Next up: Envoys. Your own Claude Code and Codex, working on your research graph without leaving Flywheel: ask it anything, add to it as you go. They run on your own setup: your settings, skills and subscription. That makes Envoys free.

Custom views, just by asking. Ask Envoys for a lens on your research and it tags, filters and reorders your graph around it, from just the results behind one question to a single line of work, in order. No digging through everything to find the part that matters.

Plan what’s next beside the evidence. Envoys turns your results into the next experiments, linked to what they build on. You watch them land on your graph as it works: new nodes marked, a counter of what’s waiting. Agents stage the work; only you commit it.

Or just talk to it. Call Codex from Envoys and go through your research out loud, no typing. It opens what it's talking about on your graph as it answers, and runs on your own ChatGPT sign-in.

Envoys opens from one button in the corner; type / for your agent's own commands and skills. By default it asks before an agent changes anything, and nothing goes through our servers. Turn it on in Settings › Experimental. Embrace the new UX paradigm.

Damn, i was actually working on something similar, you beat me to it, i will probably release it anyway in the next days.

I like having the reasoning behind the next experiment close enough to revisit later.

Claude Code on a research graph is an interesting combination. How does Envoys link an answer back to the notes and sources behind it?