Plugins

Automatically inject Helicone session headers into LLM requests for request grouping in Helicone's dashboard

Auto-inject TypeScript and Svelte types into file reads with lookup tools, token budget management, and import resolution

Use your ChatGPT Plus/Pro subscription instead of API credits with OAuth authentication for OpenAI's Codex backend

Use your existing Gemini plan instead of API billing with Google OAuth authentication

Google Antigravity OAuth Plugin with multi-account load balancing, Google Search tool, cross-model conversations, and interleaved thinking support

Optimize token usage by intelligently pruning obsolete tool outputs from conversation history with deduplication, prune tool, and on-idle analysis

Add native websearch support with inline citations and source lists for supported providers using Google grounded style

Track OpenCode usage with WakaTime including automatic CLI management, detailed file tracking, and AI coding metrics

Clean up markdown tables produced by LLMs with concealment mode support, alignment handling, and code block preservation

Battery-included plugin with background agents, pre-built LSP/AST/MCP tools, curated agents with proper models, and Claude Code compatibility layer

OpenCode plugin for enhanced LM Studio support with auto-detection and dynamic model discovery and auto-loading.

Use cursor-agent inside OpenCode (CLI-first Cursor). This plugin is for people who pay for Cursor (or have it paid for them) and want to use it from OpenCode instead of the Cursor UI.

Speckit Chain Plugin for Opencode automates the Speckit commands chain and auto-answers clarification prompts.

Purges all emojis from agent outputs! -- Covers agent text chat, markdown writes & newString edits.

A Model Context Protocol (MCP) server implementation designed for AI agents to monitor and interact with Linux servers (Ubuntu, CentOS, RedHat, etc.). This server provides comprehensive system information including CPU, memory, disk, network, and process data through both MCP protocol and HTTP REST API, enabling AI agents to perform remote system monitoring and management tasks.

A Model Context Protocol (MCP) local + server implementation designed for AI agents to monitor and interact with Linux servers (Ubuntu, CentOS, RedHat, etc.). This server provides comprehensive system information including CPU, memory, disk, network, and process data through both MCP protocol and HTTP REST API, enabling AI agents to perform remote system monitoring and management tasks.

Queue messages while OpenCode is thinking. Instead of interrupting the model mid-response, your follow-up messages wait in line and get sent automatically when it's done. Why? When you send a message while OpenCode is running: Without this plugin: Your message interrupts the current run, causing context confusion With this plugin: Your message waits, then sends automatically when the model is ready

OpenCode plugin with a structured Brainstorm → Plan → Implement workflow and session continuity.

OpenCode plugin for persistent memory using Supermemory. Your agent remembers what you tell it - across sessions, across projects.

Smart voice notification plugin for OpenCode with multiple TTS engines (ElevenLabs, Edge TTS, Windows SAPI) and intelligent reminder system.

JJ makes version control simpler than git - no staging, no stashing, automatic conflict resolution. This plugin adds automatic workspace isolation for AI development: describe what you're building, implement it, push, and the workspace cleans itself up. No ceremony, no forgotten cleanup. Just a clean slate ready for the next feature.

Plannotator hooks into plan mode, submits a plan and opens an interactive UI, feedback is automated back to opencode - approval launches opencode into build mode. Local-first, no backend and explicit annotation.