Skip to content
Back to search

deepchat

🐬DeepChat - A smart assistant that connects powerful AI to your personal world

Safety scan

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

Checked today

Check it deeper on your machine

It has changed since its scan on 11 Nov 2026.

As a Claude Code plugin, install it and then ask Claude Code:

/plugin marketplace add keithmackay/mackayi/plugin install scanskillsafety@mackayiDo a deep scan of https://github.com/ThinkInAIXYZ/deepchat with scanskillsafety

Or from a terminal, clone it and run it:

git clone https://github.com/keithmackay/scanskillsafety-skill ~/.claude/skills/scanskillsafetynode ~/.claude/skills/scanskillsafety/cli.cjs --deep 'https://github.com/ThinkInAIXYZ/deepchat'

It checks the exact commit: every file, its packages against OSV (api.osv.dev), how it compares with this page's scan (findsafeskills.com receives the repository's address), and, if you agree, Claude reading every file with your own Claude subscription. It never runs the code.

Badge for your README
findsafeskills safety rating

Markdown

[![findsafeskills safety rating](/api/listings/thinkinaixyz-deepchat/badge.svg)](/listings/thinkinaixyz-deepchat)

HTML

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

Install

i

Install instructions from the README

As written by the repo's author. findsafeskills has not verified these steps.

Download and Install

You can install DeepChat using one of the following methods:

**Option 1: GitHub Releases**

Download the latest version for your system from the [GitHub Releases](https://github.com/ThinkInAIXYZ/deepchat/releases) page:

- Windows: `.exe` installation file - macOS: `.dmg` installation file - Linux: `.AppImage` or `.deb` installation file

**Option 2: Official Website**

Download from the [official website](https://deepchatai.cn/#/download).

**Option 3: Homebrew (macOS only)**

For macOS users, you can install DeepChat using Homebrew:

brew install --cask deepchat

Configure Models

1. Launch the DeepChat application 2. Click the settings icon 3. Select the "Model Providers" tab 4. Add your API keys or configure local Ollama

Start Conversations

1. Click the "+" button to create a new conversation 2. Select the model you want to use 3. Start communicating with your AI assistant

For a comprehensive guide on getting started and using all features, please refer to the [documentation index](./docs/README.md).

