Everything Vanyx does.

Vera doesn't just talk — she runs the work, chaining Python simulations, formal proofs, literature searches, and symbolic math into a single grounded answer. Every tool run shows up as a rich card right inside the conversation, so you can watch the evidence assemble in real time. Nothing is a black box, and results are saved so you can build on them later.

Turn on Auto and Vera reads each message to choose the best model and the exact tools for the job — a quick question stays fast and lightweight, 'prove this theorem' brings in Lean and Z3, and 'simulate this' reaches for Python. You never touch a menu, and there's no speed penalty for the routing. Verified knowledge is always captured as you go.

The chatbar offers exactly the choice that matters: Vera 1 (the full-depth default) and Vera Velocity (fast and inexpensive). Both are the same Vera — same tools, same verification, same honesty — and your pick sticks per project. Under the hood, formal goals still route to specialist provers automatically; collapsing the menu is presentation, never capability.

Switch Vera's abilities on or off for each chat: run Python, build interactive surfaces, do symbolic math, write formal proofs in Lean, solve logic with Z3, search the literature, query math databases, remember verified facts, and design quantum circuits. Mix and match exactly what a problem needs, and your choices are remembered for next time. Advanced abilities like quantum stay tucked away until you want them.

Attach up to three files per message — PDFs, Word documents, spreadsheets, or plain text up to 5 MB each — by dragging, pasting, or browsing. Vera pulls out the actual text and data so she can reason over your document directly, without you copying and pasting anything. It's the fastest way to put your own material in front of the co-scientist.

Drop in a PNG, JPG, or other image and Vera can read the graph, interpret a handwritten note, or reason over a diagram or photo — all inline, with no extra tools. It's ideal for making sense of visual results, whiteboard snapshots, or figures from a paper. She sees exactly what you see.

Say "pull up the blackboard and show me Einstein's field equations" and a glass chalkboard appears with the equations writing themselves in as Vera explains — real typeset math, sketches, arrows, and callouts in six chalk colors. You draw on the same glass with your finger or mouse, open up to ten boards at once (each addressable by voice — "board 3"), and save any board straight into your knowledge library. Everything written on a board flows into the conversation, so Vera always knows what's on the glass.

Ask for your agents and the panel opens; ask for a derivation and a blackboard appears; ask to keep a simulation handy and she docks it beside the chat. A subtle pulse shows when Vera is driving, and a single autopilot toggle puts her in manual mode where she describes actions instead of taking them — you are always sovereign.

Share any window and a crisp snapshot lands in your next message, giving Vera a clear view of what's on your screen. From there she can help debug, explain, or act on whatever you're looking at. No describing it in words — just show her.

As Vera works, every tool run renders as a clean, purpose-built card inside her reply — arXiv results show titles, authors, dates, and PDF links; Semantic Scholar surfaces citation counts; LMFDB and OEIS display their structured math data; and extracted data lands in tidy tables. Math is beautifully typeset and code is syntax-highlighted. One-click copy buttons let you grab any code or data instantly.

Every conversation saves automatically and reopens with all its tool results still in place, so you can pick up right where you left off. Keep things organized by pinning important chats, renaming them inline, archiving ones you're done with, or deleting them outright. Your research history stays at your fingertips.

The Lean 4 proof assistant compiles your argument and certifies it only when the proof is complete and airtight, so a passing result is a real guarantee, not an opinion. Every proof is screened for gaps (placeholder holes left where a step should be), for sneaked-in assumptions, and for shortcuts that trust the compiler instead of the logic. Only proofs the Lean kernel fully verifies earn a pass, and each one is stamped with a reproducible fingerprint so anyone can confirm it later.

Instead of a one-shot attempt, Vera works like a determined mathematician: it drafts a proof, sees precisely which steps failed and which goals are still open, and revises again and again. The loop stops when the proof is fully verified, when it runs out of attempts or time, or when it stops making progress. The outcome is either a complete, machine-verified proof or an honest "inconclusive" with the full trail — never a confident bluff.

