Skip to content
Back to search

nextchat

✨ Zero-config AI chat assistant. No API key needed — sign up and instantly chat with GPT-5, Claude 4, Gemini 2.5, DeepSeek & 100+ top models. Pay-as-you-go saves you more. Available on Web, iOS, macOS, Android, Linux, Windows.

Safety scan

A static text scan, not a guarantee. Select the badge to see what was scanned and every finding.

Checked today
Badge for your README
findsafeskills safety rating

Markdown

[![findsafeskills safety rating](/api/listings/chatgptnextweb--nextchat/badge.svg)](/listings/chatgptnextweb--nextchat)

HTML

<a href="/listings/chatgptnextweb--nextchat"><img src="/api/listings/chatgptnextweb--nextchat/badge.svg" alt="findsafeskills safety rating" /></a>

Install

i

What was scanned

The files the safety scan read, as written by the repository's author and shown as plain text. Lines with a finding are marked.

README.md · README · 483 lines

View this file on GitHub (read at the repository's current version: the scan did not record which commit it read)

This file has changed since it was scanned, so this is not exactly the text that was scanned, and no line is marked. The findings are listed with the safety scan above.

  1. <div align="center">
  2. <a href='https://nextchat.club'>
  3. <img src="https://github.com/user-attachments/assets/83bdcc07-ae5e-4954-a53a-ac151ba6ccf3" width="1000" alt="icon"/>
  4. </a>
  5. <h1 align="center">NextChat</h1>
  6. English / [简体中文](./README_CN.md)
  7. <a href="https://trendshift.io/repositories/5973" target="_blank"><img src="https://trendshift.io/api/badge/repositories/5973" alt="ChatGPTNextWeb%2FChatGPT-Next-Web | Trendshift" style="width: 250px; height: 55px;" width="250" height="55"/></a>
  8. ✨ Light and Fast AI Assistant,with Claude, DeepSeek, GPT4 & Gemini Pro support.
  9. [![Saas][Saas-image]][saas-url]
  10. [![Web][Web-image]][web-url]
  11. [![Windows][Windows-image]][download-url]
  12. [![MacOS][MacOS-image]][download-url]
  13. [![Linux][Linux-image]][download-url]
  14. [NextChatAI](https://nextchat.club?utm_source=readme) / [iOS APP](https://apps.apple.com/us/app/nextchat-ai/id6743085599) / [Web App Demo](https://app.nextchat.club) / [Desktop App](https://github.com/Yidadaa/ChatGPT-Next-Web/releases) / [Enterprise Edition](#enterprise-edition)
  15. [saas-url]: https://nextchat.club?utm_source=readme
  16. [saas-image]: https://img.shields.io/badge/NextChat-Saas-green?logo=microsoftedge
  17. [web-url]: https://app.nextchat.club/
  18. [download-url]: https://github.com/Yidadaa/ChatGPT-Next-Web/releases
  19. [Web-image]: https://img.shields.io/badge/Web-PWA-orange?logo=microsoftedge
  20. [Windows-image]: https://img.shields.io/badge/-Windows-blue?logo=windows
  21. [MacOS-image]: https://img.shields.io/badge/-MacOS-black?logo=apple
  22. [Linux-image]: https://img.shields.io/badge/-Linux-333?logo=ubuntu
  23. [<img src="https://zeabur.com/button.svg" alt="Deploy on Zeabur" height="30">](https://zeabur.com/templates/ZBUEFA) [<img src="https://vercel.com/button" alt="Deploy on Vercel" height="30">](https://vercel.com/new/clone?repository-url=https%3A%2F%2Fgithub.com%2FChatGPTNextWeb%2FChatGPT-Next-Web&env=OPENAI_API_KEY&env=CODE&project-name=nextchat&repository-name=NextChat) [<img src="https://gitpod.io/button/open-in-gitpod.svg" alt="Open in Gitpod" height="30">](https://gitpod.io/#https://github.com/ChatGPTNextWeb/NextChat) [<img src="https://oss.opendeploy.dev/static/deploy-with-your-agent.svg" alt="Deploy with your agent" height="30">](https://opendeploy.dev/github/ChatGPTNextWeb/NextChat)
