onepot retweeted
We're launching 30B-scale virtual screening at Rowan today in partnership with @onepot_ai.
By combining Rowan's high-throughput computational infrastructure with onepot's autonomous lab, we can go from target to experimental data in weeks, not months.
6
15
75
6,802
onepot CORE 2 Triangulum is live: 30B compounds, 16 transformations, including multicomponent and multistep chemistry for the first time.
two price tiers, $250 or $375 per compound, and available at onepot.ai/ or via api.
see onepot.ai/blog/core-v2 for more
3
8
805
onepot retweeted
We're partnering with @altaratech to bring together the AI for Science Symposium, featuring talks from @medra_ai , onepot AI, and @LatchBio. Learn how AI is accelerating scientific discovery across biology 🧬, chemistry 🧪, and physics 🧑🏻🔬.
Come by on 8/27 👉
rsvp.greylock.com/greylock/r…
4
15
80
18,012
We just released onepot-Bench 0, a benchmark for testing whether LLMs can make decisions useful in a chemistry lab, built on proprietary reaction-outcome data generated in our lab. 1/5
1
1
11
3,654
We found that frontier models are generally quite good at answering basic questions about molecules and recognizing controlled molecules; however, these scores do not reflect deeper understanding of chemistry 4/5
1
3
164
Thanks to @posthog for hosting such a crazy ambitious event, and to @OpenRouter and @modal for sponsoring credits.
Excited to bring together companies shaping the future of bio x AI:
@onepot_ai -- providing synthesis with AI and robots at breakneck speed
@RowanSci -- allowing scientists to access the latest molecular design tools
@boltz_bio -- building generative models in biology and chemistry
@muni_bio -- creating the agentic environments for science
We’re moving away from manual coordination into agentic self-learning loops, a shift that positions U.S. biotech to compete on innovation and not labor arbitrage. To help shape this future, come join us on Saturday luma.com/2rbgfn69
8
23
1,427
"because no one has ever done this before"
– Sam Foxman telling about his experience at onepot
2
6
1,057
First episode of the muniverse, a podcast by @muni_bio focusing on frontier science.
Synthesis might be the most underrated bottleneck in drug discovery. While everyone is racing to build better AI models for molecule design, @onepot_ai is building a world where molecules can be designed, made, tested, and shipped on demand.
I sat down with onepot co-founders @daniil_boiko and @andrei_tyrin, alongside my co-founder @derekalia.
00:00 - What onepot actually does
00:16 - Why synthesis became the bottleneck
02:52 - The Moscow lab origin story
04:41 - Why CRO timelines take months
07:00 - How automated is the chemistry stack?
08:58 - Where humans still beat robots
11:14 - The hidden labor behind “automated” labs
13:58 - Drug discovery vs materials
15:53 - Small molecules beyond pharma
17:09 - Why small molecules are harder than biologics
18:26 - The 10-year chemistry bet
20:47 - Personalized medicine needs faster synthesis
21:56 - Predicting toxicity before human trials
23:20 - Oil, ore, polymers, and drugs
26:28 - Why complex chemistry is still underbuilt
30:47 - Zero-person biotechs
33:32 - 3D molecules, cages, and exotic reagents
36:30 - The US-China chemistry advantage
38:20 - onepot in plain English
40:45 - Why biotechs outsource chemistry
4
11
46
4,489
Happy 250th, America 🇺🇸
Chemistry’s version of a birthday card: a molecule we made with [M+H]⁺ = 250.
13 carbons for the 13 stripes.
1
8
757
onepot retweeted
🥚 Most companies sell the eggs: a molecule, a dataset, a one-off experiment.
🪿 onepot is building the goose.
An automated chemistry platform that can design, make, measure, and learn — then come back tomorrow and lay the next batch of golden eggs
2
6
712
EBOLATHON - the ultimate rapid-response challenge against viral threats.
8 hours to generate and submit compounds to test against Bundibugyo Ebola strain with wet-lab validation.
Join us in SF on July 18th: luma.com/2rbgfn69
Hosted by @muni_bio & @onepot_ai
10
19
4,577
Inspired by @AnthropicAI's blog post, we looked into AI coding assistants and their effect on our productivity.
Last year, most of our coding was still human-written, but nowadays even the non-Claude mix is a split between @cognition's Devin and @OpenAI's Codex.
1
4
237
Coding agents have also been a great help in the lab. Our robotics work requires the use of a lot of different robot APIs, some of which are poorly documented. These take days for humans to handle, while coding agents can work with them very effectively.
1
3
83