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 Β· README Β· 576 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. <p align='center'>
  2. <img src='./build/icon.png' width="150" height="150" alt="DeepChat AI Assistant Icon" />
  3. </p>
  4. <h1 align="center">DeepChat - Open-Source Local-First AI Agent Desktop Client</h1>
  5. <p align="center">DeepChat is an open-source, local-first AI agent desktop client with rich agent capabilities, designed around the Tape.systems philosophy, with support for MCP, Skills, ACP, and remote control integrations for messaging apps.</p>
  6. <p align="center">
  7. <a href="https://github.com/ThinkInAIXYZ/deepchat/stargazers"><img src="https://img.shields.io/github/stars/ThinkInAIXYZ/deepchat" alt="Stars Badge"/></a>
  8. <a href="https://github.com/ThinkInAIXYZ/deepchat/network/members"><img src="https://img.shields.io/github/forks/ThinkInAIXYZ/deepchat" alt="Forks Badge"/></a>
  9. <a href="https://github.com/ThinkInAIXYZ/deepchat/pulls"><img src="https://img.shields.io/github/issues-pr/ThinkInAIXYZ/deepchat" alt="Pull Requests Badge"/></a>
  10. <a href="https://github.com/ThinkInAIXYZ/deepchat/issues"><img src="https://img.shields.io/github/issues/ThinkInAIXYZ/deepchat" alt="Issues Badge"/></a>
  11. <a href="https://github.com/ThinkInAIXYZ/deepchat/blob/main/LICENSE"><img src="https://img.shields.io/github/license/ThinkInAIXYZ/deepchat" alt="License Badge"/></a>
  12. <a href="https://github.com/ThinkInAIXYZ/deepchat/releases/latest"><img src="https://img.shields.io/endpoint?url=https://api.pinstudios.net/api/badges/downloads/ThinkInAIXYZ/deepchat/total" alt="Downloads"></a>
  13. </p>
  14. <div align="center">
  15. <a href="https://trendshift.io/repositories/15162" target="_blank"><img src="https://trendshift.io/api/badge/repositories/15162" alt="ThinkInAIXYZ%2Fdeepchat | Trendshift" style="width: 250px; height: 55px;" width="250" height="55"/></a>
  16. </div>
  17. <div align="center">
  18. <a href="./README.zh.md">δΈ­ζ–‡</a> / <a href="./README.md">English</a> / <a href="./README.jp.md">ζ—₯本θͺž</a>
  19. </div>
  20. ## πŸ“‘ Table of Contents
  21. - [πŸ“‘ Table of Contents](#-table-of-contents)
  22. - [πŸš€ Project Introduction](#-project-introduction)
  23. - [πŸ’‘ Why Choose DeepChat](#-why-choose-deepchat)
  24. - [πŸ“¦ Quick Start](#-quick-start)
  25. - [Download and Install](#download-and-install)
  26. - [Configure Models](#configure-models)
  27. - [Start Conversations](#start-conversations)
  28. - [πŸ”₯ Main Features](#-main-features)
  29. - [πŸ“Ό Tape & Trace](#-tape--trace)
  30. - [🧠 Skills Support](#-skills-support)
  31. - [🧩 ACP Integration (Agent Client Protocol)](#-acp-integration-agent-client-protocol)
  32. - [πŸ“‘ Remote Control](#-remote-control)
  33. - [πŸ€– Supported Model Providers](#-supported-model-providers)
  34. - [Compatible with any model provider in OpenAI/Gemini/Anthropic API format](#compatible-with-any-model-provider-in-openaigeminianthropic-api-format)
  35. - [πŸ” Use Cases](#-use-cases)
  36. - [πŸ’» Development Guide](#-development-guide)
  37. - [Install Dependencies](#install-dependencies)
  38. - [Start Development](#start-development)
  39. - [Build](#build)
  40. - [πŸ‘₯ Community \& Contribution](#-community--contribution)
  41. - [⭐ Star History](#-star-history)
  42. - [πŸ‘¨β€πŸ’» Contributors](#-contributors)
  43. - [πŸ“ƒ License](#-license)
  44. ## πŸš€ Project Introduction
  45. DeepChat is a powerful open-source, local-first AI agent desktop client that brings together models, tools, Skills, agent runtimes, Tape, and long-running sessions in one desktop app. Whether you're using cloud APIs like OpenAI, Gemini, Anthropic, or locally deployed Ollama models, DeepChat delivers a smooth user experience.
  46. DeepChat's sessions and agent processes follow the Tape.systems philosophy: keep the process, so context, tool calls, requests, and results stay recoverable, traceable, and inspectable. It also provides strong MCP support, installable Skills, ACP agent integration, and remote control for Telegram, Feishu/Lark, QQBot, Discord, WeChat iLink, and other messaging workflows.
  47. <table align="center">
  48. <tr>
  49. <td align="center" style="padding: 10px;">
  50. <img src='./assets/screenshots/main-light.png' alt="DeepChat main interface in light mode" width="400"/>
  51. <br/>
  52. </td>
  53. <td align="center" style="padding: 10px;">
