Scalable, serverless AWS solution for automated document processing using OCR and generative AI
Data projects
Loading…
Data projects
Public projects with traces of AI coding tools in their repositories, sorted by newest listing.
Data · 2,290 projectsReset filters
Tools to work with campaign finance data from the FEC
Scrape public app reviews from the Apple App Store and Google Play in one run: rating, text, author, version, date, developer reply. Pay per review.
Extract text, page ranges, RAG chunks, metadata and links from PDF URLs (incl. Drive/Dropbox links) as JSON. $0.004 per PDF, no per-page fee, failures f...
Analytic column storage for PostgreSQL, built as a native table access method.
Measures how much of a fluorescent cell image is microtubule (green) outside the nucleus (blue), entirely in your browser.
Mapear trechos rodoviários, calcular distâncias de materiais e gerar pranchas de localização
Translation pending
AI summary · website and README
Open data and statistical models for biomarker shedding: standardized, validated shedding datasets from peer-reviewed studies to support wastewater-based epidemiology.
R utilities for the clinical investigations statistics group within The Heart & Vascular Institute at the Cleveland Clinic.
ML-Powered S&OP Platform: Data validation, forecasting, and statistical analysis for enterprise teams. Three DuckDB extensions for the complete planning workflow.
Registra ensaios de campo em um mapa e mostra índices de vegetação por satélite (NDVI)
Translation pending
AI summary · revised during review
Agentic search-analytics dashboard: zero-result & low-engagement queries, reviewable synonym/misspelling discovery, and an NL agent with weekly digests
Receipts for every branch and a guard that acts mid-session, computed from the agent logs on your own machine. Nothing leaves it.
Type your job title. A solver cuts 15% of payroll from a company built out of federal employment data. See whether you survive.
cartes assemble le plan IGN ou les photographies aériennes sur le territoire d'une commune française, y ajoute ses propres données et la mention des sources, et produit une image prête pour l'
Translation pending
Impacto ambiental acumulado de los proyectos renovables en Andalucía, construido a partir del BOE y el BOJA.
Translation pending
Dashboard showing how product is performing this season
See a year of daily runs alongside weight logs and Hong Kong weather
Translation pending
AI summary · README
Offtake — the ledger of disclosed AI compute, colocation, hosting and power contracts, read from SEC filings with the source excerpt on every row.
HQ outlet sales by platform, sales & purchases by outlet, and gross sales — May.
Translation pending
Convert PDFs and images to well-structured JSON, entirely in your browser. Folder uploads become a file tree with per-file conversion.
Connect your SAP ERP in real time. Data integration, agentic AI, and B2B/B2C eCommerce from a single platform.
A working data warehouse covering carbon border costs, emission factors for disclosure, retail customer economics, currency effects, weather as a control variable and long-run emissions trends.
An LLM extracts structured claims from SEC 8-K earnings releases; those claims become features in a calibrated model predicting post-announcement volatility.
Translation pending
ferx is an open-source nonlinear mixed-effects modeling platform for population PK/PD, with an R package and high-performance Rust engine.
Analyze URLs, build intelligence frameworks, and crowdsource data collection with Survey Drops.
Table, Listings, and Graphs (TLG) library for common outputs used in clinical trials.
Panel de ventas multi-tienda para bots de WhatsApp (Kapso → Shopify)
Translation pending
Ever wanted to know the ROI on your Congress Critter? Are they working hard, or hardly working? Here, I've centralized it for ya.
Automated maintenance bots for shinto.miraheze.org — Wikidata integration, interlanguage links, category cleanup, and a daily QuickStatements pipeline. Live dashboard: https://emmaleonhart.github.io/s
Hackathon winners and what everyone else built, analyzed by why they stood out — plus a demo-first planning harness.
Demo de monitoreo en tiempo real (SG-SST, Energía, Agricultura) potenciado por sensores IoT Niuvee.
Translation pending
ETL, dbt orchestration, a SQL client, dashboards, and an app builder — one open-source platform with an AI agent that knows your schema. Replaces five tools.
Open a Cities: Skylines 1 .cslmap export and read your city in layers.
Convert Qlik QVD files to Parquet, exactly. Built for a Qlik to Dremio migration: whole trees in parallel, exact decimals, no timezone guessed behind your back, and a quality gate that checks the outp
ThinkingSense is enterprise intelligence that learns how your business works — ask one question across your enterprise, get one governed, auditable answer.
