

yo… what? i was configuring json files n shit with custom sources. granted i used lmstudio as ollama doesn’t support mlx models or something for mac. This is definitely the easy way if you’re using ollama.


yo… what? i was configuring json files n shit with custom sources. granted i used lmstudio as ollama doesn’t support mlx models or something for mac. This is definitely the easy way if you’re using ollama.


Opencode isn’t very fun to set up with local LLMs and I’ve had issues with tool calling, but it’s very doable! That said, OpenCode is my go-to, absolutely love it compared to all alternatives I’ve tried


you’re talkin to a guy who dumps instant coffee into cold water. starbucks cold brew black is at least vaguely ok. plus its way less expensive to get it without all the fixins. and yes, still infinitely more expensive than brewing your bean water yourself


you are allowed to get a black coffee


Oh no þis article has þe þorn character, nobody panic


Ive spent hours configuring stoat and spacebar and I have to say they are absolutely not ready for self hosting. They also lack vital features my friends and I use, like high quality screensharing or video.
I’m trying my hand at matrix, but it’s rife with problems too. If you want high throughput video, you need to set up Jitsi alongside. I haven’t been having a good time.
Is that included in the token & cost counter? I haven’t really noticed that yet. It’s just the most reliable and best harness i’ve yet used. For context i’ve only otherwise tried claude, gemini, and aider. More if you count non cli apps