  54. <img src='./assets/screenshots/main-dark.png' alt="DeepChat main interface in dark mode" width="400"/>
  55. <br/>
  56. </td>
  57. </tr>
  58. </table>
  59. ## πŸ’‘ Why Choose DeepChat
  60. Compared to other AI tools, DeepChat offers the following unique advantages:
  61. - **Local-First Agent Desktop Client**: Run DeepChat agents, ACP agents, and remote-ready bots in one local app
  62. - **Tape.systems Philosophy**: Preserve recoverable session history, trace request context, and inspect token budgets when agent work gets complex
  63. - **Skills That Travel**: Install, import, export, and enable reusable Skills per conversation for code review, documents, frontend work, Office/PDF tasks, and more
  64. - **Native ACP Integration**: Run ACP-compatible coding and task agents as first-class entries in the model selector
  65. - **Strong MCP Support**: Support Resources, Prompts, Tools, multiple transports, inMemory services, and one-click installation
  66. - **Remote-Ready Workflows**: Control DeepChat sessions from Telegram, Feishu/Lark, QQBot, Discord, and WeChat iLink
  67. - **Unified Multi-Model Management**: One application supports mainstream cloud LLMs and local Ollama models, eliminating the need to switch between multiple apps
  68. - **Privacy-Focused**: Local data storage and network proxy support reduce the risk of information leakage
  69. - **Business-Friendly**: Embraces open source under the Apache License 2.0, suitable for both commercial and personal use
  70. ## πŸ“¦ Quick Start
  71. ### Download and Install
  72. You can install DeepChat using one of the following methods:
  73. **Option 1: GitHub Releases**
  74. Download the latest version for your system from the [GitHub Releases](https://github.com/ThinkInAIXYZ/deepchat/releases) page:
  75. - Windows: `.exe` installation file
  76. - macOS: `.dmg` installation file
  77. - Linux: `.AppImage` or `.deb` installation file
  78. **Option 2: Official Website**
  79. Download from the [official website](https://deepchatai.cn/#/download).
  80. **Option 3: Homebrew (macOS only)**
  81. For macOS users, you can install DeepChat using Homebrew:
  82. ```bash
  83. brew install --cask deepchat
  84. ```
  85. ### Configure Models
  86. 1. Launch the DeepChat application
  87. 2. Click the settings icon
  88. 3. Select the "Model Providers" tab
  89. 4. Add your API keys or configure local Ollama
  90. ### Start Conversations
  91. 1. Click the "+" button to create a new conversation
  92. 2. Select the model you want to use
  93. 3. Start communicating with your AI assistant
  94. ## πŸ”₯ Main Features
  95. - πŸ€– **Local-First Agent Desktop Client**
  96. - Select DeepChat, ACP, and remote-capable agents from one model-like entry point
  97. - Run long-lived sessions with project folders, permission modes, tool output, and resumable context
  98. - πŸ“Ό **Tape & Trace**
  99. - Session Tape records structured work history for recovery, resume, and future agent memory flows
  100. - Trace previews show request sequences, provider/model metadata, Tape view manifests, included entries, and token budgets
  101. - 🧠 **Skills**
  102. - Install Skills from folders, ZIP files, or URLs
  103. - Enable Skills per conversation so DeepChat can load task-specific instructions, references, and optional scripts
  104. - Import and export Skills with Claude Code, Codex, Cursor, Windsurf, GitHub Copilot, and other compatible tools
  105. - 🀝 **ACP (Agent Client Protocol) Agent Integration**
  106. - Run ACP-compatible agents (built-in or custom commands) as selectable β€œmodels”
  107. - ACP workspace UI for structured plans, tool calls, and terminal output when provided by the agent
  108. - πŸ“‘ **Remote Control**
  109. - Control DeepChat sessions from Telegram, Feishu/Lark, QQBot, Discord, and WeChat iLink
  110. - Bind remote endpoints to sessions, switch models, answer pending interactions, stop runs, and open desktop sessions remotely
  111. - 🌐 **Multiple Cloud LLM Provider Support**: DeepSeek, OpenAI, Moonshot/Kimi, Grok, Gemini, Anthropic, and more
  112. - 🏠 **Local Model Deployment Support**:
  113. - Integrated Ollama with comprehensive management capabilities
  114. - Control and manage Ollama model downloads, deployments, and runs without command-line operations
  115. - πŸš€ **Rich and Easy-to-Use Chat Capabilities**
  116. - Complete Markdown rendering with code block rendering based on industry-leading [CodeMirror](https://codemirror.net/)