A desktop application for working with LiDAR point clouds, plant meshes, skeletons, and procedural plant models.
An original, animated reinterpretation of a multi-cloud cost visualization concept.
Translation pending
A monitor for the erosion of voting rights across four channels of federal pressure.
Interactive visualization of property taxes and service costs for each area of Edmonton.
Explore, visualize, and compare genomic data with the UCSC Genome Browser: free, open-access tools for the human genome and beyond.
Auto-compute Citations to Software From Replication Files
Viewer for DSM/DTM 3D Terrain via hillshade, hypso color-relief, maplibre contours, raster basemap etc
Translation pending
Make the world's genetic diversity useful for better screening, medicine, discovery, and more representative research.
Helios Software is a Boston-based health technology company offering a commercial-grade HL7 FHIR database solution for healthcare organizations.
Explore a fictional drug discovery portfolio. Search, filter, and review research candidates.
Translation pending
US Congress activity from official public-domain sources. Raw records only — no ratings, no ideology scores.
Translation pending
A curated, searchable directory of Drosophila connectome datasets, brain simulations, body models, tools and the 2026 wave of "the fly brain can play X" demos.
Fast procedures for a small set of commonly-used, design-appropriate estimators with robust standard errors and confidence intervals. Includes estimators for linear regression, instrumental variables
Maximum-likelihood estimation of beta regression models for responses derived from bounded rating scales. Observations are treated as interval-censored on (0, 1) after a scale-to-unit transformation,
Tools for analyzing Solomon four-group experimental designs using historical Tests A-I, unified generalized linear models with robust covariance estimation, stratified randomization inference, full-in
An autonomous station on a Lisbon terrace — photographing and measuring every aircraft on final approach to LPPT, 24/7.
Translation pending
Functions that read some of the raw data formats produced by Google electron microscopy segmentation tools as displayed by neuroglancer and then allow basic 3D visualisation and analysis.
puremacro is an open-source empirical macroeconomics toolbox in pure Python: SVARs, local projections, Bayesian DSGE and HANK models that run on your laptop, in the browser and on an iPad.
Open-source platform — a typed knowledge graph for AI-assisted scientific reasoning. Make the AI show its work: every claim records how it was justified, so a brilliant analysis and a confident halluc
MetricAi — ask business questions in plain English and an LLM agent answers with live data, charts & insights. ReAct agent with fine-grained tools, natural-language to SQL, schema-per-tenant multi-ten
Extract structured logic models from PDFs and presentations for editing and export
AI summary · README
Interaktive Karte der Verkehrsunfälle 2017–2025 aus dem Unfallatlas — filterbar nach Schwere, Beteiligung, Unfalltyp und Jahr, mit OSM-Kontextlayern und Analyse-Szenarien.
Translation pending
Transforme planilhas em dashboards profissionais e insights estratégicos com IA.
Translation pending
LiteGraph is a multi-modal AI data platform: graph relationships, vectors, and metadata in one database, native LLM chat over your data, an MCP tool surface and memory for agents, and built-in observa
Knowledge compiled with a traceable path back to every source.
Translation pending
Generative AI synthetic users negotiate in a simulated vegetable market testing whether a trained pricing policy (not LLM role-play) produces emergent social stratification
Translation pending
A standalone RELION job‑lineage viewer that requires no ChimeraX, no third‑party server framework, and no GUI toolkit.
AI translation
Google Earth Pro の代替 Digital Earth Browser — OGC KML 2.3 対応 OSS Web アプリ
Translation pending
Implements for ggplot2 the stylistic elements (fonts, hatched patterns, color palettes) used by Emile Cheysson in the Albums de Statistique Graphique, sometimes called the pinnacle of the Golden Age o
Camera health under its own Monitoring rail item — live per-camera status across every assigned center, with an overview that changes altitude as the assignment grows, filtering, sorting, saved views
부서별 KPI 목표와 업무 진행률을 등록하고 실시간으로 확인하는 대시보드
Translation pending
AI summary · revised during review
An interactive simulation of US elections under proportional representation, built from 45,707 CES 2024 survey responses.
GrooveMap turns music catalogs into a connected knowledge graph for exploration, research, and discovery.
