Are you attending AI startup school in SF? I’m hosting dinners every day (June 13-17). Let me know if you’re interested in coming. You can also LMK if you need to be added to the AI SuS group chat.

Over the weekend we crossed 20,000 stars and usage in 80,000 repos on GitHub! Our team is humbled and we’re excited to continue to build.

Chroma now can store each collection’s embedding model, provider, and index settings, so clients, and the Cloud console, pick the right config automatically. You can use Collection Configuration in Chroma v1.0.10 or Chroma Cloud today.

Hi Elon Musk Y Combinator

Everything should be built as a TUI Thanks for building a framework that's fun to create with Charm!

kit now supports semantic search in its CLI, new in v1.5. different output formats for piping, readability. customizable embedding models, & more. defaults to a chroma backend. it's pretty fast.

Context Rot! What is it? What does it mean? New video breaking down Chroma's latest paper and applying it to interacting with AI 00:00 - What is Context? 04:44 - The Flaw of "Needle in a Haystack" 10:22 - How Distractors Degrade AI Performance 14:31 - The Impact of Prompt

This MCP gives your AI expert-level knowledge of any library, even past its July 2024 training data cutoff. Give Chroma’s package search tool a try.

I moved to SF 5 months ago. What can I do to improve my apartment?

It's so over for Dia

Damn good burrito.

In case you were wondering, Cloudflare got a whole ass pirate ship

The best way to evaluate your deep research agent's performance is by using the Epstein files as your corpus 0 contamination for sure. The FBI made sure of it.

Do people actually build agents that look like this in real life?

Applying Amdahl’s law to agents is obvious Agents spend most of their runtime just gathering the context they need to complete their task. Make it 10x faster!