  117. - Multi-window + multi-tab architecture supporting parallel multi-session operations across all dimensions, use large models like using a browser, non-blocking experience brings excellent efficiency
  118. - Supports Artifacts rendering for diverse result presentation
  119. - Messages support retry to generate multiple variations; conversations can be forked freely, ensuring there's always a suitable line of thought
  120. - Supports rendering images, Mermaid diagrams, and other multi-modal content; supports GPT-4o, Gemini, Grok text-to-image capabilities
  121. - Supports highlighting external information sources like search results within the content
  122. - πŸ” **Robust Search Extension Capabilities**
  123. - Built-in integration with leading search APIs like Bocha Search and Brave Search, allowing the model to intelligently decide when to search
  124. - Supports mainstream search engines like Google, Bing, Baidu, and Sogou Official Accounts search by simulating user web browsing, enabling the LLM to read search engines like a human
  125. - Supports reading any search engine; simply configure a search assistant model to connect various search sources, whether internal networks, API-less engines, or vertical domain search engines, as information sources for the model
  126. - πŸ”§ **Strong MCP (Model Context Protocol) Support**
  127. - Full support for Resources / Prompts / Tools
  128. - Supports StreamableHTTP, SSE, Stdio, and other transports
  129. - Official Node.js toolchain for npx/node-style services, installed from Settings when needed
  130. - inMemory services for code execution, web information retrieval, file operations, and other common utilities
  131. - Clear tool-call display with parameter and return-data debugging
  132. - DeepLink support for one-click MCP service installation
  133. - πŸ’» **Multi-Platform Support**: Windows, macOS, Linux
  134. - 🎨 **Beautiful and User-Friendly Interface**, user-oriented design, meticulously themed light and dark modes
  135. - πŸ”— **Rich DeepLink Support**: Initiate conversations via links for seamless integration with other applications, including one-click MCP service installation.
  136. - πŸš‘ **Security-First Design**: Chat data and configuration data have reserved encryption interfaces and code obfuscation capabilities
  137. - πŸ›‘οΈ **Privacy Protection**: Supports screen projection hiding, network proxies, and other privacy protection methods to reduce the risk of information leakage
  138. - πŸ’° **Business-Friendly**:
  139. - Embraces open source, based on the Apache License 2.0 protocol, enterprise use without worry
  140. - Enterprise integration requires only minimal configuration code changes to use reserved encrypted obfuscation security capabilities
  141. - Clear code structure, both model providers and MCP services are highly decoupled, can be freely customized with minimal cost
  142. - Reasonable architecture, data interaction and UI behavior separation, fully utilizing Electron's capabilities, rejecting simple web wrappers, excellent performance
  143. ## πŸ“Ό Tape & Trace
  144. DeepChat's session Tape follows the Tape.systems philosophy and keeps agent work recoverable and inspectable. Trace previews expose request sequences, provider/model metadata, Tape view manifests, included or excluded entries, and token budgets, making long-running agent sessions easier to debug and resume.
  145. ## 🧠 Skills Support
  146. DeepChat Skills are designed to be compatible with the standard Agent Skills specification. A Skill can include task instructions, reference files, assets, and optional scripts, so DeepChat can act more like a domain specialist after it is enabled.
  147. You can install Skills from folders, ZIP files, or URLs, and import/export them with Claude Code, Codex, Cursor, Windsurf, GitHub Copilot, Kiro, Antigravity, OpenCode, Goose, Kilo Code, and other compatible tools.
  148. Built-in Skills cover algorithmic art, code review, DeepChat CLI, DeepChat settings, document collaboration, DOCX, frontend design, git commit messages, infographic syntax, MCP building, memory management, PDF, PPTX, Skill creation, and XLSX workflows.
  149. Quick start:
  150. 1. Open **Settings β†’ Skills**
  151. 2. Install or import a Skill
  152. 3. Enable it in conversations that need that capability
  153. ## 🧩 ACP Integration (Agent Client Protocol)
