IRIS — open-source AI coding agent (fork of OpenCode).
English | 简体中文 | 繁體中文 | 한국어 | Deutsch | Español | Français | Italiano | Dansk | 日本語 | Polski | Русский | Bosanski | العربية | Norsk | Português (Brasil) | ไทย | Türkçe | Українська | বাংলা | Ελληνικά | Tiếng Việt
# Install script
curl -fsSL https://raw.githubusercontent.com/dragonsarealive/iris-ai/dev/install | bash
# Package managers
npm i -g iris-code@latest # or bun/pnpm/yarn
bunx iris-code # run without installing
brew install dragonsarealive/tap/iris # macOS and LinuxTip
If upgrading from OpenCode, remove versions older than 0.1.x before installing.
A desktop build is also available (branding may still say OpenCode on some artifacts). Download from the releases page.
| Platform | Download |
|---|---|
| macOS (Apple Silicon) | iris-desktop-darwin-aarch64.dmg |
| macOS (Intel) | iris-desktop-darwin-x64.dmg |
| Windows | iris-desktop-windows-x64.exe |
| Linux | .deb, .rpm, or AppImage |
The install script respects the following priority order for the installation path:
$IRIS_INSTALL_DIR- Custom installation directory$XDG_BIN_DIR- XDG Base Directory Specification compliant path$HOME/bin- Standard user binary directory (if it exists or can be created)$HOME/.iris/bin- Default fallback
# Examples
IRIS_INSTALL_DIR=/usr/local/bin curl -fsSL https://raw.githubusercontent.com/dragonsarealive/iris-ai/dev/install | bash
XDG_BIN_DIR=$HOME/.local/bin curl -fsSL https://raw.githubusercontent.com/dragonsarealive/iris-ai/dev/install | bashIRIS accepts IRIS_* mirrors of legacy OPENCODE_* flags (e.g. IRIS_SERVER_PASSWORD, IRIS_EXPERIMENTAL_AGENT_TEAMS). If the OPENCODE_* variable is unset, the IRIS_* value is copied at startup. Prefer IRIS_* for new scripts.
IRIS includes two built-in agents you can switch between with the Tab key.
- build - Default, full-access agent for development work
- plan - Read-only agent for analysis and code exploration
- Denies file edits by default
- Asks permission before running bash commands
- Ideal for exploring unfamiliar codebases or planning changes
Also included is a general subagent for complex searches and multistep tasks.
This is used internally and can be invoked using @general in messages.
For configuration and usage docs, see the upstream OpenCode documentation. IRIS-specific docs are coming soon at irislab.dev.
If you're interested in contributing to IRIS, please read our contributing docs before submitting a pull request.
If you are working on a project that's related to OpenCode and is using "opencode" as part of its name, for example "opencode-dashboard" or "opencode-mobile", please add a note to your README to clarify that it is not built by the OpenCode team and is not affiliated with us in any way.
It's very similar to Claude Code in terms of capability. Here are the key differences:
- 100% open source
- Not coupled to any provider. Although we recommend the models provided through OpenCode Zen, IRIS can be used with Claude, OpenAI, Google, or even local models. As models evolve, the gaps between them will close and pricing will drop, so being provider-agnostic is important.
- Out-of-the-box LSP support
- A focus on TUI. IRIS is built with a terminal-first approach and is going to push the limits of what's possible in the terminal.
- A client/server architecture. This, for example, can allow IRIS to run on your computer while you drive it remotely from a mobile app, meaning that the TUI frontend is just one of the possible clients.
GitHub dragonsarealive/iris-ai