A proof that quietly assumes its own conclusion looks like it compiles but proves nothing — so after a proof passes, we list exactly which foundational assumptions each theorem relies on and flag anything beyond the small trusted core the Lean kernel is built on. Shortcuts that trust the compiler rather than the logic are flagged too and can never earn the top "gold" rating. Each verified proof also gets a compact fingerprint, letting anyone confirm offline that it is exactly reproducible.

You get the complete mathematical library — algebra, topology, analysis, number theory, combinatorics — as building blocks for your own proofs, the broadest foundation available anywhere. Because the library is pre-loaded, proofs that import it compile in roughly a second instead of the usual half-minute wait, so iterating on a proof feels fast rather than painful.

Finding the right lemma in a library of over 100,000 usually means hours of manual digging. Instead, describe what you want — "sum of the first n natural numbers," a partial name, or the shape of the statement — and Loogle returns the matching Mathlib results with their exact names, statements, and where to import them from. Searching by the shape of a statement is especially powerful for surfacing every theorem that fits a given form.

Before investing days in a full proof, hand a claim to Z3 as a fast sanity check: it either finds actual values that satisfy your constraints, proves the constraints are contradictory, or hunts for a concrete counterexample that falsifies a conjecture. Many wrong conjectures get knocked down in seconds this way, saving you from chasing a proof of something false. It handles integers, real numbers, bit-level arithmetic, and nonlinear problems, and always halts within a time limit so a hard problem can never hang.

Powered by Wolfram Alpha, this returns exact closed-form results for problems like integrating x² sin(x), solving a quartic equation, or evaluating a special function, plus curated scientific data such as physical constants. Ask for steps and you get a worked solution trace, not just the answer. It complements the solver and proof tools: use it to double-check numerical results from simulations and to crack symbolic problems a constraint solver can't reach.

Rather than a single "review my paper" pass, your manuscript is handed to three concurrent referees with different missions: one checks rigor and methodology by actually re-testing derivations with the solver and Wolfram, one hunts for prior work and over-claiming by searching arXiv, and one re-runs your computational claims in Python to check reproducibility. Each returns a recommendation (accept, minor, major, or reject) with a confidence level, and an editor synthesizes them into one decision plus a concrete, prioritized list of fixes. Because the referees can genuinely falsify a claim rather than just voice concern, the feedback is real and actionable.

Vera generates several diverse, falsifiable hypotheses and puts each through a verification gauntlet: Z3 tries to find a counterexample, Wolfram checks the symbolic claims, Python re-runs the computations, arXiv is searched for supporting or conflicting prior work, and a formal Lean proof is attempted. Every hypothesis earns a verdict — supported, refuted, or inconclusive — based on evidence, and a hypothesis backed by a complete formal proof is elevated to "gold" and ranked at the top. Refuted ideas are disqualified, so what you're left with is a machine-verified finding rather than the winner of a debate.

As you cite sources, each one is quietly checked against the scholarly retraction database using two independent signals so a genuine retraction is caught reliably. The check is deliberately cautious: an unrecognized reference or a momentary network hiccup never produces a false alarm, but a confirmed retraction always raises a clear warning. It keeps discredited results from silently propagating into your work.

This panel is the living audit trail of your project's formal work: it shows whether the latest proof is machine-verified, how many proofs have passed, and an expandable history of every attempt. Each entry reveals its status, the proof itself, any errors or open goals, its reproducibility fingerprint, and when it ran — so you can always see exactly what has been proven and what still needs work.

An extended version of Mathlib called PhysLib will add quantum mechanics, relativity, and physical constants as formally verified foundations, letting quantum gates, conservation laws, and physical theorems be checked the same rigorous way math proofs are today. The verifier already recognizes physics proofs and points you in the right direction when it sees them. This capability is in progress and not yet switched on by default.

