I'm running it on my 8 years old 2080ti 11 gb VRAM + 32 gb ram. After tasking fable to optimize the setup for a few nights it's pretty good for some quick funny clips (2min30 for 5s , 5mins for 10s, with reference pics to insert anyone in the clip, not great quality but acceptable for some fun on a phone). I haven't had as much fun with Gen AI since the Stable Diffusion days.
Just took a glance so I may be completely wrong, fell free to ignore, but if I understand correctly, tsrx is just syntactic sugar for normal tsx code and does not enable anything new?
If this is the case: I think introducing tsrx as part of Octane muddies the water a bit and makes me more hesitant to try (even if it is optional).
The idea to make tsx files more readable may be interesting but in that case it should go into its own separate project, and maybe just put a lang toggle in Octane docs and a page about tsrx compat, that way if people are intrigued by the new syntax they can just look it up but the docs stay focused.
agreed, tsrx is neat as supported but personally i'm not a fan of it, makes me think of angular and more domain specific language stuff. the whole tsrx angle makes me wary of this project entirely, which is a shame, since octane does sound pretty neat. i'll still check it out, but this was indeed my initial reaction upon seeing tsrx here
TSRX allows for better runtime generated guarantees, especially around loops which generates faster runtime logic from it. We can’t assume too much statically when reading something.map as the method might have different heuristics
Just prompt it that way then, I can get Claude to plow through features for 12h with the correct prompt and setup, no need to destroy the tools that are useful when you want the opposite.
You seem to have tried a few things, if you don't mind I have a few questions as someone currently on Claude Code but would prefer to not lock myself in a commercial ecosystem (and their pricing change regarding headless usage is annoying me):
- how do/would you add the WebSearch tool to your harness? pay for a separate service or does deepseek offer something with their subscriptions?
- do pi/opencode support pasting images in prompts?
- how do you handle reading images? deepseek is not multi modal IIRC? do you pay for another model and route to it?
Any of these missing would really annoy me in day to day use...
Brave, Exa, and Tavily all offer a free tier for websearch, after that it comes out to like 1¢/search, very easy to ask pi to build a web search tool using any of these providers.
They support image locations like a file or url, but not regular images (opencode desktop might though?)
Both pi and opencode make it very easy to change models so you can easily call to 5.4-mini or whichever multi-modal LLM for reading images. I'm sure you could even create a skill to automate the process too, having the model use the cli to send the photo to the multi-modal and give it back a description.
Yes I'm also using it for coding: I often make the agent use WebSearch in the research phase when deciding on a stack or a library or research best/modern practices to do achieve something. As for images I find it super useful to be able to paste snipped screenshots to show the agent when something is wrong in a UI/frontend or just something I can't copy paste easily.
Tangential question for Claude Code subscribers, mid June `claude -p` will move to api pricing (with some "SDK credits" before it kicks in), so headless usage will become 20-30 times more expensive, and all these high level orchestrator tools/workflows depend on it. What the next move for you? How does the OpenAI subscriptions compare? Similar limitations?
