From bioinformatics analysis to study design, papers, data and servers — ask in plain language; the agent runs it, checks it and returns the results.
The tools a genomics lab needs, on its own server, operated by asking in plain language.
Sequences in email attachments. A BLAST server nobody maintains. Gene tables in personal Excel files. Papers in five reference managers. An analysis only the graduated student could rerun.
One platform that belongs to your lab — databases, genome browser, papers, data, server and projects — run by an AI agent you talk to.
Build them from your sequences and genomes; search privately.
“Build a BLAST database from these genomes.”
View screen →
JBrowse 2 with your assemblies, annotations and read tracks.
“Load this genome and its GFF into JBrowse.”
View screen →
Function, sequences and expression for your genes, searchable by ID.
“Load this expression table into the gene DB.”
View screen →
Full-text search with page citations; study a paper with a quiz.
“Which of our papers measured CBF3 at 4 °C?”
View screen →
Ask in plain language — it builds, loads, searches and runs, and asks before anything destructive.
DataShare: project folders, previews, previous versions, share links.
“Save the results in the project’s analysis folder.”
View screen →
32 or 48 vCPU · 256 GB RAM · 4.3 or 9.0 TB, GPU plans; connect your own servers too.
Runs your analyses there, in the lab’s Jupyter.
View screen →
Tasks, calendars and messages next to the research — from idea to submission.
“Make a task for each step and add the lab meeting.”
View screen →
Deadlines are close; the figures are still in a student’s notebook.
With EuchroGeneEvery figure is registered with methods and statistics; the Writing agent drafts from them.
A student graduates; nobody can rerun the analysis.
With EuchroGeneScript, versions and parameters are saved beside each figure.
Records scatter; corrections vanish.
With EuchroGeneLabNote entries are signed, hash-locked and retracted only with a reason.
Progress updates arrive late, without numbers.
With EuchroGeneMembers report to the PI from what was actually recorded.
It works in your lab’s Jupyter and registers every result with what you need to trust and rerun it.
Ask in plain words.
Data, method, check and figure — shown first.
Code runs in your Jupyter.
Failed check → fix → rerun.
Figure with statistics, Methods and script.
The agent writes the pipeline, runs it, reads the errors and fixes them — round after round, until it runs end to end. It stops and asks you if the same error repeats or the attempt limit is reached.
Statistics, Methods and a copy of the exact script (SHA-256).
The analysis plan, sample size and statistical power are set at the design stage; the agent flags any later deviation.
RNA-seq, variants, BLAST, alignments, CRISPR, primers, cloning.
Lab Jupyter or your own GPU server; switches AI at a usage limit.
Results flow to the manuscript, tables, Word and PowerPoint.
You stay in control: plans first, deletions confirmed, numbers checked, every figure traceable.
Four agents per project — Design, Analysis, Writing, Papers — plus a LabNote. You decide every open question.
Ask for a step; the agent writes the code in your Jupyter, runs it, checks and fixes it, and explains the result.
The Design agent plans from your data, references and notes — with controls and n sized by power.
Drafts from registered figures and verified references only, as tracked changes you accept.
Make PPT / Make Word builds slides or a document from your figures.
A shared library searched by meaning; answers cite pages.
Agents and members record results, decisions, methods and deviations.
Files, tasks, calendars and messages next to the research.
Stage, next step, deadline and unsigned results of every project.
D-n on each card; due within 14 days moves to the top.
Key points, deviations and overdue steps from the LabNote.
PI, researcher and staff; personal notes stay their owner’s.
One project per Specific Aim; progress reports from their records.
Agents never sign LabNote entries or mark papers published.
Connect your own subscription, or the PI adds a lab key.
At a usage limit, the other AI answers and hands back after the reset.
Tick a figure, section, reference or file — the agent works on exactly that.
A reviewer pass checks numbers and claims against tool output.
Ask in any language; manuscripts are written in American English.
Pick the model for each engine; every chat can switch between Claude and Codex.
Own server and accounts per lab — nothing shared.
Dedicated server and database, role-based access.
Two-factor login, rate limits, idle sign-out, audit log.
Export and deletion requests (GDPR / PIPA), nightly backups.
Only what a question needs, sent to the provider you connected.
Field, team size, what you want to see — we demo it.
Accounts and roles; setup and updates included.
Browser, JupyterLab or phone — then ask the Design agent.
Yearly plans per lab. Prices exclude tax.
USD 4,800 / year · tax excluded
A dedicated lab server with the AI agents and bioinformatics tools, for one year.
Key specs
Ready within 1 week of order confirmation
Request a quoteUSD 6,000 / year · tax excluded
Everything in Basic plus 1 × NVIDIA V100 32GB GPU for GPU-accelerated analyses.
Key specs
Ready within 1 week of order confirmation
Request a quoteUSD 8,800 / year · tax excluded
For labs that need more CPU and storage. Everything in the Basic plan included.
Key specs
Ready within 1 week of order confirmation
Request a quoteUSD 10,000 / year · tax excluded
The High-end plan plus 1 × NVIDIA V100 32GB GPU.
Key specs
Ready within 1 week of order confirmation
Request a quoteEvery figure the agent registers carries its statistics, Methods, an interpretation and a copy of the exact script and environment file (with its SHA-256), so anyone in the lab can see how it was made and rerun it. The agent shows its plan first, checks each run against acceptance criteria, asks before steps that could delete your data, and a reviewer pass checks the numbers in its answers against the tools’ output. You decide what goes into the paper.
Your lab does. Each lab runs on its own dedicated server with its own database and accounts, and nothing is shared with other labs. Members can export their data, and account deletion requests (GDPR / PIPA) are handled on the platform.
Only when someone asks the agent, and only the parts that question needs — sent to the provider you connected (Anthropic for Claude, OpenAI for Codex) under your own account or the lab key. Files, notebooks and records otherwise stay on your lab’s server.
Claude (by Anthropic) or Codex (by OpenAI). Each member can connect a personal Claude subscription or ChatGPT account, or a PI can add a lab shared key. With both connected, each chat picks its engine and the other takes over when one reaches its usage limit.
The Writing agent takes numbers only from registered figures, their statistics and the LabNote; a missing analysis becomes a request to the Analysis agent instead of an invented value. References are verified by DOI / PMID, and anything it cannot verify is left as [REF] for you. A second reviewer pass checks each answer against the tools’ actual output.
Per year: Basic USD 4,800, GPU USD 6,000, High-end (48 vCPU · 9.0 TB) USD 8,800 and High-end GPU USD 10,000 (tax excluded). The GPU plans include 1 × NVIDIA V100 32GB GPU. All plans include the dedicated server, software, updates, maintenance and email support; AI usage is billed separately by the provider you connect.
Yes — every member gets an account with a PI, researcher or staff role. Everyone can read the lab’s research projects; owners, project members and PIs change them. Personal LabNote entries can be changed only by their owner.
The interface is in English. You can ask the agents in Korean or any language and they answer in yours; a translation view shows a manuscript in your language. Manuscripts are written in American English, and a Korean NRF proposal or a report can be written in Korean.
Yes. Your lab’s own servers, such as GPU machines, can be connected to Jupyter and switched to with one click; the agent can run there too. File Transfer copies data between your Jupyter and another server over SSH, with a key or just the server password.
No. Everything runs in the browser, in JupyterLab or in the phone app, and we set up, update and maintain the server.
Tell us what your lab works on — we will show you the platform on a demo and send specifications and pricing for your team.