Freaking hell this is rapid.
Ran it against agent-browser by Vercel (arguably the best browser tool on the market)
- 40% faster
- 81% less input tokens
- 33% fewer steps
- 50% less tokens (not counting cache reads)
- Zero external API used
Model: GPT 6 Astra (medium)
btw OpenCode Browse supports running an agent and your browsers on different machines
had to implement this since i use a remote server, it can still orchestrate browsers on my desktop and laptop
I rebuilt OpenCode to run inside browser devtools with console.log statements!
I hope you (errr, your agents) will build some amazing console apps, too:
https://t.co/7pozkDiGTF
I've had a lot fun trying a new way to interact with agents
introducing Grim: a place to think with your agents
it's a markdown editor, a shared filesystem, hosted git, and a way to let your agents run but give feedback and view output
https://t.co/FzPV4cfb55
we get occasional reports that deepseek in OpenCode Go feels dumber for some people
i ran all the benchmarks i could find against the different configs we have
it's all in the same range, we did discover 2 specific issues in some low traffic configs we're going to kill
no matter what agent you're using, your voice is the best way to talk to them
and hex is the best way to use your voice:
- fast
- runs locally
- works on mac, windows, linux
stable release now available: https://t.co/Eb78egcyoP