butterfish-shell

butterfish-shell

Butterfish Shell is an open-source CLI tool that wraps your existing shell (bash/zsh) and adds integrated ChatGPT-style LLM prompting, autosuggestions, and an optional agent (Goal Mode) so you can ask for commands, debug failures, and get contextual help directly in the terminal.

butterfish-shell is developer tools software teams evaluate for developer tools. Use this page to review pricing, integration signals, and the best alternatives before you commit.

Freemium Enterprise
#119 in Developer Tools (119 tools)
Added 0 year ago
Data reviewed Jul 16, 2026

Profile facts come from the vendor source. AiMatch labels unknown pricing or API details instead of estimating them.

Review official source →

Quick Overview

Best for: Developer Tools

What it does

Developer Tools software for decision-makers comparing workflow fit and alternatives.

Best fit

Developer Tools

Pricing snapshot

Freemium from Free (MIT license)

Next step

Compare butterfish-shell with similar tools before you shortlist it.

Compare this tool before you shortlist it

Review alternatives, pricing posture, and workflow fit side by side.

butterfish-shell

Butterfish Shell is a shell wrapper that provides integrated LLM prompting and autosuggestions inside your existing terminal (bash or zsh) on macOS and Linux. By starting a command with a capital letter you send a prompt to an OpenAI-compatible model; the LLM receives recent shell history and output so you can ask contextual questions like why a command failed or request a command to accomplish a task. It also includes Goal Mode (agents that propose or optionally execute commands), CLI utilities for summarization, embeddings-based indexing/search, and a Neovim plugin for LLM-driven edits. Butterfish is open source (MIT) and stores configurable prompt wrappers and auth tokens in the user's configuration directory.

AI-powered command-line tool for shell prompting and autocompletion.

Own this listing?

Claim this page for a one-time $29 to add pricing, features, screenshots, verified owner details, and a clearly labeled 30-day category position after the profile is live.

Claim this listing for $29

Key Features

Shell wrapper for bash and zsh

Runs a wrapped instance of your existing shell (defaults to zsh on macOS), intercepts IO and buffers input/output to provide contextual LLM prompting without altering typical shell workflows.

Prompt by capitalized commands

Start a command with a capital letter to send it as a ChatGPT-style prompt; the AI sees recent shell history and output so you can ask contextual questions and iterate on answers.

Goal Mode (agent)

Start a command with ! to let Butterfish propose commands to achieve a goal and with !! to allow unsafe execution without confirmation; the agent can iterate on failures and request feedback.

GPT autosuggest

Provides command autosuggestions (Copilot-like) based on shell history and LLM outputs, which can be applied with Tab; autosuggest model and timeout are configurable.

Configurable and transparent prompts

Prompt wrappers are visible and editable at ~/.config/butterfish/prompts.yaml; verbose mode prints raw API requests/responses and logs to a temp file.

Model & provider flexibility

Defaults to OpenAI but can target any OpenAI-compatible API via --base-url (-u), and the manual/ autosuggest models are configurable with flags like -m and -a.

CLI utilities (summarize, index, gencmd, etc.)

Includes commands to summarize files, generate shell commands from prompts (gencmd), manage embeddings and index local files for semantic search (index, indexsearch, indexquestion).

Neovim plugin

butterfish.nvim enables LLM prompting from inside Neovim to rewrite code blocks and perform in-editor LLM tasks.

Installation options

Install via Homebrew (brew install bakks/bakks/butterfish) or go install; first run prompts for an OpenAI API key and stores it at ~/.config/butterfish/butterfish.env.

Verbose logging and debugging

Verbose flags (-v, -vv, -L) expose full LLM prompts and responses and may write logs to /var/tmp/butterfish.log for inspection.

Pricing

Free Tier Available

Butterfish itself is open source and free to use under the MIT license. However, using LLM features requires an OpenAI API key and may incur charges from OpenAI (the page notes you will need a subscription or pay for API use if you do not have free credits).

Open Source

Free (MIT license)
  • Complete Butterfish source and CLI available under the MIT license
  • Installable via Homebrew or go install

Use Cases

Generate shell commands

Ask the LLM for a command to accomplish a task (e.g., find files, install deps) and receive suggested commands that include context from recent history.

Debug failing commands

Ask 'Why did that command fail?' and the LLM, with access to shell output, will explain failures and suggest corrected commands.

