{"id":13554744,"url":"https://github.com/addyosmani/chatty","last_synced_at":"2025-05-15T07:04:46.029Z","repository":{"id":243011439,"uuid":"798163156","full_name":"addyosmani/chatty","owner":"addyosmani","description":"ChattyUI - your private AI chat for running LLMs in the browser","archived":false,"fork":false,"pushed_at":"2025-04-05T07:40:38.000Z","size":33775,"stargazers_count":712,"open_issues_count":8,"forks_count":83,"subscribers_count":6,"default_branch":"main","last_synced_at":"2025-05-10T20:01:49.639Z","etag":null,"topics":["ai","chatbot","huggingface","local"],"latest_commit_sha":null,"homepage":"https://chattyui.com","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/addyosmani.png","metadata":{"files":{"readme":"README.md","changelog":null,"contributing":"CONTRIBUTING.md","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":"2024-05-09T08:09:41.000Z","updated_at":"2025-05-06T22:42:16.000Z","dependencies_parsed_at":"2024-06-06T08:10:01.778Z","dependency_job_id":"db34118b-06a0-4bd7-bf19-194b4de4bada","html_url":"https://github.com/addyosmani/chatty","commit_stats":{"total_commits":125,"total_committers":8,"mean_commits":15.625,"dds":"0.15200000000000002","last_synced_commit":"ecdc31c72f84b8ea78bb85b1021bd63cbc3b3051"},"previous_names":["addyosmani/chatty"],"tags_count":3,"template":false,"template_full_name":null,"repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/addyosmani%2Fchatty","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/addyosmani%2Fchatty/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/addyosmani%2Fchatty/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/addyosmani%2Fchatty/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/addyosmani","download_url":"https://codeload.github.com/addyosmani/chatty/tar.gz/refs/heads/main","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":254292039,"owners_count":22046426,"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":["ai","chatbot","huggingface","local"],"created_at":"2024-08-01T12:02:54.036Z","updated_at":"2025-05-15T07:04:41.014Z","avatar_url":"https://github.com/addyosmani.png","language":"TypeScript","funding_links":[],"categories":["TypeScript"],"sub_categories":[],"readme":"\u003cdiv align=\"center\"\u003e\n  \n  [\u003cimg src=\"demo-img.jpg\"\u003e](https://chattyui.com/)\n  \n\u003c/div\u003e\n\n\u003ch1 align=\"center\"\u003e\n  Chatty\n\u003c/h1\u003e\n\n\u003cdiv align=\"center\"\u003e\n  \n![Website](https://img.shields.io/website?url=https%3A%2F%2Fchattyui.com%2F) ![GitHub Repo stars](https://img.shields.io/github/stars/addyosmani/chatty) ![GitHub forks](https://img.shields.io/github/forks/addyosmani/chatty) ![GitHub watchers](https://img.shields.io/github/watchers/addyosmani/chatty)\n\n\u003c/div\u003e\n\n**Chatty** is your private AI that leverages WebGPU to run large language models (LLMs) natively \u0026 privately in your browser, bringing you the most feature rich in-browser AI experience.\n\n# Features ✨\n\n- **In-browser privacy:** All AI models run locally (client side) on your hardware, ensuring that your data is processed only on your pc. No server-side processing!\n- **Offline:** Once the initial download of a model is processed, you'll be able to use it without an active internet connection.\n- **Chat history:** Access and manage your conversation history.\n- **Supports new open-source models:** Chat with popular open-source models such as Gemma, Llama2 \u0026 3 and Mistral!\n- **Responsive design:** If your phone supports WebGl, you'll be able to use Chatty just as you would on desktop.\n- **Intuitive UI:** Inspired by popular AI interfaces such as Gemini and ChatGPT to enhance similarity in the user experience.\n- **Markdown \u0026 code highlight:** Messages returned as markdown will be displayed as such \u0026 messages that include code, will be highlighted for easy access.