AI コーディングを強化する 7 つの OpenCode プラグイン

# Introduction

**

OpenCode** plugins are add-ons that extend the capabilities of the OpenCode AI coding agent. They provide extra tools, integrations, and workflow enhancements such as persistent memory, terminal access, cited web search, reusable skills, and analytics. These plugins help developers customize OpenCode for more advanced coding, research, and automation workflows.

In this article, we review seven OpenCode plugins that stand out for their usefulness, features, and growing adoption in the community. Together, they show how plugins can make the OpenCode agent more powerful, flexible, and practical for everyday use.

# 1. Oh My Openagent

**

Widely regarded as the most prominent plugin in the OpenCode ecosystem, oh-my-openagent stands out for its breadth. It adds background agents, pre-built language server protocol (LSP), abstract syntax tree (AST), and Model Context Protocol (MCP) tools, curated agent packs, and Claude Code compatibility, making it one of the most complete upgrades available for advanced OpenCode workflows.

Best for:** An all-in-one power pack

GitHub: https://github.com/ohmyopencode/oh-my-opencode

# 2. Opencode Antigravity Auth

**

Built for authentication, this plugin enables OpenCode to connect with Antigravity through OAuth. That allows users to sign in with Google credentials and unlock access to models such as Gemini 3.1 Pro and Claude Opus 4.6 Thinking directly inside OpenCode.

Best for:** Enabling Antigravity and Google-backed model access in OpenCode

GitHub: https://github.com/NoeFabris/opencode-antigravity-auth

# 3. Opencode Supermemory

**

Designed around persistence, opencode-supermemory gives the agent the ability to retain what users share across sessions and even across projects. It is one of the most practical additions for anyone who wants OpenCode to behave less like a stateless assistant and more like a continuing collaborator.

Best for:** Persistent memory across sessions and projects

GitHub: https://github.com/supermemoryai/opencode-supermemory

# 4. Opencode Pty

**

Focused on developer workflow, this plugin brings interactive pseudoterminal (PTY) support to OpenCode. It allows the agent to launch background processes, send follow-up input, and return later to read output, which makes it far more capable than relying only on one-off shell commands.

Best for:** Long-running background processes and interactive terminal sessions

GitHub: https://github.com/shekohex/opencode-pty

# 5. Opencode Websearch Cited

**

For research-heavy work, this plugin adds a web search tool with citation support inside OpenCode. According to the repository, it can generate inline citations and source lists, while supporting Google, OpenAI, or OpenRouter-backed search configurations depending on setup.

Best for:** Research workflows with citations

GitHub: https://github.com/ghoulr/opencode-websearch-cited

# 6. Opencode Wakatime

**

Aimed at visibility and measurement, opencode-wakatime tracks AI-assisted coding activity, time spent, and file changes. It plugs into WakaTime**'s familiar dashboard workflow, giving teams and individuals a clearer view of how OpenCode is being used.

Best for: Tracking AI-assisted coding activity

GitHub: https://github.com/angristan/opencode-wakatime

# 7. Opencode Agent Skills

**

Centered on reusability, this plugin adds support for discovering and loading agent skills from project folders, user directories, and Claude-compatible locations. It is especially useful for teams that want portable skill libraries and smoother Claude-style skill workflows within OpenCode.

Best for:** Reusable skill loading and Claude-compatible skill workflows

GitHub: https://github.com/joshuadavidthomas/opencode-agent-skills

# Final Thoughts

**

OpenCode plugins are what make the platform much more than just a coding agent. What I find most interesting is how quickly they can expand OpenCode into something that feels more personal, more capable, and much better suited to real developer workflows.

Whether the goal is better memory, stronger research, getting free access to Gemini models, richer terminal control, or reusable skills, these plugins show how flexible the ecosystem is becoming. For anyone getting started, I think the best approach is to begin with the plugins that solve the biggest day-to-day pain points first, then build from there as your workflow becomes more advanced.

Abid Ali Awan** (@1abidaliawan) is a certified data scientist professional who loves building machine learning models. Currently, he is focusing on content creation and writing technical blogs on machine learning and data science technologies. Abid holds a Master's degree in technology management and a bachelor's degree in telecommunication engineering. His vision is to build an AI product using a graph neural network for students struggling with mental illness.