Ask a question and Vera writes and runs real Python code in a private cloud workspace, with the standard scientific toolkit (numpy, scipy, sympy, mpmath, matplotlib) ready to go. The workspace boots almost instantly, stays isolated from the network and your data, and shuts down on its own so you only use compute when you need it. You get genuine numerical results, not a plausible-sounding guess.

When your code generates a chart or figure, it shows up right in the chat next to the results, no screenshots or downloads required. Line plots, histograms, 3D surfaces, and interactive visualizations all render in place as the simulation runs. It feels like watching the analysis unfold in front of you.

Describe or write a quantum circuit and run it directly in the conversation. Add measurements to get realistic sampled outcomes (up to 8,192 shots), or leave them off to see the exact probabilities. It supports the full range of real quantum work, from superposition and entanglement to classic algorithms like Grover's search and the quantum Fourier transform.

Turn on real-hardware mode and your circuit is sent to the least-busy available IBM Quantum machine to run on actual qubits. If the hardware is queued up, offline, or unavailable, it quietly falls back to a local simulation so you always get a result. No configuration or waiting for a slot to babysit.

Every autonomous research run and hypothesis tournament can be exported as a standard Jupyter notebook that anyone can open and re-run line by line. It captures the real code, printed output, and every chart alongside the written report, plus notes on how the run was set up. Reviewers and collaborators can verify your results themselves using only standard Python packages.

After a literature search, pull the details you care about out of the papers and into a single comparison table. Every row is a real paper linked to its source (arXiv, DOI, or Semantic Scholar), every column is a field you define, and anything the paper doesn't state is honestly marked 'not reported' rather than guessed. You get a grounded, citable overview of a research area in one view.

Just describe what you want to see and a self-contained interactive visualization renders instantly in the conversation, no download or setup required. Drag sliders, watch animations, and explore simulations that respond to you in real time. Each surface stays in your chat history and comes right back when you reload the page.

One click (or one ask) pops a surface out into its own window — drag it anywhere on screen and resize it from the corner. From there Vera can drive it herself: pause it, restart it, and adjust the very parameters the simulation exposes, narrating as she goes. It turns a visualization into a live instrument the two of you operate together.

Every surface comes with built-in controls to freeze an animation on any frame, replay it from the start, or pop it out into a floating window you can move and resize. It puts you in the driver's seat of the simulation. The chat card stays put, so you never lose the original.

Surfaces can build full three-dimensional worlds on demand, from spinning molecules and orbital mechanics to interactive geometry you rotate with your mouse. Lighting, cameras, and smooth animation are all handled for you. It runs at full frame rate right inside the chat.

Ask for a visualization and surfaces produce publication-quality charts, scatter plots, histograms, heatmaps, and even 3D plots, all with built-in zoom, pan, and hover-to-inspect. Custom data-driven graphics with live transitions and interactive filtering are just as easy. Everything scales cleanly to fit the surface and respects the playback controls.

Surfaces run in a locked-down space that blocks all outgoing connections, pop-ups, and access to the rest of your session. The AI-written code inside simply cannot phone home or leak your information. You get interactive power without giving anything up.

Datasets, constants, and configuration are baked straight into a surface when it's created, so everything is ready the moment it appears. There are no network calls or loading spinners to wait on. It keeps surfaces fast and fully self-contained.

Each surface can be styled with your chosen accent color and adapts its typography to read well at any size. The transparent background lets it sit naturally in the flow of the conversation. The result feels like a native part of your workspace, not a bolted-on frame.

A surface automatically grows and shrinks to match whatever it's showing, staying neatly framed as content animates in and out. You get a clean, seamless embed every time, with no clipped visuals or dead space. It just fits.

When something goes wrong inside a surface, it displays a visible, easy-to-read error notice right where the surface would be. The rest of your conversation keeps working normally, completely unaffected. Problems stay contained so nothing else breaks.

