A lightweight, powerful agent orchestration plugin for OpenCode. Transform your AI assistant into a manager capable of delegating complex tasks to specialized sub-agents.
No reviews yetBe the first to leave a review for Oh My Opencode Slim
Maker
📌
Hey Product Hunt! I built Oh My Opencode Slim because I kept hitting the same wall with AI coding assistants. One model tries to do everything, from quick lookups to complex multi-file changes, at the same cost and speed every time.
The idea is simple. An Orchestrator agent manages the session and delegates specific jobs, like exploring a codebase, checking documentation, reviewing UI, or writing an implementation, to specialized sub-agents. You can mix models freely, so a fast cheap model handles exploration while a stronger model handles the hard reasoning.
It started as a personal plugin for OpenCode to cut my own token costs and speed up iteration. After sharing it with a few friends and getting good feedback, I cleaned it up, added real time monitoring through tmux, LSP tools, AST aware pattern matching, and an extensible skills system, then open sourced it under MIT.
Would love to hear what workflows you would want to see supported next.
Report
Honestly love the idea of agent orchestration in Opencode, but it would be really helpful if there was a visual graph view showing which sub-agents are running and how they're talking to each other in real time. Right now it's kind of a black box and I have no idea what's spawning what when things get complex. Would make debugging so much easier.
Report
Maker
@cansel812054 thank Cansel - for observability you'd need to configure multiplexer integration ; we support various multiplexers - this will allow to see each agents in a dedicate pane working.
Honestly love the idea of agent orchestration in Opencode, but it would be really helpful if there was a visual graph view showing which sub-agents are running and how they're talking to each other in real time. Right now it's kind of a black box and I have no idea what's spawning what when things get complex. Would make debugging so much easier.
@cansel812054 thank Cansel - for observability you'd need to configure multiplexer integration ; we support various multiplexers - this will allow to see each agents in a dedicate pane working.