# Managed OpenScience hosting: own the open-source Claude Science workbench

> Run OpenScience on a Firecracker microVM — literature, code, experiments, and write-up in one browser workspace. BYOK, persistent home, snapshot/fork. No shared containers.

- Published: 2026-07-15 · Updated: 2026-07-15 · jurniti
- Canonical: https://www.jurniti.com/blog/openscience-hosting

**OpenScience** is the open-source AI workbench people mean when they say “Claude for science” without the black box.

You give it a research goal. It reads the literature (arXiv, Semantic Scholar, OpenAlex), forms a hypothesis, writes and runs code, hits scientific databases (UniProt, PDB, ChEMBL, PubChem, …), and writes up what it found. Specialist agents for **research**, **ml**, **biology**, and **physics**. Two hundred ninety-plus skills. A real browser workspace — file tree, editor, terminal, inline molecules and plots.

What it is *not*: a shared SaaS notebook that holds your keys and meters your model spend.

## The problem with “just run it locally”

`npm install -g @synsci/openscience && openscience` works — until it doesn’t.

- Your laptop sleeps. The literature sweep dies mid-session.
- A VPS is a snowflake: Node, ports, reverse proxy, backups, “who has sudo.”
- The workspace binds **loopback only** by design. Fine on a desktop; painful when you want a stable HTTPS URL from another machine.
- Credentials land in XDG dirs under `$HOME`. Snapshot carelessly and you ship API keys with the template.

Scientists and ML engineers want the agent **always on**, **isolated**, and **theirs** — keys inside the box, not proxy-marked-up through a vendor.

## What managed OpenScience on jurniti actually is

One Firecracker microVM per tenant. Same hardware isolation primitive AWS uses for Lambda.

| You get | Why it matters |
| --- | --- |
| Pre-baked OpenScience workspace | No install theatre. Open the browser UI on a public TLS subdomain. |
| Persistent `/home` | Projects, config, and skills survive restarts. Snapshot → template → fork. |
| BYOK | Anthropic / OpenAI / Gemini / OpenRouter / … Keys stay in the microVM. jurniti never sits on the model path. |
| Isolation | Not a Docker sidecar next to someone else’s agent. Real KVM boundary. |

Pricing is flat per VM (Starter / Pro / Max). OpenScience’s research workbench is **Pro floor** — the agent + workspace need headroom Starter’s 2 GiB doesn’t have.

## Who this is for

- **ML researchers** who want a co-scientist that can lit-review, scaffold training/eval, and write methods — without babysitting a laptop process.
- **Comp-bio / structural biology** teams who need UniProt/PDB/ChEMBL in the tool loop and a workspace that doesn’t share a kernel with strangers.
- **Labs and indie PIs** who refuse to put grant-funded keys into a multi-tenant chat product.

If you only want a chat UI and a free tier, this is the wrong product. If you want ownership, keep reading.

## How provision works (about three minutes)

1. Pick **OpenScience** at checkout (Pro or Max).
2. Stripe confirms → fleet assigns a host → microVM boots the pre-baked rootfs.
3. Open the workspace URL. Add a provider key (`openscience keys add` or the Credentials panel).
4. Give it a goal. Use `ml` or `biology` when the default research agent isn’t the right specialist.

No founder SSH. No “we’ll set it up for you on Tuesday.”

## Templates: don’t start from zero

Two high-signal public templates (when founder-gated live):

1. **AI/ML Research Co-Scientist** — lit → hypothesis → train/eval scaffold → write-up.
2. **Comp-Bio / Structural Biology Research Agent** — target/structure queries against real scientific DBs → grounded brief.

Fork → BYOK → one concrete research goal. That’s the aha.

## OpenScience vs “just use ChatGPT with papers”

Chat products summarize PDFs you paste. OpenScience **runs the loop**: tools, code, databases, multi-step sessions, artifacts on disk. You can export, snapshot, and take the upstream agent elsewhere — Apache-2.0, no jurniti fork required.

## FAQ

**Do I need Atlas (Synthetic Sciences’ managed wallet)?**  
No. BYOK is first-class. Atlas is optional.

**Can I use it headless?**  
Yes — `openscience serve` is the headless path. On jurniti the portal reverse-proxies the workspace so you get HTTPS without fighting loopback bind.

**Is my data used to train someone else’s model?**  
Not by jurniti. Your keys, your provider, your persist volume. Templates scrub auth and sessions before public share.

**Why not E2B / a generic sandbox?**  
Those are code-execution sandboxes. This is a **managed agent harness** with a full research workspace, billing, templates, and fleet that only rents boxes when prepaid cash covers them.

## Get started

[Managed OpenScience on jurniti](/openscience) — or the free [7-Day OpenScience Setup](/setup/openscience) if you want the ownership arc first.

Build the science. Own the agent.

## Frequently asked questions

### What is OpenScience?

OpenScience is an open-source AI research workbench — literature search, code, experiments, and write-up in one browser workspace. Specialist agents cover research, ML, biology, and physics, with 290+ skills and a real file tree, editor, terminal, and inline molecules/plots. It is bring-your-own-key and not a shared SaaS notebook.

### Can I run OpenScience on a server instead of my laptop?

Yes. The upstream install works on any box, but laptops sleep mid literature sweep and a snowflake VPS becomes its own ops burden. jurniti runs OpenScience on an always-on Firecracker microVM with a persistent home, so long research sessions keep running after you close the lid.

### Do I need my own API key for OpenScience?

Yes. jurniti is bring-your-own-key — your model keys live only inside your microVM. We never proxy or mark up token spend. Credentials stay on the persist volume under your home, not on a shared multi-tenant runtime.

### Why a microVM instead of a shared container or notebook SaaS?

OpenScience holds API keys and research data. A dedicated Firecracker microVM gives each tenant its own kernel and KVM hardware isolation — the same class of boundary used for serverless at scale — instead of sharing a host kernel with other users' workloads.

### How much does managed OpenScience hosting cost?

Plans start at $25/mo, or $250/year (two months free). Every plan includes a 30-day money-back guarantee on first purchase. Model spend is separate and unmarked-up because you bring your own key.

### Is this the official OpenScience product?

No. jurniti is independent managed hosting for the open-source OpenScience runtime. We install the upstream package into your microVM at first boot — no fork of the workbench itself — so you get the real agent and skill ecosystem.