  154. DeepChat has built-in support for [Agent Client Protocol (ACP)](https://agentclientprotocol.com), allowing you to integrate external agent runtimes into DeepChat with a native UI. Once enabled, ACP agents appear as first-class entries in the model selector, so you can use coding agents and task agents directly inside DeepChat.
  155. Quick start:
  156. 1. Open **Settings β†’ ACP Agents** and enable ACP
  157. 2. Enable a built-in ACP agent or add a custom ACP-compatible command
  158. 3. Select the ACP agent in the model selector to start an agent session
  159. To explore the ecosystem of compatible agents and clients, see: https://agentclientprotocol.com/overview/clients
  160. ## πŸ“‘ Remote Control
  161. DeepChat can be controlled from messaging apps, so you can keep a session running even when you are away from the desktop. Configure remote channels under **Settings β†’ Remote**.
  162. Supported channels include Telegram, Feishu/Lark, QQBot, Discord, and WeChat iLink. Remote endpoints can bind to one DeepChat session, then create new sessions, list and switch recent sessions, stop generation, open the current session on desktop, answer pending questions or permission prompts, switch models, and check runtime status.
  163. Common commands include `/start`, `/help`, `/pair`, `/new`, `/sessions`, `/use`, `/stop`, `/open`, `/pending`, `/model`, and `/status`.
  164. ## πŸ€– Supported Model Providers
  165. <table>
  166. <tr align="center">
  167. <td>
  168. <img src="./src/renderer/src/assets/llm-icons/deepseek-color.svg" width="50" height="50" alt="Deepseek Icon"><br/>
  169. <a href="https://deepseek.com/">Deepseek</a>
  170. </td>
  171. <td>
  172. <img src="./src/renderer/src/assets/llm-icons/moonshot.svg" width="50" height="50" alt="Moonshot Icon"><br/>
  173. <a href="https://moonshot.ai/">Moonshot</a>
  174. </td>
  175. <td>
  176. <img src="./src/renderer/src/assets/llm-icons/openai.svg" width="50" height="50" alt="OpenAI Icon"><br/>
  177. <a href="https://openai.com/">OpenAI</a>
  178. </td>
  179. <td>
  180. <img src="./src/renderer/src/assets/llm-icons/gemini-color.svg" width="50" height="50" alt="Gemini Icon"><br/>
  181. <a href="https://gemini.google.com/">Gemini</a>
  182. </td>
  183. </tr>
  184. <tr align="center">
  185. <td>
  186. <img src="./src/renderer/src/assets/llm-icons/ollama.svg" width="50" height="50" alt="Ollama Icon"><br/>
  187. <a href="https://ollama.com/">Ollama</a>
  188. </td>
  189. <td>
  190. <img src="./src/renderer/src/assets/llm-icons/qiniu.svg" width="50" height="50" alt="Qiniu Icon"><br/>
  191. <a href="https://www.qiniu.com">Qiniu</a>
  192. </td>
  193. <td>
  194. <img src="./src/renderer/src/assets/llm-icons/newapi.svg" width="50" height="50" alt="New API Icon"><br/>
  195. <a href="https://www.newapi.ai/">New API</a>
  196. </td>
  197. <td>
  198. <img src="./src/renderer/src/assets/llm-icons/grok.svg" width="50" height="50" alt="Grok Icon"><br/>
  199. <a href="https://x.ai/">Grok</a>
  200. </td>
  201. </tr>
  202. <tr align="center">
  203. <td>
  204. <img src="./src/renderer/src/assets/llm-icons/zhipu-color.svg" width="50" height="50" alt="Zhipu Icon"><br/>
  205. <a href="https://open.bigmodel.cn/">Zhipu</a>
  206. </td>
  207. <td>
  208. <img src="./src/renderer/src/assets/llm-icons/ppio-color.svg" width="50" height="50" alt="PPIO Icon"><br/>
  209. <a href="https://ppinfra.com/">PPIO</a>
  210. </td>
  211. <td>
  212. <img src="./src/renderer/src/assets/llm-icons/minimax-color.svg" width="50" height="50" alt="MiniMax Icon"><br/>
  213. <a href="https://platform.minimaxi.com/">MiniMax</a>
  214. </td>
  215. <td>
  216. <img src="./src/renderer/src/assets/llm-icons/fireworks-color.svg" width="50" height="50" alt="Fireworks Icon"><br/>
  217. <a href="https://fireworks.ai/">Fireworks</a>
  218. </td>
  219. </tr>
  220. <tr align="center">
  221. <td>
  222. <img src="./src/renderer/src/assets/llm-icons/aihubmix.png" width="50" height="50" alt="AIHubMix Icon"><br/>
  223. <a href="https://aihubmix.com/">AIHubMix</a>
  224. </td>
  225. <td>
  226. <img src="./src/renderer/src/assets/llm-icons/doubao-color.svg" width="50" height="50" alt="Doubao Icon"><br/>
  227. <a href="https://console.volcengine.com/ark/">Doubao</a>
  228. </td>
  229. <td>
  230. <img src="./src/renderer/src/assets/llm-icons/alibabacloud-color.svg" width="50" height="50" alt="DashScope Icon"><br/>
  231. <a href="https://www.aliyun.com/product/bailian">DashScope</a>
  232. </td>
  233. <td>