Search more than 220 million papers by describing what you actually mean, not just matching keywords, so the most relevant work rises to the top even when it uses different terminology. Each result shows citation counts, how influential a paper is, and a link to a free full-text PDF when one exists. Narrow by year to focus on the most recent thinking or trace an idea back to its origins.

Ask Vera to search arXiv's full preprint archive by topic or subject area and get back up to 25 clean, structured papers sorted with the newest first. Every result includes the abstract, the author list, a link to the paper's page, and a direct PDF link when available. It is the fastest way to see what was posted in your field this week, right inside the conversation.

Point Vera at any paper and it pulls up the works that cite it, letting you trace an idea forward through the literature in seconds. Each citing paper comes with its own citation counts and authors, so you can gauge real-world impact and spot the follow-up research that matters. It turns a single starting paper into a map of its intellectual lineage.

Every source Vera draws on is captured and turned into numbered citations you can click, backed by a clean reference list at the end of the answer. Because the citations come only from papers Vera actually retrieved during your conversation, there are no invented sources and no broken links. You always know exactly where a claim came from and can verify it in one click.

After pulling up a set of papers, ask Vera to lay them side by side in a single table covering methods, sample sizes, effect sizes, and outcomes. Every row links back to the paper it came from, and anything a paper does not actually report is honestly marked as such instead of guessed. What would be an afternoon of manual note-taking becomes a clear comparison you can read at a glance.

When a calculation or simulation spits out a run of integers, Vera checks it against the On-Line Encyclopedia of Integer Sequences and its 370,000+ catalogued sequences. A match instantly tells you whether your mystery numbers have a known closed-form, connect to a published theorem, or show up in a surprising corner of math. Each hit comes with the sequence's name, formulas, and references so you can follow the thread.

Vera pulls hard mathematical facts directly from the L-functions and Modular Forms Database: over 100 billion Riemann zeta zeros at extraordinary precision, elliptic curves, classical modular forms, number fields, and more. These are exact, authoritative values, not approximations, so you can build on them with confidence. It is like having a reference library of verified number theory answer its own questions on demand.

Keep any result worth remembering, a summary, a snippet of code, a dataset, a derived equation, in a lasting library tied to your project. Pin any of these anchors into future conversations so Vera carries your best findings forward instead of starting cold each time. Everything is tagged with its verification status, and items Vera created are clearly marked so you always know what is yours versus what was generated.

As you save findings, they automatically link up to related ones by meaning, growing into a web of connected knowledge rather than a flat pile of notes. When you ask a question, Vera can pull not just the closest match but the whole cluster around it, reasoning over related ideas the way a well-read colleague would. One switch sets how far recall reaches: keep it tight to the project at hand, or open it up to connect insights across all of your past work, and Vera widens the net on its own when a question clearly calls for it.

Researchers can choose to share their verified results, such as machine-checked proofs and confirmed facts, into a shared pool that makes Vera sharper for everyone. Whenever one person's verified result helps answer someone else's question, the original contributor is credited and stays discoverable. Sharing is always opt-in and can be turned off at any time, and your private work never enters the pool.

Browse a curated, ever-changing gallery of open Grand Challenge problems spanning math, physics, biology, and beyond. Each card lays out the problem, the current best-known results, and a single click that drops you into a workspace already primed with the context Vera needs to start real research. As the community cracks existing challenges, fresh frontiers take their place.

Give an agent a research goal and it works the problem for you — searching arXiv, running Python simulations, checking answers with the Z3 solver and Wolfram, and looking up sequences in OEIS and LMFDB. It reasons across multiple steps, then writes up a synthesized report and drops the result straight into your project chat. You can close the tab and come back later; the run keeps going without you.

Watch every running and queued agent in one place, with live timers, a rolling feed of the tools each one is using, and running totals for how many agents finished, how many hit errors, and what it all cost today. The moment an agent completes, its result appears in your chat and the deck updates instantly. It's the fastest way to see what your research fleet is up to at a glance.

