{"id":49391250,"url":"https://github.com/hexart/prompt-booster","last_synced_at":"2026-04-28T12:15:40.073Z","repository":{"id":294627740,"uuid":"968555144","full_name":"hexart/prompt-booster","owner":"hexart","description":"Prompt Booster: A comprehensive tool for optimizing LLM prompts with version control, A/B testing, and template management. Supports multiple AI providers (OpenAI, Gemini, DeepSeek, Qwen, etc.) across web and desktop platforms. Increase your AI prompt effectiveness with professional engineering tools.","archived":false,"fork":false,"pushed_at":"2026-04-06T09:34:41.000Z","size":7229,"stargazers_count":12,"open_issues_count":2,"forks_count":1,"subscribers_count":2,"default_branch":"main","last_synced_at":"2026-04-06T11:27:01.012Z","etag":null,"topics":["ab-testing","ai","ai-optimization","claude","cross-platform","deepseek","electron","gemini","llm-tools","lm-studio","monorepo","multi-language","openai","prompt-engineering","react","tailwindcss","turborepo","typescript","version-control","vite"],"latest_commit_sha":null,"homepage":"https://hexart.github.io/prompt-booster/","language":"TypeScript","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":null,"status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/hexart.png","metadata":{"files":{"readme":"README-zh.md","changelog":null,"contributing":"CONTRIBUTING-zh.md","funding":".github/FUNDING.yml","license":null,"code_of_conduct":null,"threat_model":null,"audit":null,"citation":null,"codeowners":null,"security":null,"support":null,"governance":null,"roadmap":null,"authors":null,"dei":null,"publiccode":null,"codemeta":null,"zenodo":null,"notice":null,"maintainers":null,"copyright":null,"agents":null,"dco":null,"cla":null},"funding":{"custom":["https://paypal.me/promptbooster"]}},"created_at":"2025-04-18T09:42:56.000Z","updated_at":"2026-04-06T09:34:50.000Z","dependencies_parsed_at":"2025-12-01T13:06:09.831Z","dependency_job_id":null,"html_url":"https://github.com/hexart/prompt-booster","commit_stats":null,"previous_names":["hexart/prompt-booster"],"tags_count":22,"template":false,"template_full_name":null,"purl":"pkg:github/hexart/prompt-booster","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/hexart%2Fprompt-booster","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/hexart%2Fprompt-booster/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/hexart%2Fprompt-booster/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/hexart%2Fprompt-booster/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/hexart","download_url":"https://codeload.github.com/hexart/prompt-booster/tar.gz/refs/heads/main","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/hexart%2Fprompt-booster/sbom","scorecard":null,"host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":286080680,"owners_count":32379990,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2026-04-28T11:25:28.583Z","status":"ssl_error","status_checked_at":"2026-04-28T11:25:05.435Z","response_time":56,"last_error":"SSL_connect returned=1 errno=0 peeraddr=140.82.121.5:443 state=error: unexpected eof while