Data infrastructure for AI Apache 2.0

Joined March 2022
We think memory is the largest unsolved problem in AI today Introducing Foundation: Chroma's solution to memory
I’ve been looking forward to today for 3 years Today we’re announcing Foundation - Chroma’s solution to memory Our research preview of this technology builds self-improving memory from your agent sessions. Try it out at trychroma.com/foundation
7
2
73
20,953
Chroma retweeted
Thrilled to welcome Jeff and the Chroma team to Replit! They’re pioneers in AI. They were building RAG before it was even a thing! At Replit, they’ll help solve one of the hardest problems in AI: giving agents the context and memory they need to do real work. Massive step toward the self-driving company.
Chroma is joining Replit! Together, we will build the context layer for the self-driving company. trychroma.com/blog/chroma-jo…
60
10
173
9,916
Chroma is joining Replit! Together, we will build the context layer for the self-driving company. trychroma.com/blog/chroma-jo…
31
12
16
392
45,531
We invented a new concurrency control protocol, named Fission, for agents swarms to update shared data for Foundation. trychroma.com/engineering/tr… and includes a section on "why not Git"
12
12
1
108
6,595
a new emoji - from our slack to yours 🫶
10
2,018
if you are an engineer and want to build the best memory system on earth - send me a DM
I’ve been looking forward to today for 3 years Today we’re announcing Foundation - Chroma’s solution to memory Our research preview of this technology builds self-improving memory from your agent sessions. Try it out at trychroma.com/foundation
9
10
61
8,795
I’ve been looking forward to today for 3 years Today we’re announcing Foundation - Chroma’s solution to memory Our research preview of this technology builds self-improving memory from your agent sessions. Try it out at trychroma.com/foundation
109
94
46
875
233,317
We’re excited to share our latest research led by @patpcj and @HammadTime. Frontier level agentic search performance at 20B parameters.
Introducing Harness-1, a 20B search agent trained with a state-externalizing harness. > frontier-level long-horizon search, rivaling Opus-4.6 and outperforming GPT-5.4 > Context-1-level cost and latency > externalizes candidates, evidence, verification, and search history > open-source
5
7
54
9,848
Reranking is a critical part of a high quality search system. Build an intuition for how it works and how to think about integrating reranking into your application. 👇
1
3
1
38
8,029
Join us tomorrow night!
Introducing No Latency Demo Night private event — [@nozomioai x linkup x @trychroma] apr 9, sf bringing together the most cracked builders for live demos + raw technical creativity. build anything with chroma, linkup, or nozomio: agents, retrieval systems, workflows, weird hacks top 3 demo live $500 prize + credits + high-signal feedback apply 24h in advance with a short pitch luma.com/e6vat0qv
1
4
2,195