See a two-week timeline of your costs and activity, the status of every run with downloadable notebooks, and a breakdown of which tools (Python, Wolfram, Z3, arXiv, Quantum, Lean, and more) you use most and what each one costs. A live feed shows tool activity as it happens, and you can cancel any queued or running agent with one click. Everything updates in real time, so the picture is always current.

The Vera Co-Scientist works open Grand Challenges autonomously, generating hypotheses and putting each one through the same rigorous verification the rest of the platform uses, then banking any confirmed winner as a public solution. Every finding carries its full evidence trail — the model used, the tools it called, and the verification outcome — so you can trust the result and trace exactly how it got there. These confirmed discoveries also help make the platform's models smarter over time.

Every agent run — research, tournaments, verification, and peer review — is queued so it can't be lost if you close your browser or the platform restarts mid-run. A background worker picks up each job, carries it through to completion, and makes sure billing and wrap-up always happen, even if a run crashes partway. When it's done, the result appears in your project chat automatically.

There's a cap on how many agents you can have running or queued at the same time across all your projects, which keeps costs predictable and the platform responsive. It's the same generous ceiling for everyone — commit plans raise your throughput and priority, never your capabilities. If you hit it, just wait for a slot to finish.

Instead of nickel-and-diming every step, an agent tallies everything it uses along the way — model tokens, premium tools like Python, Wolfram, Z3, and Lean, and every tool call — and charges you exactly once when it finishes. The charge lands whether the run succeeds or fails partway, so nothing slips through, and the final cost is recorded for you to review. If you bring your own model keys, only the platform-funded tools are billed.

Bring-your-own-key support (your own xAI, OpenAI, Anthropic, or Google account funding the model side) is built and stored securely, currently behind an operator switch while usage-first pricing settles. When enabled, your agents run on your keys with platform-funded tools like Python, Wolfram, Z3, and Lean still metered through your credits.

Talk to Vera and hear her spoken answers come back immediately as she works, no typing required. Start speaking while she's talking and she stops to listen, just like a real conversation. Every word from both of you appears in a transcript you can open above the chat box to read back anytime.

During a voice call, Vera acts on your spoken commands so you never touch the keyboard. Ask her to add a section to your manuscript, search the literature, or launch an agent to investigate a problem, and she does it while keeping you informed out loud. Results flow back both spoken and written into your chat.

Ask for papers on a topic and Vera searches arXiv, summarizes what she finds in her own voice, and drops the results into your chat. Request a Python simulation mid-conversation and the output appears both spoken and in text. Kick off a background research agent by voice and Vera lets you know the moment it finishes.

While you're on a voice call, Vera stays aware of what's visible — your chat, manuscript, agent results, and main content — so she can answer questions about what's in front of you. She never interrupts to announce it; she only uses it when you ask. You can turn this off in voice settings anytime if you prefer to keep your screen private.

Say something like "add a section on quantum error mitigation to my manuscript" and Vera drafts the text and drops it into your document instantly. The new writing also appears in your chat so nothing is lost. Your manuscript stays in sync with the conversation as it unfolds.

Vera keeps an eye on the research agents running in the background while you talk. When one wraps up, she brings it up naturally in conversation — letting you know the results are ready and offering to summarize them or show you the raw findings. You stay focused on the discussion while your agents work in parallel.

The transcript stays tucked away by default to keep your chat clean, and opens whenever you want to read the full back-and-forth. Vera's turns and yours are visually distinct so it's always clear who said what. It scrolls to the latest line automatically as the conversation flows.

Whenever Vera is speaking and you start talking, she stops on a dime and shifts to listening, just like a person would. There's no awkward lag — interruption is built into the live conversation. It makes talking to Vera feel natural instead of waiting for her to finish.

You can freely mix talking and typing during a voice call. Messages you type — and results Vera pulls up from her tools — are folded into what she knows, so she picks up right where the conversation left off. Voice and text feel like one seamless thread rather than two separate channels.