Agentic task execution (Goal Mode)

Use Goal Mode to have the agent propose and iterate on commands to reach a stated goal, optionally allowing unsafe execution with !!.

Code/file summarization and search

Use the summarize and embeddings-based index/indexsearch/indexquestion commands to semantically summarize files and query local codebases.

Autocomplete and command suggestions

Receive Copilot-style autosuggestions in the terminal based on prior commands and LLM outputs, applied with Tab.

LLM-driven edits in Neovim

Use the butterfish.nvim plugin to prompt LLMs from within Neovim for code transformations and rewrites.

General ChatGPT-style prompts

Because it exposes a ChatGPT interface, you can also ask general questions (e.g., recipes) directly from the terminal.

Integrations

OpenAI (and OpenAI-compatible APIs)

Uses OpenAI models by default and accepts a --base-url (-u) for any OpenAI-compatible API including local model servers.

Neovim (butterfish.nvim)

Plugin for prompting LLMs and performing edits from within Neovim.

Homebrew / Go toolchain

Distributed via Homebrew formula and as a Go installable binary.

Benefits

High-context AI assistance directly in the terminal without copy/paste by including shell history and outputs in prompts.
Speeds up command-line workflows with autosuggested commands and an ability to iterate on LLM responses conversationally.
Transparent and editable prompts let users control model instructions and behavior instead of hidden wrappers.
Flexible model/provider support for using OpenAI or any compatible local/remote API endpoint.
Open-source MIT-licensed project that can be audited, extended, and integrated into developer workflows.

Limitations

Goal Mode is experimental and "hit or miss"; success varies with task complexity and guidance.
Agent may struggle with manipulating very large text/code files and is biased toward specific command versions or flags.
History and large command outputs are truncated to fit model token windows (per-token limits and truncation rules apply).
Unsafe Goal Mode (!!) can execute commands without confirmation and is potentially dangerous; use with caution.

Frequently Asked Questions

Which platforms and shells does Butterfish support?
Butterfish works on macOS and Linux and wraps common shells such as bash and zsh (zsh is the default on macOS).
How do I install Butterfish?
Install via Homebrew on macOS: brew install bakks/bakks/butterfish, or install from source with go install github.com/bakks/butterfish/cmd/butterfish@latest.
Where is my OpenAI API key stored?
The OpenAI token is written to ~/.config/butterfish/butterfish.env (e.g., OPENAI_TOKEN=sk-foobar).
Is Butterfish free?
Butterfish is open source under the MIT license and free to use; however, LLM usage requires an OpenAI API key and may incur charges from OpenAI if you lack free credits.

Getting Started

  1. 1 Install Butterfish: either brew install bakks/bakks/butterfish (macOS) or go install github.com/bakks/butterfish/cmd/butterfish@latest.
  2. 2 Run the shell wrapper: start it with butterfish shell (or alias bf="butterfish" to shorten).
  3. 3 Provide OpenAI credentials when prompted: paste your OpenAI API key; it's saved to ~/.config/butterfish/butterfish.env.
  4. 4 Optionally configure model, autosuggest, prompts, and verbose logging via flags and by editing ~/.config/butterfish/prompts.yaml.
  5. 5 Use the command reference (butterfish shell --help and butterfish --help) to explore features like Goal Mode, autosuggest, and the CLI utilities.

Support

GitHub (issues/repo)

Project and support available at https://github.com/bakks/butterfish for issues, feedback, and source code.

Docs / CLI help

In-tool help via butterfish --help and butterfish shell --help; verbose logging (-v, -vv) and logs are written to /var/tmp/butterfish.log.

API

Available: No

Compare butterfish-shell with similar tools

See how it stacks up against alternatives

Freemium
Copperhead

Copperhead

Copperhead is an open-source AI engineering platform and CLI that helps hardware teams design, verify, and ship printed circuit boards by editing KiCad files, running KiCad checks (ERC/DRC), and producing gerbers, firmware, and documentation in a gated, auditable pipeline.

Developer Tools
Top source
Free
Moadim.io

Moadim.io

Moadim is an open-source loop engine that schedules and runs AI agents (Claude, Codex, Hermes, NanoClaw, Pi) against a repository or task on a recurring schedule in isolated workbenches with watchdogs and built-in HTTP/MCP interfaces.

