Today is the day the new Claude Max limits kick in. Just in time. Ive built out a UI for opencode which allows for bulk management of concurrent agents and subagents. Ill use this to more intelligently switch between other models for various tasks to offload pressure from my Max plan. For example, using AI elements in the frontend to dispatch cheap or free subagents for egress tokens, and preserve claude for management and ingress. Still some kinks to work out. But im liking it, will add a agent editor ui as well to configure agents on the spot

@ScriptedAlchemy Still not hitting limits lol

@ScriptedAlchemy have you hit the limits today yet?

@ScriptedAlchemy Smart approach to context and token management. I'm wondering if you have tried GPT-OSS for coding. Benchmarks say it outperforms Sonnet 3.7, and it can be run on local machines like M4, but I haven't tried it yet.

@ScriptedAlchemy Scope and analyze with a cheaper model, eoument the task, use a good inexpensive kodel to implement , use an proper and expensive model to fix bugs ...

@ScriptedAlchemy But what is pinterest/bonsai about ?

@ScriptedAlchemy Very cool.

@ScriptedAlchemy Resource optimization is key. A diversified model approach could yield interesting comparative results.

@ScriptedAlchemy 🔥

@ScriptedAlchemy This is awesome! Any plans to share more details on this to public? No pressure, just super curious —especially how you orchestrate agents/subagents and switch models.

@ScriptedAlchemy what are the new limits?

@ScriptedAlchemy that's really cool! do you intend to open source it?