Voice conversations meter per second against your one prepaid balance, exactly like every other tool — minutes are just how the time is displayed. There's no monthly allowance to run out of and nothing resets; you simply top up when your balance runs low, and a live meter shows the session's cost as you talk.

Tap the microphone in the chat bar and your speech turns into text in real time as you talk, so you can see it forming. Stop, and the finished text lands in the box ready for you to review and send. It's a fast way to compose messages hands-free without starting a full voice call.

Pick the voice that feels right to you and it sticks across your conversations. Eve is the default, and you can switch anytime. Every voice carries the same intelligence and responsiveness — only the tone changes.

As you work with Vera, your manuscript writes itself — pulling the core claims, formulas, and findings out of the whole conversation and shaping them into a publication-ready paper. It holds to top-journal standards, with clean academic structure and fully rendered mathematics. Every sync also runs a quick audit that predicts the paper's novelty and validity on the Sigma scale, so you always know where it stands.

Send any finished manuscript to the global archive where it becomes publicly readable and permanently attributed to you. As it publishes, Vera writes a two-to-three sentence abstract and assigns one to three subject tags (like Physics or Computer Science) so readers can find it. The paper lands in the archive with its abstract, tags, Sigma score, author, and date, searchable and filterable by the whole community.

An expert-level audit rates each paper from 0 to 100 on novelty, empirical logic, and mathematical depth. That single score follows the paper everywhere and powers ranking across the platform, so strong work rises to the top. Readers can filter the public archive by a minimum Sigma threshold to see only the most rigorous papers.

Patent Studio turns your research into a complete provisional patent application with every section the USPTO expects — Title, Background, Summary, Detailed Description, and a full claim set (at least three independent and seven-plus dependent claims). The draft is structured to establish your priority date and cover the full scope of your invention. Export it as a line-numbered PDF for attorney review, or as editable LaTeX for filing, and see a Sigma audit of its strength.

Compile your work on demand into a polished PDF with proper typography, margins, and fully rendered mathematics — the quality journals and patent offices expect. Patent documents come with the line-numbered margins standard in USPTO filings. Preview it inline or download the file directly.

Download a ready-to-edit LaTeX file with the right document class and all the standard packages already included, so it is submission-ready with almost no cleanup. Manuscripts come formatted for arXiv and academic journals; patents come with legal-standard formatting, line numbers, and one-inch margins for attorney review or direct filing.

Turn your manuscript into a tidy, print-styled page that opens straight to your browser's print or save-as-PDF dialog. It is the fast, lightweight way to share a draft or archive your work when you don't need full typesetting.

The public archive shows every published paper in a responsive grid, each card carrying its title, abstract, Sigma badge, topic tags, author, and date. Slide the Sigma filter to instantly narrow the view to only the highest-rigor work. Open any paper to read it in full, with every inline and display equation rendered live and beautifully alongside the prose.

On every published paper, signed-in researchers can leave a one-to-five star rating and a written critique that appears publicly, newest first, with the reviewer's name and date. Each person can review a given paper once, and reviews are rate-limited, keeping feedback genuine and spam-free. It's open, transparent peer review that helps readers judge the work at a glance.

Describe a scene and Vera renders a short video for you — opened from the same create menu as manuscripts and surfaces. The clip is saved to your project and downloadable. Metered from your balance like every other tool.

Every Grand Challenge—from the Riemann Hypothesis to room-temperature superconductivity—is its own research frontier with a dedicated leaderboard, community, and vault of machine-verified findings. Click any challenge to join, watch live autonomous discoveries as they happen, and start contributing with full transparency on exactly what has already been proven.

Each challenge has its own live leaderboard, and a global board aggregates every researcher across all challenges. Rankings are computed in real time from verified work: formally checked proofs, published manuscripts, research projects, and confirmed knowledge anchors, each weighted differently. You rise by what you actually prove and publish, and every name links to a full researcher profile.