Interactive multiple sequence alignment viewer with phylogenetic tree, protein domains, and many color schemes. React, HTML, and R.
Drop-in usability analytics for prototypes built with Claude, Cursor, v0, and other AI tools.
Village-level climate intelligence portal for Madhya Pradesh — IMD gridded data, verified sources only
Translation pending
Fixed-level parametric quantile regression for bounded responses in the open interval (0,1), using the five-parameter Generalized Kumaraswamy distribution and its six nested sub-families. For a quanti
A polling-average tracker for presidential approval, the generic ballot, and Senate races. More to come, but to learn more read here: https://policyypeaches.substack.com/
An interactive Singapore Tourism Arrivals Dashboard providing monthly visitor data categorized by origin market from 2008 to the present.
AI translation
DACKAR is a software product designed to analyze equipment reliability data and provide system engineers with insights into anomalous behaviors or degradation trends as well as the possible causes beh
Semantic SQL for vanilla Postgres. Put jev() in any query from the CLI, the SDKs or an agent over MCP. The database only ever sees plain SQL. No extension, no proxy.
Build compelling visualizations using the declarative react components.
AI translation
College basketball data, from public APIs to dashboards. Two ways to read it: an Evidence dashboard and a set of dbt Charts boards.
Compare Denver Gold Group membership and mining forum participation
Translation pending
AI summary · website content
Acompanhe a cobrança de respostas e o painel da campanha de NPS
Translation pending
AI summary · website content
General models invent biology. We build the layer they check against — a curated knowledge graph, validated pipelines, and a provenance ledger, callable over MCP.
Front-end React app for exploring model schema and variables that use it
Estado en vivo del pipeline MLOps: accuracy, cobertura, drift y operación.
Translation pending
Compare GPT-4, Claude, DeepSeek, Gemini pricing across official and aggregator channels. Find the cheapest AI API.
9회 전국동시지방선거(6.3) 결과 — 광역단체장 민주 11·국힘 5·최종 투표율 61.0% · 22대 통과 법안 1,847건 · 정치인 약 780명 약력·표결 · 환율·코스피 실시간 · 한국 구글 트렌드. 무료.
Translation pending
Provides ggplot2-based visualization functions for output objects from the exametrika package, which implements test data engineering methods described in Shojima (2022, ISBN:978-981-16-9547-1). Suppo
Theo dõi doanh thu, mục tiêu và hiệu suất nhân viên siêu thị theo thời gian thực
Translation pending
AI summary · website and README
EndTimes.LIVE — global threat & prophecy monitor (Lovable + Supabase + GitHub Actions collectors)
Translation pending
パチスロ「マギアレコード」の実戦データを記録・管理する個人制作の非公式Webアプリ。ゲーム数・当選履歴・設定示唆などをスマホでかんたんに記録できます。
Translation pending
Paint every omic layer onto the pathway that explains it: multi-omics pathway analysis across KEGG, Reactome and MapMan, with an AI agent that drafts a cited interpretation.
Searchable database of Nebraska state agency and university contracts and purchase orders from the Nebraska State Contracts Database.
Daily weather, space weather, earthquakes, and market/news noise combined into a single activity index. Features a static dashboard and Telegram alerts via GitHub Actions.
AI translation
Live, filterable geospatial picture of a theater from open sources — exportable as a briefable sheet. Not an official government product.
Translation pending
Explore historical FAA sectional charts on an interactive timeline. See how U.S. aviation charts have evolved over time.
Translation pending
Carbon-accounting API: sourced emission factors + audit-traced calculations (PCAF, GHG Protocol), every value traceable to its source. Free tier, no card.
Translation pending
A spy satellite simulator in your browser, except the data is real: live aircraft, ships, satellites, earthquakes, launches, and the water that sustains communities. Rivers, reservoirs, aquifers, drou
An Open Platform for Understanding Australia's Methane Emissions.
The backend agents build with - Multimodal database, orchestration, and serving in one file
Tools for connecting to CHILDES, an open repository for transcripts of parent-child interaction. For more information on the underlying data, see <https://langcog.github.io/childes-db-website/>.
Drop a CSV, TSV, or Parquet file and write SQL against it. DuckDB runs in the tab, so the file never leaves your disk.
Home of fog/map — live satellite fog for the West Coast.
Real-time match scouting, analytics, and offline QR data transfer built for FTC competitions by Teams 12841 & 2844.
