█

AI/TLDR

opencode

The open source AI coding agent for your terminal

GitHub★ 208kWebsiteopencode.ai
Autonomous Coding AgentsOpen source
Language
TypeScript
License
MIT
Coverage
8 stories
$curl -fsSL https://opencode.ai/install | bash

Latest news

all 8 ↓

Overview

OpenCode is an open source AI coding agent that works from your terminal. You install it as a command-line tool and use it to explore, write, and change code in your projects.

It ships with two built-in agents you switch between using the Tab key: a full-access build agent for development work, and a read-only plan agent for analysis and code exploration. A general subagent handles complex searches and multistep tasks.

Beyond the terminal, OpenCode also offers a beta desktop application for macOS, Windows, and Linux, so you can use the same agent through a graphical app.

What it does

  • Runs as a terminal-based AI coding agent you install once and use across projects
  • Built-in build agent with full access for hands-on development work
  • Read-only plan agent that denies file edits and asks before running bash commands, good for exploring unfamiliar code
  • General subagent for complex searches and multistep tasks, callable with @general in messages
  • Switch between agents instantly with the Tab key
  • Optional beta desktop app for macOS, Windows, and Linux alongside the CLI

Getting started

OpenCode installs as a command-line tool. You can use the install script, a package manager, or a platform-specific installer, then run it inside any project directory.

Install with the script

The quickest way is the official install script, which picks an install directory automatically.

bashbash
curl -fsSL https://opencode.ai/install | bash

Or install with a package manager

OpenCode is published to npm and several other package managers, so you can use the one that fits your setup.

bashbash
npm i -g opencode-ai@latest   # or bun/pnpm/yarn
brew install anomalyco/tap/opencode  # macOS and Linux
scoop install opencode               # Windows

Switch agents while you work

Once running, press Tab to switch between the build agent (full access) and the plan agent (read-only). Use @general in a message to call the general subagent for complex searches and multistep tasks.

Commands and code are distilled from the project's own documentation — always check the official repo for the latest.

When to use it

  • Writing and editing code in a project directly from the terminal with the full-access build agent
  • Exploring an unfamiliar codebase or planning changes safely with the read-only plan agent
  • Running complex searches and multistep tasks through the general subagent
  • Using the same coding agent through a desktop app on macOS, Windows, or Linux

opencode in the news

  1. 2026-09-11NOTABLERTK does not cut AI coding costs — Quesma's Terminal-Bench 2.1 run
  2. 2026-08-10NOTABLEOpenChamber 1.18.2 — agent workspace adds scheduled tasks and a live panel
  3. 2026-07-31MAJORQM — Y Combinator open-sources the multi-agent harness it runs internally
  4. 2026-07-30MAJOROpenWork — open-source Claude Cowork alternative hits 18.5K stars
  5. 2026-07-27MAJORECC 2.1.0 — Plan Canvas turns terminal agent plans into a clickable browser review
  6. 2026-07-12NOTABLEI Love LLMs, I Hate Hype — Hotz says frontier labs won't capture AI value
  7. 2026-07-12NOTABLESystima — Claude Code sends 33k tokens before your prompt, OpenCode sends 7k
  8. 2026-06-02MAJORCognition Renames Windsurf to Devin Desktop — Agent Command Center Becomes the Default IDE Surface, Devin Local Rewritten in Rust at 30% Better Token Efficiency, Agent Client Protocol Lets Claude Agent, Codex, and OpenCode Run Side-by-Side

From the AI/TLDR release feed — every item is source-verified when it ships.

How opencode compares

opencode alongside other open-source autonomous coding agents tools AI/TLDR tracks, ranked by GitHub stars.

ToolStarsWhat it does
opencode★ 208kThe open source AI coding agent for your terminal
Claude Code★ 146kAnthropic's agentic coding tool for the terminal, IDE and GitHub: it understands your codebase, executes routine tasks, explains code and handles git workflows from natural-language commands.
OpenAI Codex★ 125kOpenAI's cloud and CLI coding agent that writes features, fixes bugs, and proposes code changes across a repo, running tasks in parallel.
Gemini CLI★ 107kAn open-source command-line AI agent from Google that connects your terminal to Gemini models for reading code, editing files, running shell commands, and searching the web.
Pi★ 107kMinimal terminal coding agent harness with four built-in tools, extended through TypeScript extensions, skills and prompt templates instead of forks.
autoresearch★ 96.3kKarpathy's minimal harness that hands a coding agent a single-GPU LLM training script and lets it run fixed five-minute experiments, keeping or discarding each change on its own.
OpenHands★ 88.4kAn open-source AI software-development agent that plans tasks, edits files, runs commands, and tests code, usable from a terminal CLI, a local web GUI, or a Python SDK.
Orca★ 71.8kOpen-source desktop workspace that runs Claude Code, Codex, OpenCode and other CLI coding agents in parallel, each in its own git worktree, with a mobile companion app.