A public profile shows your total Contribution Score alongside your verified proofs, published manuscripts, and research projects, with a per-challenge breakdown so anyone can see exactly which work earned your rank. The score is computed live from machine-verified results—no self-assessment and nothing you can game. Anyone can visit your profile by username, and it travels with you everywhere on the platform.

When a later finding builds on your verified proofs, facts, or knowledge anchors, you receive named attribution that stays with you in perpetuity. You can always trace your impact chain—which of your contributions influenced downstream discoveries—while keeping full ownership of your own work.

Once a paper is published to the global archive, any signed-in researcher can leave a star rating and written assessment. Reviews go live immediately with no approval gate—each appears publicly with the reviewer's name, timestamp, and rating. You can review each paper once, and light rate limits keep the feed free of spam.

Every Grand Challenge comes with a dedicated community where members chat, coordinate, and share findings, and the Vanyx Commons Town Square sits above them all for cross-frontier discussion. A searchable directory lists every public community with its name, description, and member count, so you can find one around your interests and join in a single click.

Sign in, name your community, add a description, and choose public (anyone can join) or private (invite only). It's ready instantly with a general text channel and a voice lounge already set up, and you're the owner with full moderator control. Public communities appear in the searchable directory; private ones stay hidden and open only to people you invite—ideal for labs, sensitive research, or closed teams.

Owners and moderators can add as many text and voice channels as they need, and mark any of them private so only selected members can read and post. This lets a single community hold open discussion, topic-specific research spaces, and closed admin coordination without ever splitting into separate servers.

Community channels update instantly—messages appear the moment they're sent, and typing indicators show who is composing right now. Mention @vera to summon Vera Co-Scientist directly in the channel, where her answer posts as a reply visible to the whole group. History loads smoothly as you scroll back, and authors and moderators can remove their own or others' messages.

Community owners and moderators can remove any message instantly to keep channels focused and on-topic, without having to ban whole accounts. On top of that, automatic moderation screens every message for spam, slurs, and scam patterns and blocks offending posts before they ever appear, with a brief reason shown to the sender.

Each voice channel shows a live stage with everyone currently present, displayed by name alongside a chat sidebar so listeners can comment as speakers talk. Joining instantly puts your name in front of the group, and you can step back to text-only chat anytime. Live audio is the next phase.

Each community shows a roster of its members with names, join dates, and roles such as owner, moderator, or member. The list refreshes in real time as new people arrive, and clicking any member jumps straight to their researcher profile.

Your joined communities line up in a side rail ordered by recent activity, with the Vanyx Commons Town Square always pinned first. Click any one to jump straight into its channels and members. Leave a community to remove it from the rail, and rejoin whenever you like.

Click Join on any Grand Challenge to become an active participant, and your projects, proofs, and publications on that frontier immediately begin counting toward its leaderboard. Your membership is timestamped, and you can rejoin or reactivate at any time.

Every challenge carries a clear, color-coded status badge—open, partially solved, or solved—so you know instantly whether a problem is wide open or already showing major progress. It helps you pick where to focus and sets the context for the work still to be done.

There are no power tiers and no feature walls: every account gets 100% of Vera's capabilities. A welcome grant lets you taste it with no card at all; after that you top up a prepaid balance that never expires, with optional auto-rebill so you never stall mid-derivation. Every action shows its cost, so usage-billing always feels fair.

Researcher ($20/mo) and Lab ($200/mo) are pure volume discounts: the monthly fee is 100% credit value at a cheaper rate, plus higher throughput, priority, and concurrency. They never change what Vera can do — everyone already has everything. Use beyond your included credits and it simply bills at the pay-as-you-go rate; cancel anytime and your banked credits stay yours forever.

Plug in any OpenAI-compatible model by adding its address and an optional key in settings, whether it runs locally, is privately hosted, or is your own fine-tune. Each connection is tested before it's saved and stored securely, then appears in your model picker ready to use in chat. Built-in safety checks block connections to internal or private network addresses.

