ChatWise
The second fastest AI chatbot™
Core Features
Any LLM
ChatWise supports any LLM model, including GPT-4, Claude, Gemini, and more.
Performance
ChatWise is built with performance in mind, and is optimized for desktop experience.
Privacy
All your data is stored locally, and never leaves your device (except for sending chat requests to your LLM provider).
Simplicity
Simple yet powerful, ChatWise is designed to be easy to use, without the bloat.
Multi-modal
Chat with audio, PDF, images, text files, and more.
Web search
Search the web with Tavily or local browsers for free.
Artifacts
Render HTML/React/Charts/Documents
Web Search That Works
Get realtime info using Tavily's Search API or your local browser for free
Connect to anything with MCP
Make AI use tools like Notion, Google Sheets, Browsers and more
Changelog
v0.8.78
a day ago- MCP: allow to import HTTP MCP servers from clipboard JSON
- Press Arrow-Up (↑) in an empty input box to enter the last user message
- Support native search grounding (model's built-in search tool) if available, currently we've added support for Google Gemini, xAI Grok, and Perplexity Sonar, with more to come.
v0.8.77
5 days ago- Data Export: export the order of assistants in the sidebar
- Custom Provider: allow to select the models you want to add, instead of adding all fetched models
v0.8.76
7 days agoAdded new providers: Kimi, ZhiPu
v0.8.75
11 days agoAdd Long-running option for stdio MCP servers to always keep them connected in the background, useful for servers like @playwright/mcp where you don't want to close the browser after each response.
v0.8.74
12 days agoMCP optimization
For stdio and sse MCP servers, now it will not be kept running in the background when it's not used, MCP servers are only connected when a tool needs to be called during a conversation, and all MCP server connections will be terminated when the conversation is finished.