Chroma, every mention
35 scenes, the whole family · ← back to Chroma
tap a year for its mentions
every year anyone Shawn Wang 31Jeff Huber 12Alessio Fanelli 8Paul Klein 1Nina Lopatina 1Lance Martin 1Dhravya Shah 1Akshay Agrawal 1
Verbatim, from the transcripts: the passages where Chroma comes up
The Agent Cloud: Databricks’ Bet on the Future of AI — Matei Zaharia and Reynold Xin
- ▶ 52:20 Shawn Wang And then, uh, I recently interviewed Simon from Turbo Puffer, same thing, like, and Chroma as well.
⚡️ OpenClaw's Memory Sucks and the fix is simple — Dhravya Shah, Supermemory
- ▶ 2:25 Dhravya Shah And now, then I, like, dug down the rabbit hole, and so, so, better databases, like, at that time, and even now, except a few, like, like, TurboPuffer and Chroma,
Why Every Agent Needs a Box — Aaron Levie, Box
- ▶ 0:39 Shawn Wang We're back in the Chroma Studio with, uh, Chroma CEO, Jeff Hoover. 2 times in the scene
[State of Context Engineering] Agentic RAG, Context Rot, MCP, Subagents — Nina Lopatina, Contextual
- ▶ 10:26 Nina Lopatina There was in the HAL benchmarks, there was one about, uh, Is this the, the Chroma piece?
- ▶ 13:12 unnamed speaker Shout out to Chroma.
How Zyphra went all-in on AMD + Why Devs feel faster with AI but are slower — with Quentin Anthony
- ▶ 42:28 unnamed speaker Um, ContextRaw, we kind of talked about, I mean, the studios at the Chroma office, which wrote the ContextRaw paper, so anything specific on just context engineering in general?
Context Engineering for Agents - Lance Martin, LangChain
- ▶ 4:24 Lance Martin But also, Jeff from Chroma spoke about this on the recent pod.
- ▶ 10:15 Shawn Wang I, I do think that the compression, that was also part of the Meetup findings of yesterday where we were, we were at the context engineering meetup that Chroma hosted, uh, that you do want frequent compression because you don't want to…
Long Live Context Engineering - with Jeff Huber of Chroma
- ▶ 0:13 Shawn Wang It's weird to say welcome because obviously, actually, today's guest, Jeff, has welcomed us to Chroma for many months now. 10 times in the scene
- ▶ 3:28 Jeff Huber Chrome is written in Rust. 3 times in the scene
- ▶ 3:34 Jeff Huber Assistance tier and, like, data layer for Chroma, uh, distributed in Chroma Cloud as well.
- ▶ 4:46 unnamed speaker And it took you a while to release Chromacloud too, which rather than just getting something out that maybe broke once you got to production, you kind of took your time.
- ▶ 5:46 unnamed speaker And yeah, there was the option of like, okay, Chroma's single node is like doing really well, getting a bunch of traffic, clearly having a hosted service is the thing people want. 4 times in the scene
- ▶ 8:09 Shawn Wang We'll talk about standard condition and all the other fun stuff towards the end, but we'll, we'll focus on Chroma. 6 times in the scene
- ▶ 8:51 Shawn Wang I think like when you say single node Chroma, like I think you're describing the core difference between like what Chroma Cloud has been 4 times in the scene
- ▶ 12:27 Alessio Fanelli Can you give the canonical definition for you and then how, um, Chroma plays into it
- ▶ 19:10 Alessio Fanelli Like does everything that you talk about is on the Chroma roadmap basically, or 3 times in the scene
- ▶ 28:54 Jeff Huber And, you know, we've actually worked on now inside of Chroma, both single load and distributed, we support regex search natively. 3 times in the scene
- ▶ 34:48 Shawn Wang So in some sense, we sort of decoupled the transformer into, first we encode everything with the encoder-only model, put it into a vector database like Chroma. 2 times in the scene
- ▶ 42:31 Alessio Fanelli How do you think about that in terms of Chroma?
- ▶ 45:43 Shawn Wang What are those lessons there that you're applying to Chroma?
- ▶ 52:43 Jeff Huber If you're a great product designer that wants to work on developer tools, I think we have one of the most kind of unique opportunities at Crema. 5 times in the scene
The AI Agenda: GPT5 leaks and the business of AI News — Steph Palazzolo, The Information
- ▶ 37:36 Alessio Fanelli And you know, one thing Chroma released this context rod paper recently about context utilization and the cloud models are actually the best at using kind of like longer context.
🕰️ The Oral History of Windsurf (ft. Varun Mohan, Scott Wu, Jeff Wang, Kevin Hou, Anshul R)
- ▶ 38:08 Shawn Wang We'll try to connect you to Chroma and see. 2 times in the scene
⚡️The Future of Notebooks - with Akshay Agrawal of Marimo
- ▶ 14:02 Akshay Agrawal So this demo here, we have like a bunch of papers from archive and we've indexed them using chroma DB into like a basic vector database.
Claude Code: Anthropic's CLI Agent
- ▶ 44:32 Shawn Wang Chroma.
The Rise and Fall of the Vector DB category: Jo Kristian Bergum (ex-Chief Scientist, Vespa)
- ▶ 2:00 unnamed speaker I, I actually was the one who wrote the, uh, Chroma example in the opening I cookbook. 3 times in the scene
- ▶ 6:40 unnamed speaker I will also mention that Chroma, I think from the start has always said they're kind of going after information retrieval and not so much, not so much, uh, you know, the narrow sense of rag.
Browserbase: Browser Infrastructure For Your AI Agents
- ▶ 10:05 Paul Klein We're here in the chroma offices and like, you know, vector databases is a new category of infrastructure.
AI Engineering for Art - with comfyanonymous
- ▶ 0:13 Shawn Wang We are in the Chroma Studio again, but with our first ever anonymous guest, Comfy Anonymous.
Production AI Engineering starts with Evals
- ▶ 1:18:10 unnamed speaker Yeah, we'll, we'll be having, uh, Chroma
A Brief History of the Open Source AI Hacker - with Ben Firshman of Replicate
- ▶ 1:19:41 unnamed speaker Tell me this came from Chroma, because, because I, I'll just start that one.
The Four Wars of the AI Stack - Dec 2023 Recap
RAG is a hack - with Jerry Liu of LlamaIndex
- ▶ 1:00:49 Alessio Fanelli I know this book says wearing a, a Chroma sweatshirt. 2 times in the scene