  24. [<img src="https://github.com/user-attachments/assets/903482d4-3e87-4134-9af1-f2588fa90659" height="50" width="" >](https://monica.im/?utm=nxcrp)
  25. </div>
  26. ## ❤️ Sponsor AI API
  27. <a href='https://302.ai/'>
  28. <img src="https://github.com/user-attachments/assets/a03edf82-2031-4f23-bdb8-bfc0bfd168a4" width="100%" alt="icon"/>
  29. </a>
  30. [302.AI](https://302.ai/) is a pay-as-you-go AI application platform that offers the most comprehensive AI APIs and online applications available.
  31. ## 🥳 Cheer for NextChat iOS Version Online!
  32. > [👉 Click Here to Install Now](https://apps.apple.com/us/app/nextchat-ai/id6743085599)
  33. > [❤️ Source Code Coming Soon](https://github.com/ChatGPTNextWeb/NextChat-iOS)
  34. ![Github iOS Image](https://github.com/user-attachments/assets/e0aa334f-4c13-4dc9-8310-e3b09fa4b9f3)
  35. ## 🫣 NextChat Support MCP !
  36. > Before build, please set env ENABLE_MCP=true
  37. <img src="./docs/images/mcp-market.png" alt="NextChat MCP Market" />
  38. ## Enterprise Edition
  39. Meeting Your Company's Privatization and Customization Deployment Requirements:
  40. - **Brand Customization**: Tailored VI/UI to seamlessly align with your corporate brand image.
  41. - **Resource Integration**: Unified configuration and management of dozens of AI resources by company administrators, ready for use by team members.
  42. - **Permission Control**: Clearly defined member permissions, resource permissions, and knowledge base permissions, all controlled via a corporate-grade Admin Panel.
  43. - **Knowledge Integration**: Combining your internal knowledge base with AI capabilities, making it more relevant to your company's specific business needs compared to general AI.
  44. - **Security Auditing**: Automatically intercept sensitive inquiries and trace all historical conversation records, ensuring AI adherence to corporate information security standards.
  45. - **Private Deployment**: Enterprise-level private deployment supporting various mainstream private cloud solutions, ensuring data security and privacy protection.
  46. - **Continuous Updates**: Ongoing updates and upgrades in cutting-edge capabilities like multimodal AI, ensuring consistent innovation and advancement.
  47. For enterprise inquiries, please contact: **business@nextchat.club**
  48. ## Screenshots
  49. ![Settings](./docs/images/settings.png)
  50. ![More](./docs/images/more.png)
  51. ## Features
  52. - **Deploy for free with one-click** on Vercel in under 1 minute
  53. - Compact client (~5MB) on Linux/Windows/MacOS, [download it now](https://github.com/Yidadaa/ChatGPT-Next-Web/releases)
  54. - Fully compatible with self-deployed LLMs, recommended for use with [RWKV-Runner](https://github.com/josStorer/RWKV-Runner) or [LocalAI](https://github.com/go-skynet/LocalAI)
  55. - Privacy first, all data is stored locally in the browser
  56. - Markdown support: LaTex, mermaid, code highlight, etc.
  57. - Responsive design, dark mode and PWA
  58. - Fast first screen loading speed (~100kb), support streaming response
  59. - New in v2: create, share and debug your chat tools with prompt templates (mask)