  234. <img src="./src/renderer/src/assets/llm-icons/groq.svg" width="50" height="50" alt="Groq Icon"><br/>
  235. <a href="https://groq.com/">Groq</a>
  236. </td>
  237. </tr>
  238. <tr align="center">
  239. <td>
  240. <img src="./src/renderer/src/assets/llm-icons/jiekou-color.svg" width="50" height="50" alt="JieKou.AI Icon"><br/>
  241. <a href="https://jiekou.ai?utm_source=github_deepchat">JieKou.AI</a>
  242. </td>
  243. <td>
  244. <img src="./src/renderer/src/assets/llm-icons/zenmux-color.svg" width="50" height="50" alt="ZenMux Icon"><br/>
  245. <a href="https://zenmux.ai/">ZenMux</a>
  246. </td>
  247. <td>
  248. <img src="./src/renderer/src/assets/llm-icons/github.svg" width="50" height="50" alt="GitHub Models Icon"><br/>
  249. <a href="https://github.com/marketplace/models">GitHub Models</a>
  250. </td>
  251. <td>
  252. <img src="./src/renderer/src/assets/llm-icons/lmstudio.svg" width="50" height="50" alt="LM Studio Icon"><br/>
  253. <a href="https://lmstudio.ai/docs/app">LM Studio</a>
  254. </td>
  255. </tr>
  256. <tr align="center">
  257. <td>
  258. <img src="./src/renderer/src/assets/llm-icons/hunyuan-color.svg" width="50" height="50" alt="Hunyuan Icon"><br/>
  259. <a href="https://cloud.tencent.com/product/hunyuan">Hunyuan</a>
  260. </td>
  261. <td>
  262. <img src="./src/renderer/src/assets/llm-icons/302ai.svg" width="50" height="50" alt="302.AI Icon"><br/>
  263. <a href="https://302ai.cn/">302.AI</a>
  264. </td>
  265. <td>
  266. <img src="./src/renderer/src/assets/llm-icons/together-color.svg" width="50" height="50" alt="Together Icon"><br/>
  267. <a href="https://www.together.ai/">Together</a>
  268. </td>
  269. <td>
  270. <img src="./src/renderer/src/assets/llm-icons/poe-color.svg" width="50" height="50" alt="Poe Icon"><br/>
  271. <a href="https://poe.com/">Poe</a>
  272. </td>
  273. </tr>
  274. <tr align="center">
  275. <td>
  276. <img src="./src/renderer/src/assets/llm-icons/vercel.svg" width="50" height="50" alt="Vercel AI Gateway Icon"><br/>
  277. <a href="https://vercel.com/ai">Vercel AI Gateway</a>
  278. </td>
  279. <td>
  280. <img src="./src/renderer/src/assets/llm-icons/openrouter.svg" width="50" height="50" alt="OpenRouter Icon"><br/>
  281. <a href="https://openrouter.ai/">OpenRouter</a>
  282. </td>
  283. <td>
  284. <img src="./src/renderer/src/assets/llm-icons/azure-color.svg" width="50" height="50" alt="Azure OpenAI Icon"><br/>
  285. <a href="https://azure.microsoft.com/en-us/products/ai-services/openai-service">Azure OpenAI</a>
  286. </td>
  287. <td>
  288. <img src="./src/renderer/src/assets/llm-icons/tokenflux-color.svg" width="50" height="50" alt="TokenFlux Icon"><br/>
  289. <a href="https://tokenflux.ai/">TokenFlux</a>
  290. </td>
  291. </tr>
  292. <tr align="center">
  293. <td>
  294. <img src="./src/renderer/src/assets/llm-icons/burncloud-color.svg" width="50" height="50" alt="BurnCloud Icon"><br/>
  295. <a href="https://www.burncloud.com/">BurnCloud</a>
  296. </td>
  297. <td>
  298. <img src="./src/renderer/src/assets/llm-icons/openai.svg" width="50" height="50" alt="OpenAI Responses Icon"><br/>
  299. <a href="https://openai.com/">OpenAI Responses</a>
  300. </td>
  301. <td>
  302. <img src="./src/renderer/src/assets/llm-icons/cherryin-color.png" width="50" height="50" alt="CherryIn Icon"><br/>
  303. <a href="https://open.cherryin.ai/console">CherryIn</a>
  304. </td>
  305. <td>
  306. <img src="./src/renderer/src/assets/llm-icons/modelscope-color.svg" width="50" height="50" alt="ModelScope Icon"><br/>
  307. <a href="https://modelscope.cn/">ModelScope</a>
  308. </td>
  309. </tr>
  310. <tr align="center">
  311. <td>
  312. <img src="./src/renderer/src/assets/llm-icons/aws-bedrock.svg" width="50" height="50" alt="AWS Bedrock Icon"><br/>
  313. <a href="https://aws.amazon.com/bedrock/">AWS Bedrock</a>
  314. </td>
  315. <td>
  316. <img src="./src/renderer/src/assets/llm-icons/voiceai.svg" width="50" height="50" alt="Voice.ai Icon"><br/>
  317. <a href="https://voice.ai/">Voice.ai</a>
  318. </td>
  319. <td>
  320. <img src="./src/renderer/src/assets/llm-icons/vertexai-color.svg" width="50" height="50" alt="Vertex AI Icon"><br/>
  321. <a href="https://cloud.google.com/vertex-ai">Vertex AI</a>
  322. </td>
  323. <td>
  324. <img src="./src/renderer/src/assets/llm-icons/githubcopilot.svg" width="50" height="50" alt="GitHub Copilot Icon"><br/>
  325. <a href="https://github.com/features/copilot">GitHub Copilot</a>
  326. </td>
