{"id":13916863,"url":"https://github.com/ryan-yang125/chatllm-web","last_synced_at":"2025-07-18T17:31:05.542Z","repository":{"id":162975656,"uuid":"631462515","full_name":"Ryan-yang125/ChatLLM-Web","owner":"Ryan-yang125","description":"🗣️ Chat with LLM like Vicuna totally in your browser with WebGPU, safely, privately, and with no server. Powered by web llm.","archived":false,"fork":false,"pushed_at":"2024-08-08T03:56:09.000Z","size":5272,"stargazers_count":633,"open_issues_count":4,"forks_count":48,"subscribers_count":12,"default_branch":"main","last_synced_at":"2025-04-04T07:36:50.077Z","etag":null,"topics":["chatgpt","deep-learning","llm","nextjs","pwa","react","tvm","vicuna","webgpu","webml"],"latest_commit_sha":null,"homepage":"https://chat-llm-web.vercel.app","language":"JavaScript","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/Ryan-yang125.png","metadata":{"files":{"readme":"README.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}},"created_at":"2023-04-23T05:07:57.000Z","updated_at":"2025-03-30T17:39:04.000Z","dependencies_parsed_at":"2024-01-14T03:51:02.192Z","dependency_job_id":"b7b10183-ef16-49cd-826d-f71e0bf6295a","html_url":"https://github.com/Ryan-yang125/ChatLLM-Web","commit_stats":null,"previous_names":[],"tags_count":1,"template":false,"template_full_name":null,"purl":"pkg:github/Ryan-yang125/ChatLLM-Web","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/Ryan-yang125%2FChatLLM-Web","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/Ryan-yang125%2FChatLLM-Web/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/Ryan-yang125%2FChatLLM-Web/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/Ryan-yang125%2FChatLLM-Web/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/Ryan-yang125","download_url":"https://codeload.github.com/Ryan-yang125/ChatLLM-Web/tar.gz/refs/heads/main","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/Ryan-yang125%2FChatLLM-Web/sbom","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":265801645,"owners_count":23830451,"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","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":["chatgpt","deep-learning","llm","nextjs","pwa","react","tvm","vicuna","webgpu","webml"],"created_at":"2024-08-07T05:00:44.623Z","updated_at":"2025-07-18T17:31:04.255Z","avatar_url":"https://github.com/Ryan-yang125.png","language":"JavaScript","funding_links":[],"categories":["Browser-extensions"],"sub_categories":[],"readme":"\u003cdiv align=\"center\"\u003e\n\u003cimg src=\"./docs/images/icon.jpg\" alt=\"icon\" height=\"160\"/\u003e\n\n\u003ch1 align=\"center\"\u003eChatLLM Web\u003c/h1\u003e\n\u003ch2 align=\"center\"\u003e🚀 Check the AI search engine https://discovai.io, discover top ai tools that best match your need\u003c/h2\u003e\n\nEnglish / [简体中文](./docs/README_CN.md) / [日本語](./docs/README_JA.md)\n\n🗣️ Chat with LLM like Vicuna totally in your browser with WebGPU, safely, privately, and with no server. Powered By [web-llm](https://github.com/mlc-ai/web-llm).\n\n[Try it now](https://chat-llm-web.vercel.app)\n\n![cover](./docs/images/cover.png)\n\n\u003c/div\u003e\n\n## Features\n\n- 🤖 Everything runs inside the browser with **no server support** and is **accelerated with WebGPU**.\n\n- ⚙️ Model runs in a web worker, ensuring that it doesn't block the user interface and providing a seamless experience.\n\n- 🚀 Easy to deploy for free with one-click on Vercel in under 1 minute, then you get your own ChatLLM Web.\n\n- 💾 Model caching is supported, so you only need to download the model once.\n\n- 💬 Multi-conversation chat, with all data stored locally in the browser for privacy.\n\n- 📝 Markdown and streaming response support: math, code highlighting, etc.\n\n- 🎨 responsive and well-designed UI, including dark mode.\n\n- 💻 PWA supported, download it and run totally offline.\n\n## Instructions\n\n- 🌐 To use this app, you need a browser that supports WebGPU, such as Chrome 113 or Chrome Canary. Chrome versions ≤ 112 are not supported.\n\n- 💻 You will need a GPU with about 6.4GB of memory. If your GPU has less memory, the app will still run, but the response time will be slower.\n\n- 📥 The first time you use the app, you will need to download the model. For the Vicuna-7b model that we are currently using, the download size is about 4GB. After the initial download, the model will be loaded from the browser cache for faster usage.\n\n- ℹ️ For more details, please visit [mlc.ai/web-llm](https://mlc.ai/web-llm/)\n\n## Roadmap\n\n- [✅] LLM: using web worker to create an LLM instance and generate answers.\n\n- [✅] Conversations: Multi-conversation support is available.\n\n- [✅] PWA\n\n- [] Settings:\n  - ui: dark/light theme\n  - device:\n    - gpu device choose\n    - cache usage and manage\n  - model:\n    - support multi models: vicuna-7b✅ RedPajama-INCITE-Chat-3B []\n    - params config: temperature, max-length, etc.\n    - export \u0026 import model\n\n## Deploy to Vercel\n\n1. Click\n   [![Deploy with Vercel](https://vercel.com/button)](https://vercel.com/new/clone?repository-url=https%3A%2F%2Fgithub.com%2FRyan-yang125%2FChatLLM-Web\u0026project-name=chat-llm-web\u0026repository-name=ChatLLM-Web), follow the instructions, and finish in just 1 minute.\n2. Enjoy it 😊\n\n## Development\n\n```shell\ngit clone https://github.com/Ryan-yang125/ChatLLM-Web.git\ncd ChatLLM-Web\nnpm i\nnpm run dev\n```\n\n## Screenshots\n\n![Home](./docs/images/home.png)\n\n![More](./docs/images/mobile.png)\n\n## 🌟 History\n[![Star History Chart](https://api.star-history.com/svg?repos=Ryan-yang125/ChatLLM-Web\u0026type=Date)](https://star-history.com/#Ryan-yang125/ChatLLM-Web\u0026Date)\n\n## LICENSE\n\n[MIT](./LICENSE)\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fryan-yang125%2Fchatllm-web","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fryan-yang125%2Fchatllm-web","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fryan-yang125%2Fchatllm-web/lists"}