OpenCode

Anomaly (open source) Terminal agents Free way to start

Open-source coding agent for terminal, desktop, and IDE. Free models included, or log in with an existing ChatGPT Plus/Pro or GitHub Copilot account.

Capabilities

Read local project	Supported Works in your project.
Edit files	Supported Edits files directly.
Run commands	Supported Runs commands with approval.
Image input	Conditional Depends on the connected model’s vision support.
Long autonomous tasks	Conditional Agent loops supported; limits depend on the model/account you use.

Working experience

Code quality Good

Works on its own Good

Speed Good

Stability Conditional

Editorial assessment based on official documentation and publicly known behavior — not a field-test score. Sources and check date on this page.

🧪 ResetDog field notes

No completed field test for this tool yet. The capability descriptions on this page come from official documentation.

🎯 Good for

Change pages / UI · Fix a bug · · Continue from a screenshot · Let an agent run · Quick code question · Hand off my project

🧭 How you use it

In the terminal · Desktop app · Inside your IDE
Works on: macOS / Windows / Linux

💰 Cost & quota

Freemium · Free / open source

🆓 Free / trial access

The agent itself is free and open source; free models are included, and paid models work via your own keys or accounts. Logging in with a ChatGPT Plus/Pro or GitHub Copilot account uses those subscriptions.

🏷️ Pricing notes

Software free. Optional “Zen” model packs and any BYOK provider billed separately by that provider.

🚀 Setup

`curl -fsSL https://opencode.ai/v2/install | bash` (or npm/brew), then log in with a provider account or API key.

⚠️ Main limitations

Quality depends heavily on which model/account you connect.
Project is moving fast — verify current install docs.

🔒 Privacy & data

Open-source client; your prompts go to whichever provider you authenticate. Official privacy policy ↗

📚 Sources

https://opencode.ai/

🧾 What is official vs ours

Facts like pricing, plans, and capability limits come from the official pages linked below, checked on the date shown. Summaries and task-fit notes are written by ResetDog. Anything marked “conditional” or “unknown” was not fully confirmed — treat it as unverified.