OpenCode Go is becoming the best source of data on what models are being used and how
we've made a public stats page so you can see the latest
opencode.ai/data
OpenCode 1.17.3 can reference other git repos or local folders
饾殯饾殠饾殢饾殠饾殯饾殠饾殫饾殞饾殠饾殰: {
"饾殠饾殢饾殢饾殠饾殞饾殱": "饾殣饾殥饾殱饾殤饾殲饾殝.饾殞饾殬饾殩/饾櫞饾殢饾殢饾殠饾殞饾殱-饾殐饾殏/饾殠饾殢饾殢饾殠饾殞饾殱-饾殰饾殩饾殬饾殨"
}
gives it full access to the effect codebase, here's how we use it
There's a new version of the Models .dev website
It shows the most recently updated models first, it's broken down by the labs that made these models, and their providers
Shoutout to @adamdotdev for updating this
in the next version of @opencode, file search is powered by fff
- files the agent opens start ranking higher
- tool calls reuse the same search layer instead of starting cold
- less wasted context
- fast af
here鈥檚 me searching around the linux repo, a ~40m line codebase
A counter-bet on AI infrastructure built outside the SF playbook, and why care beats capital. Featuring turbopuffer's @Sirupsen and OpenCode's @jayair, with Shopify's @fnthawar.
0:00 Open Sleeves, Open Source
1:21 Why Open Source Won
2:45 Search Was a Pain in the Ass
5:03 Quotes Around "ARR"
6:48 Founder-Led Everything
11:31 Find Your Voice or Get Sniffed Out
14:49 First Principles in the Forest
20:08 The Vape Company That Wasn't
22:05 Why Claude Code Wasn't Enough
24:09 The World Is Our Stage
we landed on a pretty good workflow for doing parallel work in OpenCode
this demo is with git worktrees but i also preview an alternative we're working on at the end
this will be in 1.6.0
@opencode can already spawn background subagents, but I just opened a PR letting you send synchronous tasks to the background.
But more interestingly, this video was recorded edited by 饾殬饾殭饾殠饾殫饾殞饾殬饾殟饾殠 running 饾殬饾殭饾殠饾殫饾殞饾殬饾殟饾殠 with 饾殱饾殠饾殯饾殩饾殥饾殫饾殜饾殨-饾殞饾殬饾殫饾殱饾殯饾殬饾殨.