  60. - Awesome prompts powered by [awesome-chatgpt-prompts-zh](https://github.com/PlexPt/awesome-chatgpt-prompts-zh) and [awesome-chatgpt-prompts](https://github.com/f/awesome-chatgpt-prompts)
  61. - Automatically compresses chat history to support long conversations while also saving your tokens
  62. - I18n: English, 简体中文, 繁体中文, 日本語, Français, Español, Italiano, Türkçe, Deutsch, Tiếng Việt, Русский, Čeština, 한국어, Indonesia
  63. <div align="center">
  64. ![主界面](./docs/images/cover.png)
  65. </div>
  66. ## Roadmap
  67. - [x] System Prompt: pin a user defined prompt as system prompt [#138](https://github.com/Yidadaa/ChatGPT-Next-Web/issues/138)
  68. - [x] User Prompt: user can edit and save custom prompts to prompt list
  69. - [x] Prompt Template: create a new chat with pre-defined in-context prompts [#993](https://github.com/Yidadaa/ChatGPT-Next-Web/issues/993)
  70. - [x] Share as image, share to ShareGPT [#1741](https://github.com/Yidadaa/ChatGPT-Next-Web/pull/1741)
  71. - [x] Desktop App with tauri
  72. - [x] Self-host Model: Fully compatible with [RWKV-Runner](https://github.com/josStorer/RWKV-Runner), as well as server deployment of [LocalAI](https://github.com/go-skynet/LocalAI): llama/gpt4all/rwkv/vicuna/koala/gpt4all-j/cerebras/falcon/dolly etc.
  73. - [x] Artifacts: Easily preview, copy and share generated content/webpages through a separate window [#5092](https://github.com/ChatGPTNextWeb/ChatGPT-Next-Web/pull/5092)
  74. - [x] Plugins: support network search, calculator, any other apis etc. [#165](https://github.com/Yidadaa/ChatGPT-Next-Web/issues/165) [#5353](https://github.com/ChatGPTNextWeb/ChatGPT-Next-Web/issues/5353)
  75. - [x] network search, calculator, any other apis etc. [#165](https://github.com/Yidadaa/ChatGPT-Next-Web/issues/165) [#5353](https://github.com/ChatGPTNextWeb/ChatGPT-Next-Web/issues/5353)
  76. - [x] Supports Realtime Chat [#5672](https://github.com/ChatGPTNextWeb/ChatGPT-Next-Web/issues/5672)
  77. - [ ] local knowledge base
  78. ## What's New
  79. - 🚀 v2.15.8 Now supports Realtime Chat [#5672](https://github.com/ChatGPTNextWeb/ChatGPT-Next-Web/issues/5672)
  80. - 🚀 v2.15.4 The Application supports using Tauri fetch LLM API, MORE SECURITY! [#5379](https://github.com/ChatGPTNextWeb/ChatGPT-Next-Web/issues/5379)
  81. - 🚀 v2.15.0 Now supports Plugins! Read this: [NextChat-Awesome-Plugins](https://github.com/ChatGPTNextWeb/NextChat-Awesome-Plugins)
  82. - 🚀 v2.14.0 Now supports Artifacts & SD
  83. - 🚀 v2.10.1 support Google Gemini Pro model.
  84. - 🚀 v2.9.11 you can use azure endpoint now.
  85. - 🚀 v2.8 now we have a client that runs across all platforms!
  86. - 🚀 v2.7 let's share conversations as image, or share to ShareGPT!
  87. - 🚀 v2.0 is released, now you can create prompt templates, turn your ideas into reality! Read this: [ChatGPT Prompt Engineering Tips: Zero, One and Few Shot Prompting](https://www.allabtai.com/prompt-engineering-tips-zero-one-and-few-shot-prompting/).
  88. ## Get Started
  89. 1. Get [OpenAI API Key](https://platform.openai.com/account/api-keys);
  90. 2. Click
  91. [![Deploy with Vercel](https://vercel.com/button)](https://vercel.com/new/clone?repository-url=https%3A%2F%2Fgithub.com%2FYidadaa%2FChatGPT-Next-Web&env=OPENAI_API_KEY&env=CODE&project-name=chatgpt-next-web&repository-name=ChatGPT-Next-Web), remember that `CODE` is your page password;
  92. 3. Enjoy :)
  93. ## FAQ
  94. [English > FAQ](./docs/faq-en.md)
  95. ## Keep Updated
