📌Overview

Purpose:
To provide a unified, open-source AI chat platform that enables seamless interaction with multiple cloud and local large language models through an intuitive, feature-rich interface.

Overview:
DeepChat is a cross-platform AI assistant application designed to centralize access to various large language models (LLMs) such as OpenAI, Gemini, Anthropic, and locally deployed models like Ollama. It offers not only standard chat abilities but also advanced enhancements, including integrated search, tool calling, and multimodal interactions. Its user-focused, privacy-respecting design makes advanced AI technologies easily accessible for both personal and business scenarios.

Key Features:

Unified Multi-Model Support:
Connects to almost all mainstream cloud and local LLMs, allowing users to switch and manage models—like OpenAI, Gemini, Anthropic, and Ollama—within a single application.
Advanced Interaction Capabilities:
Extends beyond basic chat by integrating search enhancements (supporting multiple search engines), built-in tool calling (e.g., code execution, web access), and multimodal content rendering, making exchanges richer, more accurate, and more interactive.

DeepChat - Powerful Open-Source Multi-Model AI Chat Platform

DeepChat is a feature-rich open-source AI chat platform supporting multiple cloud and local large language models with powerful search enhancement and tool calling capabilities.

Project Introduction
Why Choose DeepChat
Main Features
Supported Model Providers
Use Cases
Quick Start
Development Guide
Community & Contribution
License

Project Introduction

DeepChat is a powerful open-source AI chat platform providing a unified interface for interacting with various large language models. It supports both cloud APIs (such as OpenAI, Gemini, Anthropic) and local models (including Ollama). DeepChat delivers features like search enhancement, tool calling, and multimodal interaction.

Why Choose DeepChat

Unified Multi-Model Management: Supports all mainstream LLMs in one app.
Seamless Local Model Integration: Built-in Ollama support for managing and using local models.
Powerful Search Enhancement: Integrates with multiple search engines for more accurate and timely responses.
Advanced Tool Calling: Code execution, web access, and other tools integrated without extra configuration.
Privacy-Focused: Local data storage and proxy support reduce information leakage risk.
Business-Friendly: Open sourced under Apache License 2.0, suitable for commercial and personal use.

Main Features

Cloud LLM Provider Support: Compatible with DeepSeek, OpenAI, Silicon Flow, Grok, Gemini, Anthropic, and more.
Local Model Deployment Support: Integrated Ollama with full management capabilities.
Rich Chat Capabilities:
- Complete Markdown and code block rendering
- Multi-session support for parallel chats
- Conversations can be forked, messages retried for variations
- Image, Mermaid diagrams, and text-to-image (Gemini) supported
- External information (e.g., search results) highlighted
Search Extensions:
- Integration with APIs such as Brave Search
- Supports Google, Bing, Baidu, and Sogou Official Accounts search
- Can use any search source via search assistant model
Model Controller Platform (MCP) Support:
- Easy configuration and tool call display
- Debug window with auto-formatting for tool parameters/returns
- Built-in Node.js runtime for tool services, and support for StreamableHTTP/SSE/Stdio protocols
- In-memory services for code execution, web retrieval, and file operations
Multi-Platform: Windows, macOS, Linux
User Interface: Light and dark modes, user-focused design
DeepLink Support: Chat via links, one-click service installation
Security & Privacy: Optional data encryption, code obfuscation, projection hiding, proxies

Supported Model Providers

DeepChat supports major AI model providers, including:

Compatible with any model provider in OpenAI, Gemini, or Anthropic API format.

Use Cases

Sample scenarios where DeepChat excels:

Daily Assistant: Q&A, suggestions, and writing aid
Development Aid: Code generation, debugging, and solving technical problems
Learning Tool: Concept explanation and knowledge exploration
Content Creation: Copywriting, creative inspiration, and optimization
Data Analysis: Interpretation, charting, reporting

Quick Start

Download and Install

Get the latest version from the GitHub Releases page for your OS.

Windows: .exe
macOS: .dmg
Linux: .AppImage or .deb

Configure Models

Launch DeepChat.
Go to settings > "Model Providers".
Add your API keys or set up local Ollama.

Start Conversations

Click "+" for a new conversation.
Pick your model.
Chat!

Development Guide

See the Contribution Guidelines for details.

To install dependencies:

npm install
npm run installRuntime
# If you get "No module named 'distutils'"
pip install setuptools
# For Windows x64
npm install --cpu=x64 --os=win32 sharp
# For mac Apple silicon
npm install --cpu=arm64 --os=darwin sharp
# For mac Intel
npm install --cpu=x64 --os=darwin sharp
# For Linux x64
npm install --cpu=x64 --os=linux sharp

To start development:

npm run dev

To build:

# Windows
npm run build:win
# macOS
npm run build:mac
# Linux
npm run build:linux
# Specify architectures:
npm run build:win:x64
npm run build:win:arm64
npm run build:mac:x64
npm run build:mac:arm64
npm run build:linux:x64
npm run build:linux:arm64

For Mac-specific signing and packaging, refer to the Mac Release Guide.

Community & Contribution

Ways to contribute:

See the Contribution Guidelines for more details.

License

DeepChat is open sourced under the Apache License 2.0.

deepchat