Remote-OpenCode – Control your AI coding assistant from Discord
Discord-to-OpenCode bridge with 1000+ weekly npm downloads, but it's a thin wrapper around OpenCode CLI.

Discord bridge to local AI using CDP—elegant security model, but niche use case.
Software developers with local AI setups who want remote task triggering
Cursor · Continue IDE · VS Code Remote Extensions
It's a local-first bridge that forwards messages to my desktop AI coding setup, then reports results back. Instead of exposing my dev machine through public ports or relying on cloud relays, it uses Chrome DevTools Protocol (WebSocket) to drive the editor UI locally and securely.
I posted a short video demonstrating how it handles UI generation and hot-reloading here: https://x.com/m_web3/status/2027743280923086968
Repo: https://github.com/tokyoweb3/LazyGravity
I would love to hear your thoughts on this architecture, especially regarding local CDP security boundaries.
Discord-to-OpenCode bridge with 1000+ weekly npm downloads, but it's a thin wrapper around OpenCode CLI.
Slack wrapper for Kiro/OpenCode when Cursor, Continue already own this UI.
Multi-platform bridge for Claude Code via chat, but only Claude fully working.
Useful setup guide for existing Anthropic feature, not a new product or tool.
Commands sent over Discord are forwarded to a local OpenCode CLI and the output streams back in real time — neat for firing off fixes or running queued tasks from your phone. It’s a pragmatic, low-friction approach to remote control (no cloud service required), but it’s niche: you must already run OpenCode locally and be comfortable exposing a bot to your environment.
Turns an existing Claude/OpenAI key into something that actually keeps working for you: heartbeat pulses propose tasks, persistent research notes and daily journals build context over time, and browser control plus messaging (Telegram/WhatsApp/Slack) make it proactively useful. Clever local-first architecture and a polished desktop UI give it real stickiness, but it's boxed in by macOS-only delivery and the need for paid third-party models.