\n- **Chat with files:** Load files (pdf \u0026 all non-binary files supported - even code files) and ask the models questions about them - fully local! Your documents never gets processed outside of your local environment, thanks to [XenovaTransformerEmbeddings](https://huggingface.co/Xenova/all-MiniLM-L6-v2) \u0026 [MemoryVectorStore](https://js.langchain.com/v0.1/docs/integrations/vectorstores/memory/)\n- **Custom memory support:** Add custom instructions/memory to allow the AI to provide better and more personalized responses.\n- **Export chat messages:** Seamlessly generate and save your chat messages in either json or markdown format.\n- **Voice input support:** Use voice interactions to interact with the models.\n- **Regenerate responses:** Not quite the response you were hoping for? Quickly regenerate it without having to write out your prompt again.\n- **Light \u0026 Dark mode:** Switch between light \u0026 dark mode.\n\n# Preview\n\nhttps://github.com/addyosmani/chatty/assets/114422072/a994cc5c-a99d-4fd2-9eab-c2d4267fcfd3\n\n# Why?\n\nThis project is meant to be the closest attempt at bringing the familarity \u0026 functionality from popular AI interfaces such as ChatGPT and Gemini into a in-browser experience.\n\n# Browser support\n\nBy default, WebGPU is enabled and supported in both Chrome and Edge. However, it is possible to enable it in Firefox and Firefox Nightly.\nCheck the [browser compatibility](https://developer.mozilla.org/en-US/docs/Web/API/WebGPU_API#browser_compatibility) for more information.\n\n# How to Install\n\n\u003e If you just want to try out the app, it's live on [this](https://chattyui.com) website.\n\u003e\n\u003e This is a Next.js application and requires Node.js (18+) and npm installed to run the project locally.\n\n## Install from source\n\nIf you want to setup and run the project locally, follow the steps below:\n\n**1. Clone the repository to a directory on your pc via command prompt:**\n\n```\ngit clone https://github.com/addyosmani/chatty\n```\n\n**2. Open the folder:**\n\n```\ncd chatty\n```\n\n**3. Install dependencies:**\n\n```\nnpm install\n```\n\n**4. Start the development server:**\n\n```\nnpm run dev\n```\n\n**5. Go to [localhost:3000](http://localhost:3000) and start chatting!**\n\n## Docker\n\n\u003e [!NOTE]  \n\u003e The Dockerfile has not yet been optimized for a production environment. If you wish to do so yourself, checkout the [Nextjs example](https://github.com/vercel/next.js/blob/canary/examples/with-docker/Dockerfile)\n\n```\ndocker build -t chattyui .\ndocker run -d -p 3000:3000 chattyui\n```\n\nOr use `docker-compose`:\n\n```\ndocker compose up\n```\n\n\u003e If you've made changes and want to rebuild, you can simply run `docker-compose up --build`\n\n# Roadmap\n\n- [ ] **Multiple file embeddings:** The ability to embed multiple files instead of one at a time for each session.\n- [ ] **Prompt management system:** Select from and add different system prompts to quickly use in a session.\n\n# Contributing\n\nContributions are more than welcome! However, please make sure to read the [contributing guidelines](https://github.com/addyosmani/chatty/blob/main/CONTRIBUTING.md) first :)\n\n# Hardware requirements\n\n\u003e [!NOTE]  \n\u003e To run the models efficiently, you'll need a GPU with enough memory. 7B models require a GPU with about 6GB memory whilst 3B models require around 3GB.\n\u003e\n\u003e Smaller models might not be able to process file embeddings as efficient as larger ones.\n\n# Acknowledgements \u0026 credits\n\nChatty is built using the [WebLLM](https://github.com/mlc-ai/web-llm) project, utilizing [HuggingFace](https://huggingface.co/), open source LLMs and [LangChain](https://www.langchain.com/). We want to acknowledge their great work and thank the open source community.\n\n# Authors\n\nChatty is created and maintained by [Addy Osmani](https://github.com/addyosmani/) \u0026 [Jakob Hoeg Mørk](https://github.com/jakobhoeg).\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Faddyosmani%2Fchatty","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Faddyosmani%2Fchatty","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Faddyosmani%2Fchatty/lists"}