Developer Tools
Top source
Free
Docs.dev Your Own Hosted Docs Platform in Minutes

Docs.dev Your Own Hosted Docs Platform in Minutes

Docs.dev is a deployable documentation template that runs as a Cloudflare Worker in your account, using your GitHub repo as the source of truth and agent-powered drafting (e.g., Claude Code or Codex) to generate reviewable docs branches that your team publishes via commit.

Developer Tools
Botbin.io

Botbin.io

Botbin.io is a pastebin-style hosting service for AI agent artifacts that lets agents publish HTML artifacts (landing pages, interactive dashboards, rich reports) and share links instead of raw HTML in chat or terminals.

Developer Tools
Contact for pricing
statuslin.es

statuslin.es

statuslin.es is a community gallery of Claude Code status lines—copyable, previewed scripts and themes for terminal/status-bar displays that show Claude model stats (tokens, cost, limits), git info, and other runtime metrics.

Developer Tools
Free
Bullet · Fast, by design.

Bullet · Fast, by design.

Bullet is a fast coding agent and developer tool that routes, searches, and executes code-focused tasks with a tight loop to minimize latency — offered as a macOS download and currently available in private beta.

Developer Tools
Contact for pricing
Waku

Waku

Waku is a native macOS app that consolidates coding agents and their activity into a single local timeline—sessions, transcripts, tool activity, and checkpoints—while running entirely on your machine with a GPU-accelerated native UI.

Developer Tools
Free
Codify

Codify

Codify is a cross-platform tool that declares and automates developer environments as code—via a CLI and dashboard—so teams and individuals can standardize, reproduce, and apply development setups on macOS, Linux, and WSL.

Developer Tools

Premium Alternatives

Paid
OTP Inspired actor supervisor based full stack templates

OTP Inspired actor supervisor based full stack templates

ShipStacks provides production-grade, OTP-inspired full-stack SaaS templates that include supervisors/actor patterns, auth, payments, uploads, AI chat and agent playbooks, and Docker-ready deployment in multiple languages and frameworks.

Developer Tools
Paid
1endpoint

1endpoint

1endpoint is a low-cost AI model gateway that provides a single API to run many models with transparent, usage-based token pricing, prompt caching, and tools for high-volume workloads.

Developer Tools
Enterprise-ready
Paid
wrapfast

wrapfast

WrapFast is a SwiftUI boilerplate and starter kit for building iOS apps and AI wrappers quickly. It includes an Xcode SwiftUI project, a Node.js Express backend to secure AI API keys, AI integrations (OpenAI & Anthropic), monetization flows, cloud database support, documentation, and a Discord community aimed at indie makers and solo founders.

Developer Tools
Enterprise-ready
Paid
runpod

runpod

Runpod is an AI Developer Cloud that provides on-demand GPU infrastructure—Pods, Serverless endpoints, and multi-node Clusters—enabling teams to experiment, train, fine-tune, deploy, and scale AI workloads across 31 global regions with support for 30+ GPU SKUs.

Developer Tools
Enterprise-ready
Paid
ratio1

ratio1

Ratio1 is a blockchain-powered, decentralized AI operating system and edge/cloud computing platform that enables rapid development and deployment of AI apps, a tokenized GPU compute marketplace, and node-based infrastructure via Node Deeds and the $R1 utility token.

Developer Tools
Enterprise-ready
Paid
startkit-ai

startkit-ai

StartKit.AI is a purchasable, production-focused Node.js boilerplate that provides a complete SaaS app and pre-built AI modules to help developers ship AI startups quickly, including demos for chat, PDF, images, RAG, authentication, payments, and integrations with AI providers.

Developer Tools
Enterprise-ready
Paid
builderkit

builderkit

BuilderKit is a modular Next.js AI boilerplate and starter kit that provides deployable TypeScript code, pre-built AI apps, UI components, auth, payments, and integrations to accelerate building and shipping AI SaaS products.

Developer Tools
Paid
Finetunefast

Finetunefast

FinetuneFast provides finetuning boilerplates, inference templates, and deployment tooling to accelerate building and shipping ML models (text-to-image, LLMs, RAG, TTS) — aimed at developers, indie makers and businesses who want production-ready examples and fast time-to-deploy.

Developer Tools
Enterprise-ready

Explore Related Categories

Explore by Outcome