An open-source, local-first AI agent desktop client supporting MCP, Skills, ACP agents and remote control from messaging apps.
Lucassssss/eechat
A locally deployed desktop AI chat client with MCP tool support, offering private conversation storage and connections to your own or third-party model APIs.
Open-source alternative to:ChatGPT
- Stars
- 347
- Forks
- 47
- Open issues
- 21
- Last commit
- 2 months ago
What is it?
eechat is a desktop AI chat application built for local deployment. Conversation history is stored on the user's machine, and the app can connect to your own model API or third-party services such as OpenAI and Anthropic, or to custom local or remote models.
The main extension point is MCP (Model Context Protocol). A management interface lets users add, start, stop and remove MCP tools without using the command line, and tool configurations can be edited as JSON with compatibility noted for Claude Desktop, Cursor and Cline configs. Bun and uv runtimes can be detected or downloaded automatically, and MCP tools can be called directly from the chat window.
The chat interface includes multi-session management, Markdown rendering with code highlighting, tables and math formulas, light and dark themes, saved prompts, and adjustable model parameters such as temperature and max output. Pre-built packages are available for Windows, macOS and Linux, and the project can also be built from source with npm.
Key features
- 01Manage and run MCP tools through a visual interface
- 02Call MCP tools directly inside the chat window
- 03Store all conversation history locally
- 04Connect to OpenAI, Anthropic or custom model APIs
- 05Render Markdown with code highlighting, tables and math formulas
- 06Adjust model parameters and save reusable prompts
Use cases
- Running a private AI assistant that keeps conversations on your own machine
- Experimenting with MCP tools without editing configuration files by hand
- Chatting with a self-hosted or custom model through a desktop client
Quick start
- 1
Clone the repository
git clone https://github.com/Lucassssss/eechat.git - 2
Enter the project folder
cd eechat - 3
Install dependencies
npm install - 4
Run in development mode
npm run dev
Things to know
- Build-from-source steps require Node.js and npm.
- No license is clearly stated; the license metadata is unspecified.
- Model features depend on your own API keys or third-party services for cloud models.
Topics
FAQ
- What is eechat?
- A locally deployed desktop AI chat client with MCP tool support, offering private conversation storage and connections to your own or third-party model APIs. eechat is a desktop AI chat application built for local deployment. Conversation history is stored on the user's machine, and the app can connect to your own model API or third-party services such as OpenAI and Anthropic, or to custom local or remote models.
- Is eechat free to use? What license does it have?
- eechat is open source under the Other license. Check the license terms before using it in commercial products.
- Is eechat still maintained?
- Updated within 6 months. The last commit to eechat was on Aug 11, 2026.
- What can I use eechat for?
- Running a private AI assistant that keeps conversations on your own machine Experimenting with MCP tools without editing configuration files by hand Chatting with a self-hosted or custom model through a desktop client
- How do I install eechat?
- Clone the repository: git clone https://github.com/Lucassssss/eechat.git Enter the project folder: cd eechat Install dependencies: npm install Run in development mode: npm run dev
- Where can I get eechat?
- The source code and installation instructions are on GitHub: https://github.com/Lucassssss/eechat
Summary generated by AI from the project's README. GitHub stats refresh daily.
Related projects
A cross-platform desktop AI assistant that connects to major LLM providers and acts as an MCP client with a local knowledge base.
Cross-platform AI chat client that connects LLMs such as OpenAI, Claude, Ollama and DeepSeek to MCP servers.
Cherry Studio is a cross-platform desktop AI client that connects to many LLM providers, local models and 300+ preset assistants.
A local-first AI chat client that connects to multiple LLM providers and adds productivity tools through the MCP protocol.
Local and cloud runner for open models such as Gemma, Qwen, DeepSeek and gpt-oss, with a CLI, REST API and Python/JavaScript libraries.