Avanika Narayan (@Avanika15) / X

Avanika Narayan

1,373 posts

Avanika Narayan

@Avanika15

cs phd @Stanford | prev co-founder/ai @rox_ai | intelligence-per-watt.ai

Joined September 2018

Pinned
Avanika Narayan
@Avanika15
Nov 19, 2024
So excited to be launching @rox__ai with the incredible @ishanmkh, Diogo Ribeiro and @shriram_s. The Rox Agent Swarm is the first enterprise ready fleet of AI agents, designed to supercharge the world’s best sellers. Get your Agent Swarm now —> rox.com Rox
Rox
@rox_ai
Nov 19, 2024
We built a B2B SaaS sales company and here’s what it taught us about B2B SaaS sales 🧵👇 (but actually) Today we’re launching Rox, the first publicly available AI agent swarm for the top sales teams, and in the private beta it already helped reps grow their books 30%. 2025 is
00:00
38K
Avanika Narayan
@Avanika15
May 13, 2025
can you chat privately with a cloud llm—*without* sacrificing speed? excited to release minions secure chat: an open-source protocol for end-to-end encrypted llm chat with <1% latency overhead (even @ 30B+ params!). cloud providers can’t peek—messages decrypt only inside a
00:00
79K
Avanika Narayan
@Avanika15
Jun 16, 2022
Can Foundation Models (FMs) clean and integrate your data? We explore the efficacy of FMs on these hard classical data tasks (1/7)
Avanika Narayan
@Avanika15
Jan 10, 2023
This quarter, Stanford’s Advances in Foundation Models Class (CS 324) will be partnering with the Stanford MLSys Seminar to host a special talk series on foundation models! Our first talk will be @tri_dao. Catch us *TOMORROW* at 3:30 PT:
109K
Avanika Narayan
@Avanika15
Feb 25, 2025
we shipp’d 👭 on-device lms and frontier cloud lms. and…they were a match☺️. 98% accuracy, just 17.5% the cloud API costs beyond excited to drop minions: where local lms meet cloud lms 😊 joint work w/@EyubogluSabri & @dan_biderman at @hazyresearch. ty @togethercompute,
Dan Biderman
@dan_biderman
Feb 25, 2025
How can we use small LLMs to shift more AI workloads onto our laptops and phones? In our paper and open-source code, we pair on-device LLMs (@ollama) with frontier LLMs in the cloud (@OpenAI, @Together), to solve token-intensive workloads on your 💻 at 17.5% of the cloud cost
00:00
32K
Avanika Narayan
@Avanika15
Apr 3, 2025
Replying to @Mascobot and @a16z
@Mascobot love this so much — run minions on it and get the best of both worlds:
GitHub - HazyResearch/minions: Big & Small LLMs working together
From github.com
21K
Avanika Narayan
@Avanika15
Jun 14, 2023
Fine-tuned performance without a step of SGD? Excited to share TART, which transplants transformer-based reasoning modules on arbitrary foundation models to improve in-context learning performance! 📜 arxiv.org/abs/2306.07536 💻 github.com/HazyResearch/T… ✍️ hazyresearch.stanford.edu/blog/2023-06-1…
24K
Avanika Narayan
@Avanika15
May 8, 2024
Can AI agents automate enterprise-level workflows? Excited to share ECLAIR, a first step towards end-to-end digital workflow automation in knowledge-intensive settings like hospitals! ✍️Join the waitlist to work with ECLAIR: bit.ly/eclair-signup 📄Paper:
22K
Avanika Narayan
@Avanika15
Sep 9, 2025
🚨 minions is officially supported in @Docker 🚨! beyond excited about this collab: you can now run minions via the docker model runner and unlock hybrid ai for your local workloads! details in comments below 👇🏽 huge thanks to world class eng + dev squad @Docker ❤️:
21K
Avanika Narayan
@Avanika15
Jan 19, 2023
Excited to announce a few updates in our work towards using foundation models for data wrangling tasks! 📜Our paper has been published in VLDB 2023 💪Added 2 new integration tasks: data transformation & schema matching ✍️We wrote a blog post 🏋Added data tasks to HELM benchmark
13K
Avanika Narayan
@Avanika15
Aug 15, 2025
[8/14] minions daily ship 🚢 📱 gemma3 270m! smaller models keep getting stronger. shipped support for @GoogleDeepMind's gemma 3 270m — a compact lm optimized for efficient, on-device inference. run it in minions today, using the @ollama client ♥️
8.2K
Avanika Narayan
@Avanika15
Apr 9, 2025
[4/09] minions daily ship 🚢 🔍 deep research! — we shipped a deep research mode in minions (h/t @MAliyanIshfaq for the 🤯 pr). stop burning $200/month on @OpenAI — get deep research for nearly $0 w/minions + the latest local lms from @ollama 💪 see it in action explaining the
00:00
13K
Avanika Narayan
@Avanika15
Mar 7, 2025
[3/6] minions daily ship 🚢 💻 minions cli — run minions directly on 🫵 local filesystem! analyze your files, code repos and more! acts as as drop-in replacement for @AnthropicAI’s claude code, but way cheaper 😊. see minions cli in action👇 🧠 qwen qwq model support — s/o
00:00
12K
Avanika Narayan
@Avanika15
Nov 28, 2024
this tg, grateful to be building alongside the best in the world 🍁 > customers: @tryramp, @MongoDB, @confluentinc, and many more who trust us > team : @amolsingh, @damonlin_, @derhacobian, and the entire @rox__ai crew — 💛🖤 > partners: @Konstantine, @josephinekchen,
Rox
@rox_ai
Nov 28, 2024
happy thanksgiving from rox. we're grateful to all the rox⭐️s — our incredible customers, partners, and builders — for their support
4.2K