OpenCode is an open source AI coding agent that lets developers interact with large language models (LLMs) in their terminal, IDE, or as a desktop application to write and debug code. It enables integration with 75+ LLM providers (including Claude, GPT, Gemini, and local models), offers multi-session management, LSP (Language Server Protocol) auto-loading, and easy sharing of sessions for collaboration and debugging. Built with privacy in mind, OpenCode does not retain user code or context data, making it ideal for privacy-sensitive environments and trusted by a large developer community.
The open-source AI coding project OpenCode alerted users to a security breach where stored API keys for external providers were exposed.
OpenCode silently patched a critical RCE flaw, leaving vulnerable users unaware of the security risk, researchers at Pillar Security warned
OpenCode is an open source AI coding agent that's become a popular alternative to Claude Code and Cursor. But hackers got into part of its online platform and stole some users’ API keys, and the AI tools it turned to for help kept refusing to look at the malicious code.
A breach affecting the OpenCode Console may lead to the exposure of API keys for Anthropic, OpenAI and Google Gemini users
OpenCode 2.0 drops its CLI-only model for a shared background service with an SDK, API, and Code Mode. Here is what changed and why it matters.
Pair OpenCode, an open-source terminal-native AI coding agent, with open weight models on Amazon Bedrock to get a secure, flexible, pay-per-use coding assistant. Learn how to configure multi-model workflows, match the right model to each task, and keep your data in your own AWS account with no infrastructure to manage.
Visit OpenCode's official website for product details and getting started.
Comprehensive guides and API references for using OpenCode.