OpenCode

OpenCode

MIT-licensed AI coding agent, model-agnostic across 75+ providers. Runs in terminal, desktop, or IDE without Anthropic-only lock-in.

🩺 Vitals

What do these metrics mean?
  • Last active: when code was last pushed, as of our last check. The dot is green when that was recent, grey otherwise. A long gap can mean a tool is finished and stable, not only unmaintained.
  • Latest release: the most recent tagged, packaged version the maintainers published. Not every healthy project tags releases.
  • Open issues: unresolved reports and requests. A high number is normal for a popular project and is not a warning on its own.
  • Stars: how many people bookmarked the project on its forge. A rough popularity signal, not a measure of quality.

πŸ—οΈ Profile

1. The Executive Summary

What is it? OpenCode is an MIT-licensed AI coding agent that runs across terminal, desktop, and IDE. It integrates with your local Language Server Protocol (LSP) and supports 75+ model providers (including local runners like Ollama), separating the workflow into "Plan Mode" (architecture) and "Build Mode" (execution). A desktop app (beta) and extensions for VS Code, Cursor, Zed, and Windsurf extend the same agent beyond the terminal.

The Strategic Verdict:

2. The "Hidden" Costs (TCO Analysis)

Cost Component Claude Code (SaaS) OpenCode (Self-Hosted)
Model Cost Fixed / Token-based Variable (BYO Key)
Data Privacy Vendor Cloud Transit 100% Local (with Ollama)
Lock-in High (Anthropic only) Zero (Switch models)
Telemetry Hard to disable Opt-in / Transparent

3. The "Day 2" Reality Check

πŸš€ Deployment & Operations

πŸ›‘οΈ Security & Governance (Risk Assessment)

4. Market Landscape

🏒 Proprietary Incumbents

🀝 Open Source Ecosystem