNOME or XFCE , integrated seamlessly as if they were native to the OS. Underlying Mechanism WinApps works by: - Running Windows in a Docker , Podman

GitHub 开源项目

2 阅读2026/09/10
查看指南
GitHub - microsoft/SkillOpt: SkillOpt is a text-space optimizer that trains reusable natural-language skills for frozen LLM agents through t 阅览图
开源项目 · 自动化与 Agent 类
开源
开源项目·自动化与 Agent 类·新手

GitHub - microsoft/SkillOpt: SkillOpt is a text-space optimizer that trains reusable natural-language skills for frozen LLM agents through t

SkillOpt: Executive Strategy for Self-Evolving Agent Skills Train agent skills like you train neural networks — with epochs, (mini-)batchsize, learning rates, and validation gates — but without touching model weights. 📖 For installation, data preparation,

GitHub 开源项目

0 阅读2026/09/10
查看指南
GitHub - browser-act/skills: Browser automation CLI built for AI agents. Break through anti-bot walls, hand off to humans across platforms w 阅览图
开源项目 · 自动化与 Agent 类
开源
开源项目·自动化与 Agent 类·新手

GitHub - browser-act/skills: Browser automation CLI built for AI agents. Break through anti-bot walls, hand off to humans across platforms w

What can BrowserAct be used for? BrowserAct enables AI agents and teams to perform real-browser automation, web data extraction, and account-based workflows. It helps agents get past anti-bot walls, hand off to humans across platforms when stuck, run parallel

GitHub 开源项目

0 阅读2026/09/10
查看指南