Create, rename, archive, and delete projects, and sort them by date or filter down to the ones that led to a published paper or patent. Full-text search finds anything by name across all your work. Your dashboard shows recent projects at a glance with document counts and dates.

Set a public display name, pick a custom accent color that instantly recolors the whole interface, and upload your own logo (up to 2MB) to replace the Vanyx wordmark — turning the workspace into a branded lab. Every change applies live, the moment you make it. Like everything here, it's included for everyone.

Your billing settings show your prepaid balance (which never expires), your per-credit rate, and your plan. Top up in one click, enable auto-rebill so long runs never stall, and open the secure portal to manage payment methods, invoices, or your commit plan. Complimentary and admin accounts are clearly marked as such.

From your account settings you control exactly how your work is used: opt in or out of letting your verified work help train future models, and opt in or out of sharing your knowledge. You can permanently erase all the data you've contributed, or delete your entire account and everything you own — which automatically cancels your subscription first. Password changes live here too.

Land on Vanyx and start chatting right away as a guest — no email needed. When you ask your first real question or start a project, a single email box appears that either signs you in as a returning user or creates a new account on the spot, with your work carried over seamlessly. Guests can browse public challenges, communities, and papers, and sign in whenever they want to post or join.

Press ⌘K (or Ctrl+K) and type. Anything you write can start a new chat instantly ("solve: …"), or pick from the list to open a workbench app or jump to any page. Pick an app before you even open a chat and it's waiting for you when the workspace loads. Built keyboard-first, like a professional instrument should be.

The left rail hosts your workbench: click an icon and that app docks next to the conversation; drag the divider to resize, or pop any app out into its own draggable, resizable floating window. On your phone the same apps live in a real bottom tab bar built for thumbs, not a shrunken desktop.

Install Vanyx straight from your browser to run it as a standalone, fullscreen app with no browser clutter around it. It works on iPhone, Android, Windows, and Mac, keeps you signed in, syncs in real time, and still opens cached pages when you're offline.

Anywhere you see a question-mark icon, click it for a plain-language explanation of what that control does — what it changes, what it costs, and when you'd use it. Explanations appear in place without leaving the page, and you can toggle the icons on or off globally whenever you want a cleaner interface.

Forgot your password? Enter your email on the login page and we'll send a secure link to set a new one. Already signed in? Update your password anytime from your account settings. Both flows are protected against abuse and delivered by email.

New to a research platform this deep? Toggle Explain-everything mode from the rail or Settings and small info badges bloom on controls throughout the app — the workbench apps, the command palette, your live dashboard stats, and more. Hover or tap any badge for a clear, jargon-free description of exactly what that control does and why you'd use it. Turn it off and every badge vanishes — zero clutter when you don't need it. It remembers your choice.

As a conversation grows, the blackboards and interactive surfaces Vera opens scroll up with the transcript. The Active Tools tray keeps a running index pinned in view: click a chip to scroll a board back into focus or pop it out into a floating window, and click a surface to bring its window forward. The same live index appears in Mission Control, so nothing you're working with is ever more than one click away.

Instead of a blank “ask me anything,” the chat box animates through concrete examples of what the system can actually do — proving there are infinitely many primes, simulating a damped pendulum, verifying a theorem in Lean, searching 220M papers, running a hypothesis tournament — typed out and cycled one after another. Start typing and it steps aside instantly.

Research Workspace collapses the work into six focused tabs: Mission (the dossier — scorecard, distance-to-summit, mission graph, and a Library that opens papers, notebooks, datasets, and connections as floating windows), Lab notebook (decisions and failed experiments), Writing (manuscript and patent drafts side by side), Proofs, Anchors, and Agents/Runs. Chat and Surfaces stay as separate rail apps. Vera can open any tab through open_panel — legacy names still deep-link to the right place.