aicoolies logo
Crush logo

Crush

Glamorous agentic coding for the terminal by Charm

Share
open-sourceOpen Source
Visit Website →

LSP-enhanced terminal coding agent from Charmbracelet with the broadest cross-platform support including Android. Features mid-session model switching and MCP extensibility for custom tool integration. Combines the elegance of Charmbracelet's TUI toolkit with practical coding assistance, offering a polished terminal experience for developers on any platform.

We have a review for this tool

A detailed review by the aicoolies team — click to read

Crush is a glamorous AI coding agent that lives in your terminal, developed by the Charm team as an evolution of the OpenCode project. It provides a rich TUI and CLI for interacting with AI models to perform code generation, debugging, file operations, and development automation directly from the command line. Current public sources position it as free BYOK software, but the repository uses FSL-1.1-MIT, a source-available license with a future MIT conversion path rather than a plain permissive open-source license.

Crush differentiates itself through its integration with the Charm ecosystem of terminal tools, bringing polished TUI aesthetics powered by Bubble Tea and Lip Gloss to the AI coding experience. It supports multiple AI providers including OpenAI, Anthropic, Google Gemini, Groq, AWS Bedrock, Azure, and any OpenAI or Anthropic-compatible endpoint, allowing developers to swap between models without losing session context. The tool leverages your existing shell environment, directory layout, and Git history as the AI workspace, enabling contextual understanding without manual configuration.

Crush targets developers who prefer terminal-centric workflows and want an aesthetically pleasing, model-agnostic AI coding assistant that integrates with their existing command-line tools. It is especially appealing to users of Charm's broader terminal tool ecosystem and developers who value the flexibility of choosing their own AI provider rather than being locked into a single model vendor. Crush works across macOS, Linux, Windows/WSL, Android, FreeBSD, OpenBSD, and NetBSD, and its BYOK model makes it cost-effective for developers who already have API access to preferred models.

Pricing

Free to run with your own model/API keys; no hosted Crush subscription documented. Source is under FSL-1.1-MIT, so treat it as source-available/future-MIT rather than plain permissive open source.

Platforms

macOS, Linux, Windows/WSL, Android, FreeBSD, OpenBSD, and NetBSD terminals; supports OpenAI/Anthropic-compatible APIs, MCP servers, and LSP-aware code context.

Categories

Tags

Use Cases

Alternatives

OpenCode logo

OpenCode

Top Pick

Open-source AI coding agent for the terminal

Open-source terminal-based AI coding agent built in Go by the SST team, with a rich TUI (Bubble Tea) supporting 75+ model providers including OpenAI, Anthropic, Gemini, Bedrock, Groq, and OpenRouter. Features vim-like editing, persistent SQLite sessions, and LSP integration for 40+ languages. Fully free with no vendor lock-in, it has rapidly grown to 95k+ GitHub stars.

open-source
goose ai

Goose

Open-source extensible AI agent by Block

Autonomous coding agent from Block (Square) that works with any LLM through MCP-first extensibility. Apache 2.0 licensed with 47K+ GitHub stars and a Linux Foundation AAIF founding project. Designed for terminal-based workflows with deep tool integration, making it a strong open-source option for developers who want agent-assisted coding without vendor lock-in.

open-sourceOpen Source
pi dev code

Pi

Top Pick

Minimal terminal coding harness

Pi Coding Agent is an MIT-licensed Node.js CLI from earendil-works for building and running coding agents in a local terminal. The current package describes a read/bash/edit/write toolset and session management, while the repo positions Pi as a unified LLM API, agent loop, TUI, and coding-agent CLI. It is best framed as a lean, self-extensible BYO-model toolkit rather than a managed IDE.

open-sourceOpen Source
Claude Code logo

Claude Code

Top Pick

Anthropic's agentic coding CLI

Anthropic's agentic CLI coding tool that delegates complex tasks to Claude directly from the terminal. Understands entire codebases via automatic context gathering, edits multiple files, runs shell commands, and manages Git workflows autonomously. Supports CLAUDE.md for persistent project instructions, integrates with VS Code and JetBrains, and uses Claude Opus/Sonnet with extended thinking for complex architectural decisions. Built for terminal-first developers.

paidOpen Source

Related Tools

Ghostty logo

Ghostty

Top Pick

Fast, native terminal emulator

GPU-accelerated terminal emulator written in Zig by Mitchell Hashimoto (HashiCorp co-founder). Native UI rendering on macOS and Linux. Supports ligatures, true color, Kitty graphics protocol, and splits/tabs. Configurable via a simple key-value file with sensible defaults. Open-source with 20K+ GitHub stars and a focus on correctness, speed, and minimal resource usage. Growing as a modern alternative to iTerm2, Alacritty, and WezTerm.

open-sourceOpen Source
Cursor logo

Cursor

Top Pick

The AI-first code editor

AI-first code editor built as a VS Code fork that deeply integrates LLMs into every part of the development workflow. Features Tab autocomplete with multi-line predictions, Cmd+K inline editing, AI chat with full codebase awareness, and Agent mode for autonomous multi-file edits with terminal execution. Supports GPT-4, Claude, and more with automatic context from project files and docs. Includes privacy mode for SOC 2 compliance. The leading AI-native IDE with 100K+ paying users.

freemiumTelemetry
Hermes Agent logo

Hermes Agent

Top Pick

Open-source AI agent framework with persistent memory, reusable skills, tools, and messaging gateways

Hermes Agent is an open-source AI agent framework with persistent memory, reusable skills, 40+ tools, cron jobs, and messaging gateways.

open-sourceOpen Source
Codex logo

Codex

Top Pick

OpenAI coding agent for app, editor, terminal, and cloud work

Codex is OpenAI's coding agent for software development across the Codex app, editor, terminal, and cloud tasks. It helps write, review, debug, refactor, and automate code, with ChatGPT plan access for managed surfaces and API-key usage for CLI, SDK, and IDE workflows. The open-source CLI and SDK support local repository work, while cloud features add GitHub review, Slack/Linear integrations, worktrees, skills, MCP, and automations.

freemiumOpen Source

Accomplish Coworker

Open-source desktop AI coworker for browsing and code execution.

Accomplish Coworker is an MIT-licensed open-source AI coworker that runs on the desktop, combining computer-use style browsing with code execution so agents can research, implement, run, and debug workflows in one local environment.

open-sourceOpen SourceTelemetry
OpenUI logo

OpenUI

Open-source UI generation from natural-language prompts

OpenUI is an Apache-2.0 design-to-code tool from W&B that turns natural-language interface prompts into live HTML previews and frontend code. Teams can run it locally or with Docker, connect OpenAI, Groq, LiteLLM-compatible providers, or Ollama, and export generated UI toward React, Svelte, Web Components, and related workflows. It fits rapid UI mockups where developers want editable code instead of screenshots.

open-sourceOpen SourceTelemetry

Comparisons