Realiserad/fish-ai

Supercharge your command line with LLMs and get shell scripting assistance in Fish. 💪

What it solves

fish-ai is a plugin for the Fish shell that integrates AI-powered command-line assistance. It reduces the need to manually search for complex shell commands, read manpages, or fix typos in commands that failed to execute.

How it works

The plugin connects to a variety of language models (LLMs) via API or self-hosted instances. It captures the current command-line buffer, OS information, and optionally command history or file contents, and sends them to the LLM to generate responses. It uses two primary keyboard shortcuts to trigger these actions: Ctrl + P for transformations and Ctrl + Space for completions and fixes.

Who it’s for

Users of the Fish shell who want to automate the generation of shell commands from natural language comments, get AI-driven autocompletions, or quickly fix broken commands without leaving the terminal.

Highlights

  • Bidirectional Transformation: Converts natural language comments into shell commands and vice versa.
  • AI-Driven Autocomplete: Uses a built-in fuzzy finder (fzf) to suggest command completions.
  • Command Fixes: Suggests corrections for commands that fail to execute.
  • Flexible Provider Support: Compatible with Anthropic, Azure OpenAI, Google Gemini, Groq, Cohere, DeepSeek, OpenRouter, and self-hosted models (e.g., via Ollama).
  • Privacy-Focused: Includes a redaction system to remove passwords, API keys, and private keys from prompts before they are sent to the LLM.
  • Lightweight: Open source and approximately 2000 lines of code for easy auditing.

Related

  • Project
    VictorTaelin/AI-scripts

    A collection of AI-powered command-line tools for coding workflows, including terminal chat, automated code editing, and context-aware refactoring.

  • Project
    yaroslavyaroslav/OpenAI-sublime-text

    A Sublime Text plugin that adds AI‑powered chat to the editor, supporting OpenAI, Claude, Gemini and any OpenAI‑compatible endpoint. It offers inline phantom answers, project‑specific assistants, context‑file inclusion, streaming, and full configuration via settings.

  • Project
    gergap/vim-ollama

    A Vim plugin that adds local, privacy-preserving AI code completion, chat, and automated editing using Ollama and other LLM backends.

  • Project
    theJayTea/WritingTools

    Writing Tools is a free, open‑source desktop app for Windows, Linux and macOS that lets you invoke an LLM anywhere on your computer with a hot‑key. It can proofread, rewrite, change tone, translate, summarise web pages or YouTube transcripts, and even chat with the model. You can use cloud APIs (Gemini, OpenAI, Anthropic, etc.) or run local models via Ollama, llama.cpp or Apple‑silicon MLX. The app is privacy‑focused (no telemetry, local storage of API keys) and licensed under GPL‑v3.

  • Project
    di-sukharev/opencommit

    OpenCommit is a Node‑JS CLI that uses LLMs (OpenAI, Anthropic, Ollama, etc.) to auto‑generate conventional, emoji‑enhanced Git commit messages from staged changes. It supports global and per‑repo configuration, multiple providers, local model servers, a Git hook, and a GitHub Action for automatic commit‑message improvement.