
Crush is a terminal AI coding assistant for developers who want to work with their code and tools through a model they choose. The app runs on your machine, while model requests go to your selected local backend or cloud provider. It supports macOS, Linux, Windows (PowerShell and WSL), Android, FreeBSD, OpenBSD and NetBSD.
Local model connections include Ollama, llama.cpp, LM Studio, oMLX and LiteLLM, with automatic model discovery for those providers. For cloud models, Crush connects to Anthropic, OpenAI, Gemini and OpenRouter, among others. Charm also offers Hyper, a hosted provider for Crush. Custom providers can use OpenAI-compatible or Anthropic-compatible APIs, so you're not limited to the built-in provider choices.
You can switch models during a session without losing its context, and keep separate work sessions within the same project. Crush uses Language Server Protocol (LSP) integrations to add code context and supports Model Context Protocol (MCP) connections for additional tools. These capabilities suit developers who want a terminal agent that fits an existing workflow and lets them change model backends without abandoning a conversation.
Crush includes built-in color themes with live previews and editing. It records pseudonymous usage metadata tied to a device-specific hash, but doesn't collect prompts or responses through those metrics. You can opt out of metrics collection, and Crush respects DO_NOT_TRACK.
Claim this page with an email at charm.land. Crush gets the verified badge, and you can upgrade the listing to be featured on localhosted. Proud to be listed? Put our badge on your site.
Want more people to find Crush?Promote it
Something wrong or outdated on this page?
42Updated 12 hours ago
macOS · Windows · Linux · Docker#Agent Skills#Code execution#Distributed execution
Code Buddy is an AI coding assistant for developers who want a terminal agent running on their own machine, with a choice of local or cloud models. It reads repositories, edits code and runs commands on Linux, macOS and Windows. Ollama keeps model inference local without an API key or account; cloud providers send model requests off the machine. Routing includes automatic provider failover.
4.4KUpdated 19 hours agoMIT
macOS · Windows · Linux · Web · JetBrains#Agent Client Protocol#Code execution#Git integration
68.5KUpdated 3 days agoApache-2.0
macOS · Windows · Linux#Agent Client Protocol#Code execution#Human approval
110.7KUpdated 3 hours agoMIT
macOS · Windows · Linux · Docker#Agent Skills#Code execution#MCP
28.2KUpdated 1 day agoApache-2.0
macOS · Windows · Linux · Web · VS Code · JetBrains#Code execution#Git integration#MCP
49.3KUpdated 4 months agoApache-2.0
macOS · Windows · Linux#Code execution#Git integration#Multimodal input
gptme is a self-hosted AI agent that works directly in your terminal, with access to your files and installed tools. It's for developers who want a coding assistant in their own environment, and people who want an agent for data analysis or other knowledge work. The software is free under the MIT license and doesn't require a gptme account.
Open Interpreter is a terminal coding assistant built around open-weight models, with model-specific behavior for Kimi, Qwen and DeepSeek. It's a fork of OpenAI's Codex for developers who want to choose their model provider while keeping a familiar agent interface. The project uses the Apache 2.0 license.
Pi is a terminal-based coding assistant for developers who want to shape the agent around their own workflow. Its core stays small, while extensions can change its tools, commands and terminal interface. It's open source under the MIT license.
Qwen Code is an Apache 2.0 licensed AI coding agent for developers who want help working through a codebase, changing code and checking the result. It runs on macOS, Windows and Linux, with a terminal interface and a desktop app. It builds on Google Gemini CLI and has developed into an agent that can use Qwen models alongside other model providers.
Aider is an Apache 2.0 open-source coding assistant for developers who work in a terminal and keep their projects in Git. It can help start a project or make changes to an existing codebase. You can use local LLMs or connect to cloud models from providers including Anthropic, DeepSeek and OpenAI.