A Neovim plugin that provides as-you-type AI code completion using OpenAI, Gemini, Claude, Ollama, llama.cpp, Codestral and other LLM providers.
milanglacier/minuet-ai.el
An Emacs package that brings as-you-type code completion from LLMs such as OpenAI, Claude, Gemini, Ollama and llama.cpp into your editor.
Open-source alternative to:GitHub Copilot
- Stars
- 384
- Forks
- 16
- Open issues
- 13
- Last commit
- 29 days ago
What is it?
Minuet is an Emacs Lisp package that requests code completions from large language models while you type. It supports cloud providers including OpenAI, Claude, Gemini and Codestral, as well as OpenAI-compatible endpoints and local servers such as Ollama and llama.cpp.
It offers two completion modes: chat-style prompting for chat models, and fill-in-the-middle (FIM) completion for models that support it, such as DeepSeek, Codestral and some Ollama models. Suggestions can be shown as an overlay ghost text or picked from the minibuffer, and multi-line suggestions can be accepted one line or one word at a time.
The package also includes an experimental next-edit prediction feature, minuet-duet, which proposes rewrites of the surrounding editable region based on recent edits.
Key features
- 01Inline code completion from OpenAI, Claude, Gemini, Codestral and OpenAI-compatible providers
- 02Fill-in-the-middle completion for FIM-capable models such as DeepSeek and Ollama models
- 03Streaming responses with overlay ghost text or minibuffer selection
- 04Accept multi-line suggestions line by line or word by word
- 05Experimental next-edit prediction through the minuet-duet commands
Use cases
- Getting code suggestions in Emacs while using a cloud LLM API key
- Running completion fully locally with Ollama or llama.cpp
- Comparing different LLM providers for code completion within one editor setup
Quick start
- 1
Install minuet from ELPA or MELPA with package.el
(package-install 'minuet) - 2
Set an API key environment variable for your chosen provider, such as OPENAI_API_KEY
- 3
Configure the provider in your init file and bind keys such as M-y to minuet-complete-with-minibuffer
Things to know
- Requires Emacs 29+ compiled with native JSON support.
- You need an API key for a cloud provider or a locally running LLM server.
- The next-edit prediction (minuet-duet) feature is highly experimental.
- Previewing insertions in the buffer requires the optional consult package.
In collections
Topics
FAQ
- What is minuet-ai.el?
- An Emacs package that brings as-you-type code completion from LLMs such as OpenAI, Claude, Gemini, Ollama and llama.cpp into your editor. Minuet is an Emacs Lisp package that requests code completions from large language models while you type. It supports cloud providers including OpenAI, Claude, Gemini and Codestral, as well as OpenAI-compatible endpoints and local servers such as Ollama and llama.cpp.
- Is minuet-ai.el free to use? What license does it have?
- minuet-ai.el is open source under the GPL-3.0 license. Check the license terms before using it in commercial products.
- Is minuet-ai.el still maintained?
- Actively maintained. The last commit to minuet-ai.el was on Oct 9, 2026.
- What can I use minuet-ai.el for?
- Getting code suggestions in Emacs while using a cloud LLM API key Running completion fully locally with Ollama or llama.cpp Comparing different LLM providers for code completion within one editor setup
- How do I install minuet-ai.el?
- Install minuet from ELPA or MELPA with package.el: (package-install 'minuet) Set an API key environment variable for your chosen provider, such as OPENAI_API_KEY Configure the provider in your init file and bind keys such as M-y to minuet-complete-with-minibuffer
- Where can I get minuet-ai.el?
- The source code and installation instructions are on GitHub: https://github.com/milanglacier/minuet-ai.el
Summary generated by AI from the project's README. GitHub stats refresh daily.
Related projects
A Vim plugin that adds Copilot-style code completion, chat and AI-assisted editing, backed by a local Ollama server or OpenAI-compatible and Mistral APIs.
VS Code extension for local LLM code completion, AI chat, and an agentic coding assistant backed by llama.cpp.
Open-source AI coding agent for VS Code that works with your own models, including hosted APIs, accounts, and local Ollama or llama.cpp.
An open-source coding agent for the terminal that runs on local models via Ollama or any OpenAI-compatible API.
Open source AI coding agent that runs in VS Code, JetBrains IDEs, or the terminal, with access to 500+ models.