Everything shipped: research, products, open source, client sites and earlier projects.
A study of web agents that write the whole plan in one LLM call and execute it locally, grounding each step to a page element with Laya, a small on-device ModernBERT model. 200 tasks on seven public websites, 2,800 recorded runs across two models, and every trace published.
Plan Once, Ground Locally: full pagedoi.org/10.5281/zenodo.22904595Source
Ice sits on the desktop as a small character you can move. Talk to it and it works across the browser, files and apps, leaving a trail of every step: what it opened, what it wrote, what failed and how long it took. The macOS beta comes first, Windows next.
It is not a chat box. You watch Ice work the way you would watch a colleague, and it asks before doing anything you haven’t allowed. Reservations are open at $5, refundable until launch, and the first 100 paid reservations become founding members who keep the desktop app for life.
Describe a site and Blank writes a real React project you can read, edit, connect to your own database and publish on your own domain. Nothing is locked in, because there is nothing to lock: the code, the data and the repository are yours from the first build.
Most AI site builders keep the result inside their editor. Blank goes the other way: every build is a project you could hand to any developer, with a Postgres database and row-level security in your own Supabase account, a custom domain, version history, and a one-click push to your own GitHub repository.
Synapse trains on a site’s own content, answers customers at any hour, collects leads and passes the conversation to a human when it should. The free plan covers 250 messages a month without a card.
It is built for businesses whose website already holds the answers: one script tag installs it, replies come back in well under a second, and when the content doesn’t cover a question, Synapse says it doesn’t know rather than guessing.
A teacher uploads notes, a PDF or a photo of the board, and CampusQuiz drafts the quiz: multiple choice, true or false, or mixed. Students join with a six-character code, with nothing to install, attempt it live, and see their score and the explanations the moment they submit.
While the class works, a live board shows who has joined, who has submitted, the correct rate for each question and the weakest topics so far. Across quizzes, each student’s dashboard tracks the concepts they keep getting wrong. It is free for students, built for teachers, colleges and coaching institutes in India, and the sister product of CampusPrep.in.
A study site for RGPV B.Tech students: pick a branch and semester to get the official syllabus, solved and unsolved previous-year papers, short notes and important questions, with nothing behind a sign-up wall.
It covers 570 subjects from first year to eighth semester. On top of the papers sit subject analytics and a personal workspace where students keep their own notes and practice questions. CampusQuiz, its sister product, brings the same students into live class quizzes.
HD meetings and webinars that run in any browser, with breakout rooms, polls and Q&A, a whiteboard, waiting rooms, screen sharing, cloud recording and admin audit logs.
Conference is NARA’s browser-first alternative to Zoom: there is nothing to install, anyone can join by meeting ID, billing is self-serve, and the same room scales from a one-to-one call to an all-hands. An Android app is on Google Play.
Loci pairs rapid serial visual presentation, one word at a time at a pace you set, with the oldest memory technique there is: each paragraph becomes a place in a memory palace, illustrated by generated imagery, and AI-written quizzes check retention.
NARA builds a small set of products and takes client work. Synapse answers a website’s visitors around the clock; Conference hosts meetings and webinars in the browser. Frame, an AI video editor, and Nara AI, an assistant across the products, are in the works.
Scan your face for a personalised skin report, then consult a certified dermatologist over video and get a digital prescription, with medicines delivered to your door.
Built with Team Saakshya at the SISTec Innovation Hackathon 2026, for a problem statement on blockchain-based document verification. Upload a marksheet, a degree or a PAN card: Saakshya reads and audits it, checks the claim against the issuing authority’s register, anchors a salted hash in a Merkle-batched ledger and returns a signed credential with a QR code that verifies offline.
The point is the verdict. Instead of a yes or no, every document gets one of four levels: L3 PROVEN (issuer-signed or from DigiLocker), L2 CONFIRMED (matches the official register), L1 PLAUSIBLE (clean, but no register to check) and L0 REJECTED (evidence of tampering).
atlas-mcp connects any coding agent, including Claude Code, Cursor, Windsurf, VS Code with Copilot and Cline, to a team’s Atlas knowledge hub. The agent pulls approved prompts, documents and scoped secrets as context, and Atlas records what the agent builds, so the team can see the work without anyone updating a ticket.
It is a thin, cached client over the Atlas REST API. Reads come from a local stale-while-revalidate cache, so they are instant and work offline; writes queue and flush when the network returns. Authentication, fine-grained scopes and audit stay on the server, and tools a key cannot use are hidden from the agent.
Coding agents tend to stop at the first green checkmark. Wire this endpoint into a Stop hook and, before the agent ends its turn, it fetches one line of senior-engineer operating advice: find the next high-value task, verify the work, commit it and continue.
GET / returns one newline-terminated line of text/plain. Modes steer the advice toward continuing, verifying, shipping, focus or quality; the default deliberately never says stop, and an explicit stop mode is the honest counterweight. The corpus is static and hand-curated, with a no-repeat window so consecutive calls differ, and no external calls, keys or rate limits.
Treatments, doctors, clinics and reviews for The Shining 32 in Indore, with bookings and an admin-only CMS.
The menu by section with prices, the four places to sit, opening hours and directions, plus a table-side app guests can install on their phones that keeps working without a connection.
Courses, batches and trial-class booking for students, plus a member area and a console for staff.
A walkthrough and tooling for capturing a WPA2 four-way handshake with a monitor-mode adapter and brute-forcing it offline, written to make the case for long passphrases.
Speech in, system actions and speech out, with an AI model in the loop for real-time replies.
Hand landmarks from MediaPipe mapped to cursor movement, clicks and media controls.
Automated scanning and security-testing modules that helped researchers find and report vulnerabilities faster.
