Skip to content
#small language model Open access

Vibe Coding Platform-Swift

Sep 2026 · Zenodo (CERN European Organization for Nuclear Research)

Abstract

Swift Tasks is a browser-based, Bring-Your-Own-Key (BYOK) AI vibe-coding platform that converts a natural-language description into a complete, multi-file web application through token-by-token streaming generation, with a live rendered preview that updates as generation proceeds. The platform's central architectural contribution is fully isolated multi-project workspaces: per-project Zustand store instances on the client (implemented as a factory-and-registry pattern, Map ) and projectId-scoped database rows with cascade deletes ensure that chat history, files, model configuration, and generation state never leak between projects. Swift Tasks supports five categories of large-language-model (LLM) providers – a free platform demo model (GLM-4.6), OpenRouter, OpenAI, Anthropic, and custom OpenAI-compatible endpoints such as Groq, Together, DeepSeek and Ollama – with model identifiers auto-fetched from each provider's /models API and automatic fallback to the demo model on configuration, authentication, or region errors, without ever forwarding the user's key to the fallback provider. Generation executes as a detached, server-side job managed by a JobManager singleton, so that closing the browser tab does not terminate an in-progress build; the client reattaches through Server-Sent Events (SSE) using an in-memory ring buffer and a resumable cursor. All API keys and arbitrary secrets are encrypted at rest with AES-256-GCM, returned to the client only in masked form, and revealed solely through an explicit user action. The generated application is rendered inside a sandboxed iframe that has no access to the parent window, cookies, or local storage, and is shipped to production through one-click Netlify deployment, ZIP export, or self-contained HTML, alongside deployment guides for Vercel, Cloudflare Pages, Surge, and GitHub Pages. The system is implemented with Next.js 16 (App Router), TypeScript 5, Prisma ORM over Neon serverless PostgreSQL, shadcn/ui with Tailwind CSS 4, Monaco Editor, the Vercel AI SDK, and Zustand. By combining real-time generation, complete project isolation, secure BYOK key management, sandboxed preview, and one-click deployment in a single zero-configuration platform, Swift Tasks offers an open, self-hostable, and cost-accessible alternative to proprietary AI coding assistants for individual developers, students, and small teams.

View source

Similar papers

#small language model Dataset Open access Oct 2026

Socratic guiding questions in synthetic arithmetic data: matched LoRA runs (revision v2)

Supporting data, adapters, predictions and code for the article *Low-Cost LoRA Fine-Tuning of Small Language Models for Multi-Step Arithmetic Reasoning* by Jake O'Grady, Asena Isik Gürhan, Chee Fong Ting and Effirul Ramlan (University of Galway). We generated 20,000 GSM8K-derived arithmetic problems with step-by-step s...

O'Grady, Jake, Gürhan, Asena Isik, Chee, Fong Ting et al. · 465 citations
#computer vision Open access Jun 2016

Software Development in Startup Companies: The Greenfield Startup Model

The results are packaged in the Greenfield Startup Model (GSM), which explains the priority of startups to release the product as quickly as possible, and the need to shorten time-to-market, by speeding up the development through low-precision engineering activities.

Carmine Giardino, Nicolò Paternoster, M. Unterkalmsteiner et al. · 178 citations · ⚡14
#computer vision Open access Oct 2016

Software Startups - A Research Agenda

Software startup companies develop innovative, software-intensive products within limited timeframes and with few resources, searching for sustainable and scalable business models.

M. Unterkalmsteiner, P. Abrahamsson, Xiaofeng Wang et al. · 157 citations · ⚡17
#machine learning Review Open access Oct 2016

“Failures” to be celebrated: an analysis of major pivots of software startups

This study conducts a case survey study based on the secondary data of the major pivots happened in 49 software startups, and demonstrates that customer need pivot is the most common among all pivot types.

Sohaib Shahid Bajwa, Xiaofeng Wang, Anh Nguyen-Duc et al. · 127 citations · ⚡15
#computer vision Review Open access May 2015

A survey study on major technical barriers affecting the decision to adopt cloud services

The comparison of adopter and non-adopter sample reveals three potential adoption inhibitor, security, data privacy, and portability, which underlines the importance of the technical and security perspectives for research investigating the adoption of technology.

Nattakarn Phaphoom, Xiaofeng Wang, S. Samuel et al. · 111 citations · ⚡8
#large language models Review Open access Nov 2020

Status of the WHO recommended timing and frequency of antenatal care visits in Northern Bangladesh

Objective There is dearth of information on the timeliness of antenatal care (ANC) uptake. This study aimed to determine the timely ANC uptake by a medically trained provider (MTP) as per the World Health Organization (WHO) recommendations and the country guideline. Methods Cross-sectional survey was done with 2,731 wo...

B. Sarker, Musfikur Rahman, T. Rahman et al. · 89 citations · ⚡7

Related blog posts

We use cookies to run the site and, with your consent, for analytics and to show ads. See our Cookie Policy.