  327. </tr>
  328. <tr align="center">
  329. <td>
  330. <img src="./src/renderer/src/assets/llm-icons/xiaomi.png" width="50" height="50" alt="Xiaomi Icon"><br/>
  331. <a href="https://platform.xiaomimimo.com/#/docs/quick-start/first-api-call">Xiaomi</a>
  332. </td>
  333. <td>
  334. <img src="./src/renderer/src/assets/llm-icons/o3-fan.png" width="50" height="50" alt="o3.fan Icon"><br/>
  335. <a href="https://o3.fan">o3.fan</a>
  336. </td>
  337. <td>
  338. <img src="./src/renderer/src/assets/llm-icons/novitaai.svg" width="50" height="50" alt="Novita AI Icon"><br/>
  339. <a href="https://novita.ai/">Novita AI</a>
  340. </td>
  341. <td>
  342. <img src="./src/renderer/src/assets/llm-icons/astraflow.png" width="50" height="50" alt="Astraflow Icon"><br/>
  343. <a href="https://astraflow.ucloud.cn/">Astraflow</a>
  344. </td>
  345. </tr>
  346. <tr align="center">
  347. <td>
  348. <img src="./src/renderer/src/assets/llm-icons/anthropic.svg" width="50" height="50" alt="Anthropic Icon"><br/>
  349. <a href="https://www.anthropic.com/">Anthropic</a>
  350. </td>
  351. <td>
  352. <img src="./src/renderer/src/assets/llm-icons/siliconcloud-color.svg" width="50" height="50" alt="SiliconFlow Icon"><br/>
  353. <a href="https://www.siliconflow.cn/">SiliconFlow</a>
  354. </td>
  355. <td>
  356. <img src="./src/renderer/src/assets/llm-icons/orcarouter.svg" width="50" height="50" alt="OrcaRouter Icon"><br/>
  357. <a href="https://www.orcarouter.ai/">OrcaRouter</a>
  358. </td>
  359. <td>
  360. <img src="./src/renderer/src/assets/llm-icons/synthorai.svg" width="50" height="50" alt="Synthorai Icon"><br/>
  361. <a href="https://synthorai.io/">Synthorai</a>
  362. </td>
  363. </tr>
  364. <tr align="center">
  365. <td>
  366. <img src="./src/renderer/src/assets/llm-icons/requesty.png" width="50" height="50" alt="Requesty Icon"><br/>
  367. <a href="https://www.requesty.ai/">Requesty</a>
  368. </td>
  369. <td>
  370. <img src="./src/renderer/src/assets/llm-icons/litellm.svg" width="50" height="50" alt="LiteLLM Icon"><br/>
  371. <a href="https://www.litellm.ai/">LiteLLM</a>
  372. </td>
  373. <td>
  374. <img src="./src/renderer/src/assets/llm-icons/opper.svg" width="50" height="50" alt="Opper Icon"><br/>
  375. <a href="https://opper.ai/">Opper</a>
  376. </td>
  377. <td>
  378. <img src="./src/renderer/src/assets/llm-icons/aistupidlevel.svg" width="50" height="50" alt="AI Stupid Level Icon"><br/>
  379. <a href="https://aistupidlevel.info/">AI Stupid Level</a>
  380. </td>
  381. <td>
  382. <img src="./src/renderer/src/assets/llm-icons/runcrate.svg" width="50" height="50" alt="Runcrate Icon"><br/>
  383. <a href="https://www.runcrate.ai/?utm_source=deepchat">Runcrate</a>
  384. </td>
  385. <td>
  386. <img src="./src/renderer/src/assets/llm-icons/cloudgpu.svg" width="50" height="50" alt="CloudGPU Icon"><br/>
  387. <a href="https://cloudgpu.app/?utm_source=deepchat">CloudGPU</a>
  388. </td>
  389. <td>
  390. <img src="./src/renderer/src/assets/llm-icons/cheapaimodel.svg" width="50" height="50" alt="cheapaimodel Icon"><br/>
  391. <a href="https://cheapaimodel.ai/?utm_source=deepchat">cheapaimodel</a>
  392. </td>
  393. </tr>
  394. <tr align="center">
  395. <td>
  396. <img src="./src/renderer/src/assets/llm-icons/obscurify.svg" width="50" height="50" alt="Obscurify.ai Icon"><br/>
  397. <a href="https://obscurify.ai/?utm_source=deepchat">Obscurify.ai</a>
  398. </td>
  399. <td>
  400. <img src="./src/renderer/src/assets/llm-icons/wally-color.svg" width="50" height="50" alt="Wally Icon"><br/>
  401. <a href="https://www.runwally.com/">Wally</a>
  402. </td>
  403. <td>
  404. <img src="./src/renderer/src/assets/llm-icons/trustedrouter.svg" width="50" height="50" alt="TrustedRouter Icon"><br/>
  405. <a href="https://trustedrouter.com/">TrustedRouter</a>
  406. </td>
  407. <td>
  408. <img src="./src/renderer/src/assets/llm-icons/standardcompute.svg" width="50" height="50" alt="Standard Compute Icon"><br/>
  409. <a href="https://standardcompute.com/">Standard Compute</a>
  410. </td>
  411. </tr>
  412. <tr align="center">
  413. <td>
  414. <img src="./src/renderer/src/assets/llm-icons/uberllm-color.svg" width="50" height="50" alt="UberLLM Icon"><br/>
  415. <a href="https://uberllm.dev/">UberLLM</a>
  416. </td>
  417. <td>
  418. <img src="./src/renderer/src/assets/llm-icons/openllm.svg" width="50" height="50" alt="OpenLLM Icon"><br/>
  419. <a href="https://www.openllm.sh/">OpenLLM</a>
