[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"project-10825":3},{"id":4,"name":5,"fullName":6,"owner":7,"repo":5,"description":8,"homepage":9,"htmlUrl":10,"language":11,"languages":10,"totalLinesOfCode":10,"stars":12,"forks":13,"watchers":14,"openIssues":15,"contributorsCount":16,"subscribersCount":16,"size":16,"stars1d":17,"stars7d":18,"stars30d":19,"stars90d":16,"forks30d":16,"starsTrendScore":19,"compositeScore":20,"rankGlobal":10,"rankLanguage":10,"license":21,"archived":22,"fork":22,"defaultBranch":23,"hasWiki":24,"hasPages":22,"topics":25,"createdAt":10,"pushedAt":10,"updatedAt":37,"readmeContent":38,"aiSummary":39,"trendingCount":16,"starSnapshotCount":16,"syncStatus":18,"lastSyncTime":40,"discoverSource":41},10825,"serge","serge-chat\u002Fserge","serge-chat","A web interface for chatting with Alpaca through llama.cpp. Fully dockerized, with an easy to use API.","https:\u002F\u002Fserge.chat",null,"Svelte",5727,394,47,18,0,1,2,4,38.79,"Apache License 2.0",false,"main",true,[26,27,28,29,30,31,32,33,34,35,36],"alpaca","docker","fastapi","llama","llamacpp","nginx","python","svelte","sveltekit","tailwindcss","web","2026-06-12 02:02:27","# Serge - LLaMA made easy 🦙\n\n![License](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Flicense\u002Fserge-chat\u002Fserge)\n[![Discord](https:\u002F\u002Fimg.shields.io\u002Fdiscord\u002F1088427963801948201?label=Discord)](https:\u002F\u002Fdiscord.gg\u002F62Hc6FEYQH)\n\nSerge is a chat interface crafted with [llama.cpp](https:\u002F\u002Fgithub.com\u002Fggerganov\u002Fllama.cpp) for running LLM models. No API keys, entirely self-hosted!\n\n- 🌐 **SvelteKit** frontend\n- 💾 **[Redis](https:\u002F\u002Fgithub.com\u002Fredis\u002Fredis)** for storing chat history & parameters\n- ⚙️ **FastAPI + LangChain** for the API, wrapping calls to [llama.cpp](https:\u002F\u002Fgithub.com\u002Fggerganov\u002Fllama.cpp) using the [python bindings](https:\u002F\u002Fgithub.com\u002Fabetlen\u002Fllama-cpp-python)\n\n🎥 Demo:\n\n[demo.webm](https:\u002F\u002Fuser-images.githubusercontent.com\u002F25119303\u002F226897188-914a6662-8c26-472c-96bd-f51fc020abf6.webm)\n\n## ⚡️ Quick start\n\n🐳 Docker:\n\n```bash\ndocker run -d \\\n    --name serge \\\n    -v weights:\u002Fusr\u002Fsrc\u002Fapp\u002Fweights \\\n    -v datadb:\u002Fdata\u002Fdb\u002F \\\n    -p 8008:8008 \\\n    ghcr.io\u002Fserge-chat\u002Fserge:latest\n```\n\n🐙 Docker Compose:\n\n```yaml\nservices:\n  serge:\n    image: ghcr.io\u002Fserge-chat\u002Fserge:latest\n    container_name: serge\n    restart: unless-stopped\n    ports:\n      - 8008:8008\n    volumes:\n      - weights:\u002Fusr\u002Fsrc\u002Fapp\u002Fweights\n      - datadb:\u002Fdata\u002Fdb\u002F\n\nvolumes:\n  weights:\n  datadb:\n```\n\nThen, just visit http:\u002F\u002Flocalhost:8008, You can find the API documentation at http:\u002F\u002Flocalhost:8008\u002Fapi\u002Fdocs\n\n### 🌍 Environment Variables\n\nThe following Environment Variables are available:\n\n| Variable Name         | Description                                             | Default Value                        |\n|-----------------------|---------------------------------------------------------|--------------------------------------|\n| `SERGE_DATABASE_URL`  | Database connection string                              | `sqlite:\u002F\u002F\u002F\u002Fdata\u002Fdb\u002Fsql_app.db`      |\n| `SERGE_JWT_SECRET`    | Key for auth token encryption. Use a random string      | `uF7FGN5uzfGdFiPzR`                  |\n| `SERGE_SESSION_EXPIRY`| Duration in minutes before a user must reauthenticate   | `60`                                 |\n| `NODE_ENV`            | Node.js running environment                             | `production`                         |\n\n## 🖥️ Windows\n\nEnsure you have Docker Desktop installed, WSL2 configured, and enough free RAM to run models.\n\n## ⚠️ Memory Usage\n\nLLaMA will crash if you don't have enough available memory for the model\n\n## 💬 Support\n\nNeed help? Join our [Discord](https:\u002F\u002Fdiscord.gg\u002F62Hc6FEYQH)\n\n## 🧾 License\n\n[Nathan Sarrazin](https:\u002F\u002Fgithub.com\u002Fnsarrazin) and [Contributors](https:\u002F\u002Fgithub.com\u002Fserge-chat\u002Fserge\u002Fgraphs\u002Fcontributors). `Serge` is free and open-source software licensed under the [MIT License](https:\u002F\u002Fgithub.com\u002Fserge-chat\u002Fserge\u002Fblob\u002Fmain\u002FLICENSE-MIT) and [Apache-2.0](https:\u002F\u002Fgithub.com\u002Fserge-chat\u002Fserge\u002Fblob\u002Fmain\u002FLICENSE-APACHE).\n\n## 🤝 Contributing\n\nIf you discover a bug or have a feature idea, feel free to open an issue or PR.\n\nTo run Serge in development mode:\n\n```bash\ngit clone https:\u002F\u002Fgithub.com\u002Fserge-chat\u002Fserge.git\ncd serge\u002F\ndocker compose -f docker-compose.dev.yml up --build\n```\n\nThe solution will accept a python debugger session on port 5678. Example launch.json for VSCode:\n\n```json\n{\n    \"version\": \"0.2.0\",\n    \"configurations\": [\n        {\n            \"name\": \"Remote Debug\",\n            \"type\": \"python\",\n            \"request\": \"attach\",\n            \"connect\": {\n                \"host\": \"localhost\",\n                \"port\": 5678\n            },\n            \"pathMappings\": [\n                {\n                    \"localRoot\": \"${workspaceFolder}\u002Fapi\",\n                    \"remoteRoot\": \"\u002Fusr\u002Fsrc\u002Fapp\u002Fapi\u002F\"\n                }\n            ],\n            \"justMyCode\": false\n        }\n    ]\n}\n```\n","Serge 是一个基于 llama.cpp 的聊天界面，用于运行大型语言模型。它完全容器化，并提供了一个易于使用的 API。该项目使用 SvelteKit 构建前端界面，通过 FastAPI 和 LangChain 包装对 llama.cpp 的调用，同时利用 Redis 存储聊天记录和参数设置，确保了高效的数据管理和用户体验。Serge 适合需要在本地部署并运行 AI 联机聊天应用的场景，如个人开发者、小型团队或任何希望拥有自托管聊天解决方案的用户。其快速启动特性和详细的文档支持使得即便是技术背景较浅的用户也能轻松上手。","2026-06-11 03:30:21","top_topic"]