I just published Framer MCP plugin Control @framer with @claudeai or @cursor_ai some things you can do with it: • ideate and rewrite landing pages with Claude • create custom React components • update all colors in a page at once • export Framer components to react

github issues should have an option to get a notification only when a collaborator/contributor comments, not any user @jaredpalmer

it even works with @aisdk it's a thin layer on top of existing API requests to make sure they are not aborted when the user closes the page when the user comes back and they repeat the request the response is replayed from scratch and resumed

if you want something like "use workflow" but for existing code and with no architecture change check out durablefetch.com it makes any fetch request durable and resumable

We've raised $100M from Kleiner Perkins, Index Ventures, Lightspeed, and NVIDIA. Today we're introducing Sonic-3 - the state-of-the-art model for realtime conversation. What makes Sonic-3 great: - Breakthrough naturalness - laughter and full emotional range - Lightning fast - 90ms model latency, 190ms end-to-end (fastest on market) - Supports 42 languages The difference: We build on State Space Models (SSMs) instead of Transformers. Transformers (what everyone else uses) are like rewatching the entire conversation from the start before saying each new word. Every word requires reviewing everything. SSMs (what Sonic-3 uses) are like humans, remembering the topic and vibe of the conversation. Enough context to speak naturally without replaying everything. My co-founder, Albert, and I pioneered the SSM paradigm at Stanford AI Lab (S4, Mamba), and it is now being adopted industry-wide. Thousands of businesses like ServiceNow, Cresta, and Decagon power millions of conversations monthly with Sonic. Try for free or book a demo here: cartesia.ai/sonic. If you're qualified and we can't make your voice AI better than what you're using now, I'll donate $5K to your chosen charity. As part of this launch, we cooked something super cool for you 👇🏻

just found mediafox on github video player powered by mediabunny, made by @wiedymi with multi track support 😻 github.com/wiedymi/mediafox

so does Remix v3 have any docs anywhere?

should I build my own coding agent cli?

grok is pretty cool

This way the Framer MCP should no longer add too much noise when you have it loaded but not using Framer

I just heavily reduced the size of the Framer MCP tools context size I moved most of the docs content from the tools descriptions to the tools output, with a main tool that should be called at session start to get overall Framer project structure and docs From 8k to 6k tokens

maybe bitcoin is God's funding system and he funds prophets by showing private keys in a dream

not sure about this

I just got an idea for rendering the diff in critique: use different shiki themes for deleted and added portions of code, remove the background I have the suspicion this will look great

look at this

grok video model is crazy good now

you will still need to keep some state in the database for background jobs unfortunately

this approach can also work for long running background tasks: the client is just another server that does requests to your own server. on failure it repeats them your server code only needs to be stateless and idempotent

this only works for models that support assistant prefill unfortunately (@basetenco kimi k2 does which is great)