Which LLM providers are supported?
Ask m’ AI supports OpenAI, LocalAI, Ollama, Anthropic, Mistral, DeepSeek, Google Gemini, Github Copilot, and AnythingLLM.
@rainu
基本信息
A scriptable and powerful UI-Chat-Application for chatting with most Gen-AI LLMs
工具列表暂未提供
当前收录暂时没有可展示的工具列表,不代表服务没有工具。请查阅项目文档了解支持的能力。
工具是从 README 中自动提取的。维护者可以在 ## Tools 标题下列出工具,即可填充这部分内容。
Ask m’ AI is a desktop chat application for large language models (e.g., OpenAI’s GPT). It is designed to be scriptable – you can call it from the terminal with all necessary options as arguments, and conversations are printed to the terminal for use in scripts.
Install it via AUR (yay -S ask-mai) or download a release for your OS/architecture. Launch it from the command line with a provider flag (e.g., -b openai for OpenAI) and the required API keys. You can also run it as an MCP server by using ask-mai ask-mai-mcp-server or renaming the binary to ask-mai-mcp-server.
Ask m’ AI supports OpenAI, LocalAI, Ollama, Anthropic, Mistral, DeepSeek, Google Gemini, Github Copilot, and AnythingLLM.
Pass `ask-mai-mcp-server` as the first positional argument, e.g., `ask-mai ask-mai-mcp-server`. You can also rename the binary to `ask-mai-mcp-server` and run it directly. To stream via HTTP, add the `-http-address` flag.
On Arch Linux, install via AUR (`yay -S ask-mai`). For other systems, download the appropriate binary from the releases page. You can also build it yourself using the Wails framework and, optionally, package it as a Flatpak.
Yes. You can choose between light and dark themes, select from several code highlight themes, and set the UI language to English or German.
Yes. The application is scriptable and prints conversations to the terminal, so it can be used non‑interactively in scripts. You can also start it with a pre‑filled prompt using the `-ui-prompt` flag.

Yuppsy MCP: build and publish real estate websites from your AI assistant. Yuppsy lets your AI assistant create live websites for real estate agents and individual property listings. You don't need a designer or any code
不止于 CSS
A curated list of references for MLOps
YC (S26) | Open Computer History | Continuously record your company computer work, map your workflows, help you find work worth automating, and power your agents' context
Hindsight: Agent Memory That Learns
评论