# Introduction
OpenCode plugins are add-ons that extend the capabilities of the OpenCode AI code agent. They provide additional tools, integrations, and workflow enhancements such as persistent memory, end-to-end access, citation web searches, reusable capabilities, and analytics. These plugins help developers customize OpenCode for more advanced coding, research, and automated workflows.
In this article, we review seven OpenCode plugins that stand out for their usability, features, and growing community adoption. Together, they show how plugins can make an OpenCode agent more powerful, flexible, and useful for everyday use.
# 1. Oh My Openagent
Widely considered the most prominent plugin in the OpenCode ecosystem, oh-my-openagent stands out for its scope. It adds backend agents, a pre-built language server protocol (LSP), an abstract syntax tree (AST), and Model Context Protocol (MCP) tools, selected agent packages, and Claude code compatibility, making it one of the most complete enhancements available for advanced OpenCode workflows.
Suitable for: An all-in-one power pack
GitHub:
# 2. Opencode Antigravity Auth
Designed for authentication, this plugin enables OpenCode to communicate with Antigravity via OAuth. That allows users to sign in with Google credentials and unlock access to models like Gemini 3.1 Pro and Claude Opus 4.6 Thinking directly within OpenCode.
Suitable for: It enables Antigravity and Google-based model access to OpenCode
GitHub:
# 3. Opencode Supermemory
Designed for persistence, opencode-supermemory enables the agent to store what users share across sessions and even across projects. It's one of the most useful additions for anyone who wants OpenCode to behave less like a stateless assistant and more like a continuous contributor.
Suitable for: Continuous memory across sessions and projects
GitHub:
# 4. Opencode Pty
Focused on developer workflow, this plugin brings functional pseudoterminal (PTY) support to OpenCode. It allows the agent to run background processes, send trace input, and return later to read the output, making it more capable than relying solely on single shell commands.
Suitable for: Long-running background processes and interactive terminal sessions
GitHub:
# 5. Cited Opencode Websearch
For serious research work, this plugin adds a web search tool with citation support within OpenCode. Compatible with the repository, it can generate in-line citations and lists of sources, while supporting Google, OpenAI, or OpenRouter-based search configurations depending on the setup.
Suitable for: Research goes by citations
GitHub:
# 6. Opencode Wakatime
Aimed at visibility and measurement, opencode-wakatime tracks AI-assisted coding activity, time spent, and file changes. It connects of Timea common dashboard workflow, giving teams and individuals a clear view of how OpenCode is being used.
Suitable for: Tracking AI-assisted coding work
GitHub:
# 7. Opencode Agent Capabilities
Focused on reusability, this plugin adds support for finding and loading agent capabilities from project folders, user directories, and Claude-compatible locations. It is especially useful for teams looking for portable skill libraries and a smooth Claude-style workflow within OpenCode.
Suitable for: Reloading skills and workflows with Claude
GitHub:
# Final thoughts
OpenCode plugins are what make the platform more than just a coding agent. What I find most interesting is how quickly they can extend OpenCode into something that feels more personal, capable, and better suited to a real developer's workflow.
Whether the goal is better memory, robust research, getting free access to Gemini models, rich terminal control, or reusable capabilities, these plugins show how flexible the ecosystem can be. For anyone starting out, I think the best approach is to start with plugins that solve the biggest day-to-day pain points first, and then build from there as your workflow gets more advanced.
Abid Ali Awan (@1abidiawan) is a data science expert with a passion for building machine learning models. Currently, he specializes in content creation and technical blogging 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 idea is to create an AI product using a graph neural network for students with mental illness.