  96. If you have deployed your own project with just one click following the steps above, you may encounter the issue of "Updates Available" constantly showing up. This is because Vercel will create a new project for you by default instead of forking this project, resulting in the inability to detect updates correctly.
  97. We recommend that you follow the steps below to re-deploy:
  98. - Delete the original repository;
  99. - Use the fork button in the upper right corner of the page to fork this project;
  100. - Choose and deploy in Vercel again, [please see the detailed tutorial](./docs/vercel-cn.md).
  101. ### Enable Automatic Updates
  102. > If you encounter a failure of Upstream Sync execution, please [manually update code](./README.md#manually-updating-code).
  103. After forking the project, due to the limitations imposed by GitHub, you need to manually enable Workflows and Upstream Sync Action on the Actions page of the forked project. Once enabled, automatic updates will be scheduled every hour:
  104. ![Automatic Updates](./docs/images/enable-actions.jpg)
  105. ![Enable Automatic Updates](./docs/images/enable-actions-sync.jpg)
  106. ### Manually Updating Code
  107. If you want to update instantly, you can check out the [GitHub documentation](https://docs.github.com/en/pull-requests/collaborating-with-pull-requests/working-with-forks/syncing-a-fork) to learn how to synchronize a forked project with upstream code.
  108. You can star or watch this project or follow author to get release notifications in time.
  109. ## Access Password
  110. This project provides limited access control. Please add an environment variable named `CODE` on the vercel environment variables page. The value should be passwords separated by comma like this:
  111. ```
  112. code1,code2,code3
  113. ```
  114. After adding or modifying this environment variable, please redeploy the project for the changes to take effect.
  115. ## Environment Variables
  116. ### `CODE` (optional)
  117. Access password, separated by comma.
  118. ### `OPENAI_API_KEY` (required)
  119. Your openai api key, join multiple api keys with comma.
  120. ### `BASE_URL` (optional)
  121. > Default: `https://api.openai.com`
  122. > Examples: `http://your-openai-proxy.com`
  123. Override openai api request base url.
  124. ### `OPENAI_ORG_ID` (optional)
  125. Specify OpenAI organization ID.
  126. ### `AZURE_URL` (optional)
  127. > Example: https://{azure-resource-url}/openai
  128. Azure deploy url.
  129. ### `AZURE_API_KEY` (optional)
  130. Azure Api Key.
  131. ### `AZURE_API_VERSION` (optional)
  132. Azure Api Version, find it at [Azure Documentation](https://learn.microsoft.com/en-us/azure/ai-services/openai/reference#chat-completions).
  133. ### `GOOGLE_API_KEY` (optional)
  134. Google Gemini Pro Api Key.
  135. ### `GOOGLE_URL` (optional)
  136. Google Gemini Pro Api Url.
  137. ### `ANTHROPIC_API_KEY` (optional)
  138. anthropic claude Api Key.
  139. ### `ANTHROPIC_API_VERSION` (optional)
  140. anthropic claude Api version.
  141. ### `ANTHROPIC_URL` (optional)
  142. anthropic claude Api Url.
  143. ### `BAIDU_API_KEY` (optional)
  144. Baidu Api Key.
  145. ### `BAIDU_SECRET_KEY` (optional)
  146. Baidu Secret Key.
  147. ### `BAIDU_URL` (optional)
  148. Baidu Api Url.
  149. ### `BYTEDANCE_API_KEY` (optional)
  150. ByteDance Api Key.
  151. ### `BYTEDANCE_URL` (optional)
  152. ByteDance Api Url.
