EFFLUX.AI

What is EFFLUX.AI?

Efflux Desktop is an AI copilot for individuals that integrates multi-vendor LLM models and tool invocation via the Model Context Protocol (MCP). It runs on Windows and macOS, giving users control over their human-AI collaboration.

How to use EFFLUX.AI?

After installing the executable, launch Efflux, go to the Models page to configure a vendor API key and endpoint. Then visit the Plugins page to add custom MCP servers (via command/arguments or JSON). Finally, start a chat, select your model, and use the @ sign to invoke a plugin.

Key features of EFFLUX.AI

• Multi-vendor AI model integration (OpenAI, Anthropic, DeepSeek, etc.)
• Dynamic discovery and loading of MCP servers
• Standardized tool calling with exception handling and timeout control
• Text-to-artifact capabilities and real-time streaming responses
• Chat history management and Build mode for constructing tasks
• Plugin management with custom command or JSON configuration

Use cases of EFFLUX.AI

—

FAQ from EFFLUX.AI

What platforms does EFFLUX.AI support?

Windows and macOS.

How do I add my own MCP server?

In the Plugins page, click “Add Custom Plugin” and enter the plugin name, command, environment variables, and arguments, or switch to JSON Mode and paste a JSON string.

Is EFFLUX.AI free and open source?

Yes, the project follows an appropriate open source license. Refer to the LICENSE file for details.

Which AI models are supported?

Multiple vendors are supported, including OpenAI, Anthropic, DeepSeek, and others.

How do I configure a model?

Go to the Models page, find your vendor card, click “API-KEY”, and enter your endpoint and API key, then click Save.