OpenCode plugin that prevents agents/tools from reading or editing sensitive .env* files, while still allowing safe inspection via EnvSitter.
Raven is a context firewall for OpenCode. It routes noisy search, docs, web, GitHub, and MCP calls through a free focused agent before they hit your main model, saving cost and context!
Orderly SDK documentation runtime: MCP server, exact indexes, and narrative (QMD) retrieval
OpenCode TUI sidebar plugin that shows running background sub-agents.
Isomorphic client Runtime for Typescript/node.js/browser javascript client libraries generated using AutoRest
TypeScript/JavaScript client SDK for building applications that interact with Kagenti ADK agents.
Warp terminal integration for OpenCode — native notifications and more
OpenCode plugin that adds a lightweight resolver/coder harness for continuous agentic coding.
FlowDesk OpenCode plugin with Release 1 non-dispatch command-backed registration.
Ganglia — MCP tools + Code Mode for every major AI coding assistant (Claude Code, Cursor, Windsurf, Cline, OpenCode, Continue, Zed, Codex CLI, Gemini CLI)
OpenCode plugin that prefixes shell commands with snip to reduce LLM token consumption
Plannotator plugin for OpenCode - interactive plan review with visual annotation
Multi-agent swarm coordination for OpenCode with learning capabilities, beads integration, and Agent Mail
A set of utilities for developing TypeScript agents using Google Agent Development Kit (ADK)
Google Antigravity IDE OAuth auth plugin for Opencode - access Gemini 3 Pro and Claude 4.6 using Google credentials
Opencode plugin to fetch latest and trending research papers from arXiv and OpenAlex
Opinionated OpenCode agent harness — PRIME, plan, build, QA, skills, MCP wiring, hashline editing.
OpenCode plugin that gives coding agents persistent memory using Supermemory
Adds Vim-style insert and normal mode editing to the OpenCode prompt.
No prompt limits. No broken streams. Full thinking + tool support. Your Cursor subscription, properly integrated.
Intelligently detects and recovers stalled OpenCode sessions using abort+continue with status polling and progress tracking
AI Network Agent Development Kit
Official Agent Development Kit for MIOSA — build LLM agents that natively use MIOSA sandboxes, desktop computers, and deployments with the tool-call loop pre-wired.
A Team-first Agent System