  153. ### `ALIBABA_API_KEY` (optional)
  154. Alibaba Cloud Api Key.
  155. ### `ALIBABA_URL` (optional)
  156. Alibaba Cloud Api Url.
  157. ### `IFLYTEK_URL` (Optional)
  158. iflytek Api Url.
  159. ### `IFLYTEK_API_KEY` (Optional)
  160. iflytek Api Key.
  161. ### `IFLYTEK_API_SECRET` (Optional)
  162. iflytek Api Secret.
  163. ### `CHATGLM_API_KEY` (optional)
  164. ChatGLM Api Key.
  165. ### `CHATGLM_URL` (optional)
  166. ChatGLM Api Url.
  167. ### `DEEPSEEK_API_KEY` (optional)
  168. DeepSeek Api Key.
  169. ### `DEEPSEEK_URL` (optional)
  170. DeepSeek Api Url.
  171. ### `HIDE_USER_API_KEY` (optional)
  172. > Default: Empty
  173. If you do not want users to input their own API key, set this value to 1.
  174. ### `DISABLE_GPT4` (optional)
  175. > Default: Empty
  176. If you do not want users to use GPT-4, set this value to 1.
  177. ### `ENABLE_BALANCE_QUERY` (optional)
  178. > Default: Empty
  179. If you do want users to query balance, set this value to 1.
  180. ### `DISABLE_FAST_LINK` (optional)
  181. > Default: Empty
  182. If you want to disable parse settings from url, set this to 1.
  183. ### `CUSTOM_MODELS` (optional)
  184. > Default: Empty
  185. > Example: `+llama,+claude-2,-gpt-3.5-turbo,gpt-4-1106-preview=gpt-4-turbo` means add `llama, claude-2` to model list, and remove `gpt-3.5-turbo` from list, and display `gpt-4-1106-preview` as `gpt-4-turbo`.
  186. To control custom models, use `+` to add a custom model, use `-` to hide a model, use `name=displayName` to customize model name, separated by comma.
  187. User `-all` to disable all default models, `+all` to enable all default models.
  188. For Azure: use `modelName@Azure=deploymentName` to customize model name and deployment name.
  189. > Example: `+gpt-3.5-turbo@Azure=gpt35` will show option `gpt35(Azure)` in model list.
  190. > If you only can use Azure model, `-all,+gpt-3.5-turbo@Azure=gpt35` will `gpt35(Azure)` the only option in model list.
  191. For ByteDance: use `modelName@bytedance=deploymentName` to customize model name and deployment name.
  192. > Example: `+Doubao-lite-4k@bytedance=ep-xxxxx-xxx` will show option `Doubao-lite-4k(ByteDance)` in model list.
  193. ### `DEFAULT_MODEL` (optional)
  194. Change default model
  195. ### `VISION_MODELS` (optional)
  196. > Default: Empty
  197. > Example: `gpt-4-vision,claude-3-opus,my-custom-model` means add vision capabilities to these models in addition to the default pattern matches (which detect models containing keywords like "vision", "claude-3", "gemini-1.5", etc).
  198. Add additional models to have vision capabilities, beyond the default pattern matching. Multiple models should be separated by commas.
  199. ### `WHITE_WEBDAV_ENDPOINTS` (optional)
  200. You can use this option if you want to increase the number of webdav service addresses you are allowed to access, as required by the format:
  201. - Each address must be a complete endpoint
  202. > `https://xxxx/yyy`
  203. - Multiple addresses are connected by ', '
  204. ### `DEFAULT_INPUT_TEMPLATE` (optional)
  205. Customize the default template used to initialize the User Input Preprocessing configuration item in Settings.
  206. ### `STABILITY_API_KEY` (optional)
  207. Stability API key.
  208. ### `STABILITY_URL` (optional)
  209. Customize Stability API url.
  210. ### `ENABLE_MCP` (optional)