reading","robots_txt_status":"success","robots_txt_updated_at":"2025-07-24T06:49:26.215Z","robots_txt_url":"https://github.com/robots.txt","online":false,"can_crawl_api":true,"host_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub","repositories_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories","repository_names_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repository_names","owners_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners"}},"keywords":["ab-testing","ai","ai-optimization","claude","cross-platform","deepseek","electron","gemini","llm-tools","lm-studio","monorepo","multi-language","openai","prompt-engineering","react","tailwindcss","turborepo","typescript","version-control","vite"],"created_at":"2026-04-28T12:15:38.670Z","updated_at":"2026-04-28T12:15:40.021Z","avatar_url":"https://github.com/hexart.png","language":"TypeScript","funding_links":["https://paypal.me/promptbooster"],"categories":[],"sub_categories":[],"readme":"# Prompt Booster\n![Prompt Booster](img/banner.png)\n\n[English](README.md) [在线体验](https://hexart.github.io/prompt-booster/)\n\n一个用于优化和增强多平台大型语言模型(LLMs)提示词的综合性单体仓库项目。\n\n## 概述\n\nPrompt Booster是一款专为帮助用户优化大型语言模型提示词而设计的专业工具。它利用多个AI提供商，实现跨平台的提示词优化、版本控制、A/B测试和模板管理。\n\n该项目采用单体仓库架构，使用Turborepo和PNPM工作区，组织为包含共享代码的packages和特定平台应用的apps。\n\n## 项目结构\n\n```markdown\nprompt-booster/\n├── apps/                      # 特定平台实现\n│   ├── web/                   # Web应用（包含核心业务逻辑和UI组件）\n│   │   └── src/\n│   │       ├── core/          # 核心业务逻辑（提示词管理、模型配置、状态管理）\n│   │       ├── components/    # UI组件\n│   │       └── hooks/         # 自定义React Hooks\n│   └── desktop/               # Electron桌面应用\n├── packages/                  # 共享包\n│   └── api/                   # 针对LLM提供商的API客户端实现\n├── backend/                   # FastAPI后端服务（计划中）\n├── docs/                      # 项目文档\n├── docker/                    # Docker配置文件\n│   ├── frontend.Dockerfile    # 前端容器构建文件\n│   └── nginx.conf             # Nginx配置\n└── docker-compose.yml         # Docker compose配置\n```\n\n## 核心功能\n\n### Web应用核心模块\n\nWeb应用包含完整的核心业务逻辑（位于`apps/web/src/core`），提供：\n\n- 模型配置管理\n- 带版本控制的提示词管理\n- 用于提示词优化的模板系统\n- 使用Zustand进行状态管理\n- 存储实用工具\n\n[查看Web应用文档](apps/web/README-zh.md)\n\n### @prompt-booster/api\n\n一个用于与各种LLM服务交互的灵活客户端库：\n\n- 多个LLM提供商的统一接口\n- 支持OpenAI、Gemini、DeepSeek、Hunyuan、Siliconflow和Ollama\n- 流式响应处理\n- 错误管理\n- 认证策略\n\n[查看API包文档](packages/api/README-zh.md)\n\n## 应用\n\n### Web应用\n\n基于浏览器的提示词优化应用：\n\n- 提示词增强和迭代\n- 质量分析\n- A/B测试\n- 版本历史管理\n- 模型配置\n\n[查看Web应用文档](apps/web/README-zh.md)\n\n### 桌面应用\n\n使用Electron的原生桌面体验：\n\n- 跨平台支持（Windows、macOS、Linux）\n- 原生操作系统菜单和键盘快捷键\n- 离线功能\n- 与Web版本一致的UI\n\n**重要说明**：桌面应用被有意设计为完全独立于主项目结构的包。与单体仓库中使用pnpm的其他包不同，由于pnpm与Electron Builder之间的兼容性问题，桌面包专门使用npm进行依赖管理。桌面客户端虽然使用编译后的web应用，但维护着自己的构建过程和依赖树。有关详细的编译和开发说明，请参阅[桌面应用文档](apps/desktop/README-zh.md)。\n\n[查看桌面应用文档](apps/desktop/README-zh.md)\n\n## 设置和开发\n\n### 先决条件\n\n- Node.js 18.17.0或更高版本\n- PNPM 10.9.0或更高版本\n\n### 安装\n\n1. 安装 Node.js：\n\n   - 从 [Node.js 官网](https://nodejs.org/) 下载并安装 Node.js 18.17.0 或更高版本\n   - 在终端运行 `node -v` 和 `npm -v` 命令验证安装是否成功\n\n2. 