slytes gives researchers and teachers one workspace with verified literature, writing, a private sandbox with an AI agent, one-click AI apps and AI-made presentations. No setup, no DevOps, no copying between tools.
Free during beta. Built by a researcher, used for real thesis work.
slytes.com / workspace / aqpso-vqc
Used to research, write and cite a real master's thesis proposal
Built on Cloudflare
Isolated sandbox per user
The problem
Research is split across eight tools, and AI code has nowhere safe to run.
Your work lives in pieces
Papers in one tool, writing in another, code in Colab, and an AI chat that can't see any of your files.
AI code runs unguarded
AI-written code runs next to real data and credentials on laptops and lab servers, with no isolation.
Prototypes die in notebooks
A good model never reaches anyone, because there's no path from a notebook to a running app.
Slides rebuilt by hand
Every talk, defence and lecture means rebuilding slides and notes from scratch.
How it works
Five steps. One workspace.
Everything from the first paper to the final talk happens in the same place, with an AI that can see all of it.
01
Read
Upload papers. Each becomes a paper card of verified findings, with the exact quote and page. Semantic search across the collection.
Live
02
Write
LaTeX or Markdown with a live PDF preview. Every AI citation is checked word for word against the paper and recorded.
Live
03
Build
Your own VS Code and Jupyter in an isolated sandbox, with an AI agent that runs code there. You choose Ask, Approve or Auto.
Live
04
Ship
One click turns a project into a live AI app (Python, Node or static), built from hardened templates.
Live
05
Present
The AI drafts the deck, speaker script with timings, likely Q&A and a numbers cheat sheet, grounded in your work.
New
It asks before it assumesQuestion cards with clickable answers: which template, where to save, audience, length.
You see it workingA live status line and timers on every step, so you always know what the AI is doing.
Shared workspacesBring in your supervisor, co-authors and lab members.
Why slytes
Built for work that has to hold up.
Verified citations
Citations you can trust.
Every finding on a paper card carries the sentence copied from the PDF and its page. When the AI cites, the quote is checked against the paper and written to a ledger, so a citation can't drift later.
Findings verified word for word against the PDF text
Each finding states its scope, so you don't cite past it
University thesis templates followed exactly
Sandbox and agent
A real sandbox, not a chat.
Each user gets a private VS Code and Jupyter environment. The AI agent (Claude or Codex) edits files and runs code there, and asks for your OK on anything that matters.
Permission levels: Ask, Approve or Auto
Approval cards in the chat before deploys
Credentials stored per workspace, never in your code
One-click AI apps
From research to production in the same place.
Put a model or tool in front of people without handing it to DevOps. Apps are built from hardened templates and keep running until you turn them off.
Python, Node or static sites
Non-root, read-only filesystem, isolated network
Members-only by default, public when you choose
AI presentations
Decks made from your actual work.
The AI drafts slides from your papers, code and results, together with a timed speaker script, likely questions and answers, a closing and a numbers cheat sheet.
Presenter view with a timer and a separate audience window
Motion, 3D scenes and embedded video
Every deck kept in a gallery for your next talk
Who it's for
For the people doing the research, and the people teaching it.
Researchers
PhD students, postdocs and labs
In AI, quantum and data science, where the work spans papers, code and a thesis.
One home for literature, writing and experiments
AI-written code runs isolated from your data and keys
Turn a prototype into an app your lab can use
Defence and progress decks drafted from your work
Teachers
Lecturers and course leads
Who build slides, notes and demos for every class, and want students to try AI safely.
Slides and notes drafted from your material
Small AI tools for class, shipped in one click
A safe sandbox for each student
Shared workspaces for co-teaching
Security and trust
Your data stays in your workspace.
slytes was designed on the assumption that AI-written code shouldn't be trusted by default.
Isolated sandboxes
Each user's IDE and agent run in their own container, apart from other users and the server.
Hardened apps
Apps run as non-root on a read-only filesystem with no Linux capabilities, their own network and set limits.
Approval before action
You choose how much the agent can do alone. Deploying or deleting an app always needs your OK.
Private by default
Workspaces are visible only to you until you invite someone by name. Secrets never go into images.
Early access
Free during beta.
We're opening slytes to researchers and teaching teams in small groups. Join the waitlist and we'll be in touch.
Researcher
PhD, postdoc, independent
Workspace, AI agent, sandbox IDE, a live app and the presenter.
Lab
3 to 20 seats
Shared workspaces, more apps, compute based on usage.
Classroom
Lecturers and courses
A sandbox per student, AI slides and notes.
Institution
Universities
SSO, data region, admin and audit.
Talk to us
FAQ
Questions
Which AI models does slytes use?
The agent runs on Claude or Codex, and you pick the model per conversation. More providers can be added for institutions.
Is my code isolated?
Yes. Your IDE and the agent run in your own sandbox container. Published apps run as non-root on a read-only filesystem with their own network, and secrets are kept out of the image.
Can I trust the citations the AI writes?
Each citation is tied to a finding on a paper card, which holds the exact sentence from the PDF and its page. The quote is checked word for word and recorded in a ledger when the text is written, so it isn't re-guessed later.
Can my supervisor or co-authors join?
Yes. Invite them by username to a shared workspace. Members can see and edit everything inside, and only the owner can invite, remove, rename or delete.
Where is my data stored?
In your workspace on slytes servers, separate from other users. Data region options for institutions are on the roadmap. Write to us if you have specific requirements.
How much does it cost?
It's free during the beta. Researcher, Lab, Classroom and Institution plans are coming, and waitlist members will hear about pricing first.
Get started
Start your research workspace.
Read, write, build, ship and present, all in one place.
