{"id":30800681,"url":"https://github.com/inoribea/aetherweaver","last_synced_at":"2025-09-05T20:12:19.727Z","repository":{"id":302627780,"uuid":"1005893846","full_name":"inoribea/AetherWeaver","owner":"inoribea","description":"AetherWeaver — an intelligent AI gateway \u0026 orchestrator for the Serverless Edge, with weighted intent routing across LangChain experts and end-to-end streaming.","archived":false,"fork":false,"pushed_at":"2025-08-25T09:59:25.000Z","size":14231,"stargazers_count":0,"open_issues_count":0,"forks_count":0,"subscribers_count":0,"default_branch":"main","last_synced_at":"2025-08-25T11:41:16.787Z","etag":null,"topics":["agents","intelligent-routing","langchain","lcel","serverless","vercel"],"latest_commit_sha":null,"homepage":"","language":"TypeScript","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":"mit","status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/inoribea.png","metadata":{"files":{"readme":"README-CN.md","changelog":null,"contributing":null,"funding":null,"license":"LICENSE","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}},"created_at":"2025-06-21T03:18:54.000Z","updated_at":"2025-08-25T09:59:28.000Z","dependencies_parsed_at":"2025-08-25T11:15:14.052Z","dependency_job_id":"223b0b3c-3d21-48d2-9309-944fea42942b","html_url":"https://github.com/inoribea/AetherWeaver","commit_stats":null,"previous_names":["inoribea/langchain-vercel"],"tags_count":0,"template":false,"template_full_name":null,"purl":"pkg:github/inoribea/AetherWeaver","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/inoribea%2FAetherWeaver","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/inoribea%2FAetherWeaver/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/inoribea%2FAetherWeaver/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/inoribea%2FAetherWeaver/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/inoribea","download_url":"https://codeload.github.com/inoribea/AetherWeaver/tar.gz/refs/heads/main","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/inoribea%2FAetherWeaver/sbom","scorecard":null,"host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":273813835,"owners_count":25172892,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2022-07-04T15:15:14.044Z","status":"online","status_checked_at":"2025-09-05T02:00:09.113Z","response_time":402,"last_error":null,"robots_txt_status":"success","robots_txt_updated_at":"2025-07-24T06:49:26.215Z","robots_txt_url":"https://github.com/robots.txt","online":true,"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":["agents","intelligent-routing","langchain","lcel","serverless","vercel"],"created_at":"2025-09-05T20:12:18.542Z","updated_at":"2025-09-05T20:12:19.711Z","avatar_url":"https://github.com/inoribea.png","language":"TypeScript","readme":"# AetherWeaver: 统一 LLM 路由与编排平台\n\nAetherWeaver 是一个功能强大、可扩展的平台，用于构建先进的 LLM 应用。它为多个模型服务商提供了统一的接口、智能路由、RAG 功能以及 OpenAI 兼容的 API 端点。\n\n## ✨ 主要特性\n\n- **多模型支持**: 集成 OpenAI、Google Gemini、Deepseek、Claude 等多种大语言模型。\n- **智能路由**: 根据任务的复杂度和类型（如代码、视觉、推理），将请求动态路由到最合适的模型。\n- **检索增强生成 (RAG)**: 支持多种 Embedding 模型（OpenAI、Cloudflare）和向量数据库（Qdrant、Upstash、Pinecone）。\n- **OpenAI 兼容 API**: 可作为 OpenAI API 的直接替代品，无缝集成现有工具生态。\n- **可观测性**: 内置 Langfuse 集成，提供详细的请求追踪和监控。\n- **可扩展的 Agent**: 支持构建带有自定义工具（如网络搜索）的强大 Agent。\n\n## 🚀 快速开始\n\n1.  **克隆代码仓库**:\n    ```bash\n    git clone https://github.com/inoribea/AetherWeaver.git\n    cd AetherWeaver\n    ```\n\n2.  **安装依赖**:\n    ```bash\n    yarn install\n    ```\n\n3.  **配置环境变量**:\n    ```bash\n    cp .env.example .env.local\n    ```\n    在 `.env.local` 文件中填入你的 API 密钥。至少需要一个模型服务商的 API 密钥（例如 `OPENAI_API_KEY`）。\n\n4.  **启动开发服务器**:\n    ```bash\n    yarn dev\n    ```\n\n5.  **打开浏览器** 并访问 `http://localhost:3000`。\n\n## 🛠️ 配置\n\n应用程序通过环境变量进行配置。关键选项包括：\n\n- `ANALYSIS_MODE`: 设置为 `rule_based` (默认) 以进行快速路由，或 `llm_enhanced` 以实现更精准的、由 AI 驱动的路由。\n- `EMBEDDING_PROVIDER`: 为文档嵌入选择 `OpenAI` 或 `Cloudflare`。\n- `QDRANT_URL` / `UPSTASH_VECTOR_REST_URL`: 配置你的向量数据库连接。\n- `LANGFUSE_SECRET_KEY`: 提供你的 Langfuse 密钥以启用监控。\n\n完整的变量列表，请参阅 [docs/vercel-guide.md](docs/vercel-guide.md)。\n\n## 📚 文档\n\n- **[项目总览](docs/SUMMARY.md)**: 功能和配置的高级摘要。\n- **[API 用法](docs/chat_api_usage.md)**: 如何使用不同的聊天 API。\n- **[RAG 与 Embedding](docs/retrieval_interface.md)**: 关于配置 RAG 的详细信息。\n- **[智能路由](docs/v1_decision_logic.md)**: 对路由逻辑的深入解释。\n- **[部署指南](docs/vercel-guide.md)**: 在 Vercel 上部署的指南。\n\n## 🤝 贡献\n\n欢迎参与贡献！请创建 Issue 或提交 Pull Request。\n\n## 📄 许可证\n\n本项目采用 MIT 许可证。详情请见 [LICENSE](LICENSE) 文件。","funding_links":[],"categories":[],"sub_categories":[],"project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Finoribea%2Faetherweaver","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Finoribea%2Faetherweaver","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Finoribea%2Faetherweaver/lists"}