  211. Enable MCP(Model Context Protocol)Feature. For security, MCP also requires
  212. `CODE` to be configured; all MCP server actions verify that access code.
  213. ### `SILICONFLOW_API_KEY` (optional)
  214. SiliconFlow API Key.
  215. ### `SILICONFLOW_URL` (optional)
  216. SiliconFlow API URL.
  217. ### `AI302_API_KEY` (optional)
  218. 302.AI API Key.
  219. ### `AI302_URL` (optional)
  220. 302.AI API URL.
  221. ## Requirements
  222. NodeJS >= 18, Docker >= 20
  223. ## Development
  224. [![Open in Gitpod](https://gitpod.io/button/open-in-gitpod.svg)](https://gitpod.io/#https://github.com/Yidadaa/ChatGPT-Next-Web)
  225. Before starting development, you must create a new `.env.local` file at project root, and place your api key into it:
  226. ```
  227. OPENAI_API_KEY=<your api key here>
  228. # if you are not able to access openai service, use this BASE_URL
  229. BASE_URL=https://chatgpt1.nextweb.fun/api/proxy
  230. ```
  231. ### Local Development
  232. ```shell
  233. # 1. install nodejs and yarn first
  234. # 2. config local env vars in `.env.local`
  235. # 3. run
  236. yarn install
  237. yarn dev
  238. ```
  239. ## Deployment
  240. ### Docker (Recommended)
  241. ```shell
  242. docker pull yidadaa/chatgpt-next-web
  243. docker run -d -p 3000:3000 \
  244. -e OPENAI_API_KEY=sk-xxxx \
  245. -e CODE=your-password \
  246. yidadaa/chatgpt-next-web
  247. ```
  248. You can start service behind a proxy:
  249. ```shell
  250. docker run -d -p 3000:3000 \
  251. -e OPENAI_API_KEY=sk-xxxx \
  252. -e CODE=your-password \
  253. -e PROXY_URL=http://localhost:7890 \
  254. yidadaa/chatgpt-next-web
  255. ```
  256. If your proxy needs password, use:
  257. ```shell
  258. -e PROXY_URL="http://127.0.0.1:7890 user pass"
  259. ```
  260. If enable MCP, use:
  261. ```
  262. docker run -d -p 3000:3000 \
  263. -e OPENAI_API_KEY=sk-xxxx \
  264. -e CODE=your-password \
  265. -e ENABLE_MCP=true \
  266. yidadaa/chatgpt-next-web
  267. ```
  268. ### Shell
  269. ```shell
  270. bash <(curl -s https://raw.githubusercontent.com/Yidadaa/ChatGPT-Next-Web/main/scripts/setup.sh)
  271. ```
  272. ## Synchronizing Chat Records (UpStash)
  273. | [简体中文](./docs/synchronise-chat-logs-cn.md) | [English](./docs/synchronise-chat-logs-en.md) | [Italiano](./docs/synchronise-chat-logs-es.md) | [日本語](./docs/synchronise-chat-logs-ja.md) | [한국어](./docs/synchronise-chat-logs-ko.md)
  274. ## Documentation
  275. > Please go to the [docs][./docs] directory for more documentation instructions.
  276. - [Deploy with cloudflare (Deprecated)](./docs/cloudflare-pages-en.md)
  277. - [Frequent Ask Questions](./docs/faq-en.md)
  278. - [How to add a new translation](./docs/translation.md)
  279. - [How to use Vercel (No English)](./docs/vercel-cn.md)
  280. - [User Manual (Only Chinese, WIP)](./docs/user-manual-cn.md)
  281. ## Translation
  282. If you want to add a new translation, read this [document](./docs/translation.md).
  283. ## Donation
  284. [Buy Me a Coffee](https://www.buymeacoffee.com/yidadaa)
  285. ## Special Thanks
  286. ### Contributors
  287. <a href="https://github.com/ChatGPTNextWeb/ChatGPT-Next-Web/graphs/contributors">
  288. <img src="https://contrib.rocks/image?repo=ChatGPTNextWeb/ChatGPT-Next-Web" />
  289. </a>
  290. ## LICENSE
  291. [MIT](https://opensource.org/license/mit/)

Ratings and comments

Sign in to rate this skill.

Sign in

Free to use. If it’s helped, pass it on.