  420. </td>
  421. <td>
  422. <img src="./src/renderer/src/assets/llm-icons/wiro.svg" width="50" height="50" alt="Wiro AI Icon"><br/>
  423. <a href="https://wiro.ai/">Wiro AI</a>
  424. </td>
  425. </tr>
  426. </table>
  427. ### Compatible with any model provider in OpenAI/Gemini/Anthropic API format
  428. Any service that speaks the OpenAI, Gemini, or Anthropic API format can be added as a custom provider next to the built-in ones.
  429. ## πŸ” Use Cases
  430. DeepChat is suitable for various AI application scenarios:
  431. - **Daily Assistant**: Answering questions, providing suggestions, assisting with writing and creation
  432. - **Development Aid**: Code generation, debugging, technical problem solving
  433. - **Learning Tool**: Concept explanation, knowledge exploration, learning guidance
  434. - **Content Creation**: Copywriting, creative inspiration, content optimization
  435. - **Data Analysis**: Data interpretation, chart generation, report writing
  436. ## πŸ’» Development Guide
  437. Please read the [Contribution Guidelines](./CONTRIBUTING.md)
  438. Windows and Linux are packaged by GitHub Action.
  439. For Mac-related signing and packaging, please refer to the [Mac Release Guide](https://github.com/ThinkInAIXYZ/deepchat/wiki/Mac-Release-Guide).
  440. ### Install Dependencies
  441. ```bash
  442. $ pnpm install
  443. $ pnpm run installRuntime
  444. # if got err: No module named 'distutils'
  445. $ pip install setuptools
  446. ```
  447. * For Windows: To allow non-admin users to create symlinks and hardlinks, enable `Developer Mode` in Settings or use an administrator account. Otherwise `pnpm` ops will fail.
  448. ### Start Development
  449. ```bash
  450. $ pnpm run dev
  451. ```
  452. ### Build
  453. ```bash
  454. # For Windows
  455. $ pnpm run build:win
  456. # For macOS
  457. $ pnpm run build:mac
  458. # For Linux
  459. $ pnpm run build:linux
  460. # Specify architecture packaging
  461. $ pnpm run build:win:x64
  462. $ pnpm run build:win:arm64
  463. $ pnpm run build:mac:x64
  464. $ pnpm run build:mac:arm64
  465. $ pnpm run build:linux:x64
  466. $ pnpm run build:linux:arm64
  467. ```
  468. For a more detailed guide on development, project structure, and architecture, please see the [Developer Guide](./docs/guides/getting-started.md) and the maintained [documentation index](./docs/README.md).
  469. ## πŸ‘₯ Community & Contribution
  470. DeepChat is an active open-source community project, and we welcome various forms of contribution:
  471. - πŸ› [Report issues](https://github.com/ThinkInAIXYZ/deepchat/issues)
  472. - πŸ’‘ [Submit feature suggestions](https://github.com/ThinkInAIXYZ/deepchat/issues)
  473. - πŸ”§ [Submit code improvements](https://github.com/ThinkInAIXYZ/deepchat/pulls)
  474. - πŸ“š [Improve documentation](https://github.com/ThinkInAIXYZ/deepchat/wiki)
  475. - 🌍 [Help with translation](https://github.com/ThinkInAIXYZ/deepchat/tree/main/src/renderer/src/i18n)
  476. Check the [Contribution Guidelines](./CONTRIBUTING.md) to learn more about ways to participate in the project.
  477. ## ⭐ Star History
  478. [![Star History Chart](https://star-history.dera.page/svg?repos=ThinkInAIXYZ/deepchat&type=Timeline)](https://star-history.dera.page/#ThinkInAIXYZ/deepchat&Timeline)
  479. ## πŸ‘¨β€πŸ’» Contributors
  480. Thank you for considering contributing to deepchat! The contribution guide can be found in the [Contribution Guidelines](./CONTRIBUTING.md).
  481. <a href="https://openomy.com/thinkinaixyz/deepchat" target="_blank" style="display: block; width: 100%;" align="center">
  482. <img src="https://openomy.com/svg?repo=thinkinaixyz/deepchat&chart=bubble&latestMonth=3" target="_blank" alt="Contribution Leaderboard" style="display: block; width: 100%;" />
  483. </a>
  484. ## πŸ™πŸ» Thanks
  485. This project is built with the help of these awesome libraries and projects:
  486. - [Vue](https://vuejs.org/)
  487. - [Electron](https://www.electronjs.org/)
  488. - [Electron-Vite](https://electron-vite.org/)
  489. - [oxlint](https://github.com/oxc-project/oxc)
  490. - [Bub](https://github.com/bubbuild/bub), whose tape model inspired DeepChat's session tape design. For the underlying tape architecture, visit [tape.systems](https://tape.systems/).
  491. ## πŸ“ƒ License
  492. [LICENSE](./LICENSE)

Ratings and comments

Sign in to rate this skill.

Sign in

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