安装 pnpm：\n\n   ```bash\n   # 使用 npm 安装\n   npm install -g pnpm\n   \n   # 或使用推荐的独立脚本安装\n   curl -fsSL https://get.pnpm.io/install.sh | sh -\n   \n   # 验证安装\n   pnpm --version\n   ```\n\n3. 克隆仓库：\n\n   ```bash\n   git clone https://github.com/hexart/prompt-booster.git\n   cd prompt-booster\n   ```\n\n4. 安装依赖：\n\n   ```bash\n   pnpm install\n   ```\n\n### 开发工作流\n\n启动Web应用的开发服务器：\n\n```bash\n# 构建包并以开发模式启动Web应用\npnpm dev\n```\n\n以开发模式运行桌面应用：\n\n```bash\n# 以开发模式启动桌面应用\ncd apps/desktop\nnpm install\nnpm run dev\n```\n\n构建所有包和应用：\n\n```bash\n# 构建所有包和应用\npnpm build\n```\n\n清理项目：\n\n```bash\n# 清理构建产物\npnpm clean\n\n# 深度清理（包括node_modules）\npnpm clean:all\n```\n\n### 桌面应用构建\n\n为不同平台构建桌面应用包：\n\n```bash\ncd apps/desktop\n# 为所有平台打包\nnpm run build\n\n# 为macOS打包\nnpm run build:mac\n```\n\n## 部署\n\n### Docker部署\n\n#### 使用自动更新快速启动\n\n使用以下命令拉取最新镜像并在容器中运行Prompt Booster。每次运行此命令时将自动更新到最新版本：\n\n```bash\ndocker pull ghcr.io/hexart/prompt-booster:latest \\\n\u0026\u0026 docker rm -f prompt-booster 2\u003e/dev/null || true \\\n\u0026\u0026 docker run -d \\\n    --name prompt-booster \\\n    --restart always \\\n    -p 8080:80 \\\n    ghcr.io/hexart/prompt-booster:latest\n```\n\n此命令：\n\n- 从GitHub容器注册表拉取最新镜像\n- 移除任何名为\"prompt-booster\"的现有容器\n- 创建一个具有自动重启策略的新容器\n- 将主机上的8080端口映射到容器中的80端口\n\n#### 使用Docker Compose\n\n项目还包括用于更高级部署的Docker Compose配置：\n\n1. 构建并启动容器：\n\n   ```bash\n   docker-compose up -d\n   ```\n\n   这将：\n\n   - 使用`docker/frontend.Dockerfile`构建前端容器\n   - 使用`docker/nginx.conf`配置Nginx\n   - 启动`docker-compose.yml`中定义的服务\n\n2. 在`http://localhost:8080`访问应用\n\n### 手动部署\n\n对于Web应用的手动部署：\n\n1. 构建项目：\n\n   ```bash\n   pnpm build\n   ```\n\n2. 构建文件将位于`apps/web/dist`\n\n3. 将这些文件部署到任何静态Web服务器\n\n## 当前开发状态\n\n该项目目前正在积极开发中。根据开发路线图：\n\n- 第1阶段（基础）和第2阶段（高级功能和桌面版）已完成\n- 第3阶段（增强功能）目前正在进行中\n- 第4-7阶段（后端和同步、移动端、微信小程序、完善和发布）计划在未来开发\n\n## 项目文档\n\n提供额外文档：\n\n- [架构设计](docs/architecture-design.md)\n- [后端架构](docs/backend-architecture.md)\n- [数据库设计](docs/database-design.md)\n- [开发路线图](docs/development-roadmap.md)\n\n## 技术栈\n\n- **语言**：TypeScript、Python（后端）\n- **前端**：React 19.1、TailwindCSS 4.1\n- **状态管理**：Zustand 5.0\n- **构建工具**：Vite、Turborepo、PNPM\n- **桌面**：Electron 37\n- **后端**（计划）：FastAPI、PostgreSQL\n- **容器化**：Docker\n\n## 贡献\n\n欢迎贡献！请参阅我们的[贡献指南](CONTRIBUTING-zh.md)获取如何为此项目贡献代码的详细说明。\n\n- 📋 [贡献指南](CONTRIBUTING-zh.md) - 如何Fork、开发和提交Pull Request\n- 🐛 [报告问题](https://github.com/hexart/prompt-booster/issues) - 报告错误或请求新功能\n\n请遵循贡献指南中概述的现有代码风格和开发指导原则。\n\n## 致谢\n\n本项目的开发过程中受到了 [linshenkx](https://github.com/linshenkx) 开发的 [prompt-optimizer](https://github.com/linshenkx/prompt-optimizer) 项目的启发和参考。我们在此对linshenkx在提示词工程和优化领域的开创性工作表示衷心的感谢。他们在MIT许可下的开源贡献对Prompt Booster的开发起到了重要的促进作用。我们强烈推荐大家查看他们的原始项目。\n\n## 许可证\n\n本项目采用MIT许可证和Apache许可证2.0的双重许可，您可以选择使用其中任一许可。\n\n- MIT许可证 ([LICENSE-MIT](LICENSE-MIT) 或 http://opensource.org/licenses/MIT)\n- Apache许可证2.0 ([LICENSE-APACHE](LICENSE-APACHE) 或 http://www.apache.org/licenses/LICENSE-2.0)\n\n© Hexart Studio 2026","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fhexart%2Fprompt-booster","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fhexart%2Fprompt-booster","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fhexart%2Fprompt-booster/lists"}