An access layer for the digitized Leibniz Nachlass: machine transcription with per-line confidence and provenance, searchable and browsable. Not an edition.
Crested gecko prices by morph, from real MorphMarket listings and sales.
Ask the Earth a question, get a radar answer. Real satellite radar analysis on a 3D globe.
Translation pending
Every FIFA nation is a row and a column, the men's game above the diagonal and the women's below it: 6,520 fixtures played against 2,822.
This is the project for all people on the earth. The earth is round. Open data of the Earth on a round globe, in your browser.
Provides quantitative tools for substantive and content-oriented scale pretesting. Implements item-sort indices from Anderson and Gerbing (1991) <doi:10.1037/0021-9010.76.5.732>, exact item-sort infer
Avogadro libraries provide 3D rendering, visualization, analysis and data processing that is useful in computational chemistry, molecular modeling, bioinformatics, materials science, and related areas.
AI translation
Track grape chemistry and wine phenolics for Monte Xanic winery
AI summary · website and README
Generating and evaluating road-network proposals for informal urban settlements — a Stony Brook University REU project.
Live data-center, power-grid, energy, interconnection-queue, fiber, natural-gas & M&A intelligence for AI agents — 92 tools, 24,600+ facilities, 300+ markets scored daily (DCPI), 1,600+ tracked M&A de
AI powered (free tier) receipt analysis, granular data extraction, price comparison, shopping prediction and nutrition data
Translation pending
Live emissions accounting for Kimball Union Academy — Scopes 1/2/3 with measured-data pipeline + on-campus sequestration.
Is the number real? If yes, every lead gets its own investigator, and the evidence decides. Multi-agent attribution for business metrics.
Simulate Citi Bike station rebalancing scenarios and view equity-based priority rankings
Translation pending
AI summary · website and README
An always-on, multi-cloud data platform bridging operational data to high-impact products and services, accelerating research from idea to operations, with secure data access.
Instantly run SQL queries on your CSVs — or ask in plain English. No install, no sign-in, right in your browser.
Translation pending
Airbyte is the open-source data movement platform. Run ELT pipelines across 700+ connectors to any warehouse, lake, vector database, or AI agent.
Live parcel search for Manitoba Open Data — Roll Entry + Zoning + Development Plan + Traffic + Contaminated Sites, queried directly from the province's ArcGIS REST endpoints.
Dados atualizados sobre provedores de internet. Veja quais empresas operam, número de clientes, market share e análise completa por município.
Translation pending
Send data from your behavioral experiments to the OSF. Born-open data as a service.
YouTube intelligence: find breakout Shorts channels, viral videos, and what's working.
Translation pending
Health data portal for evidence-based planning across Niger State.
Translation pending
전국 16개 시도의 아파트 공급을 적정물량과 비교. 준공·착공 실적으로 본 앞으로 3년 입주물량과 주간 시세 지도 — 국가 통계 기반, 매주 자동 갱신.
Translation pending
This is a pure C zero-dependency embeddable engine where columnar analytics and graph operations share a single operation DAG, pass through a multi-pass optimizer, and execute as fused morsel-driven bytecode.
AI translation
One cube definition. Excel, Dashboards, and AI agents talk the same numbers. Open source.
Mixpanel is the product intelligence platform for the AI era, combining analytics, session replay, experiments, feature flags, and AI-powered insights.
When is the road to the island underwater? Closure times for the next eight days.
Interactive apps, data access and open-source tooling built on the CalCOFI integrated database.
A Python package for interactive mapping and geospatial analysis with minimal coding in a Jupyter environment
Caspian Sea oil spill intelligence — satellite detection, AI analysis, and operator response.
Translation pending
Eight years and 683 films — what I watch, when I watch it, and what that says about my taste.
Batch Processing ETL on NBA's Last Two Minute (L2M) Report
Translation pending
A browser-based implementation of Cytoscape for network visualization and analysis. Runs entirely in your browser with data-driven styling, collaborative workflows, and Cytoscape ecosystem integration
Search and browse Canadian arts data, mint IDs, and query linked open data
AI summary · website and README
Ask your database questions using natural language. The IA generates professional SQL using CTEs, validates it against your schema, and returns exportable tables, charts, and analyses.
AI translation
A dashboard that automatically analyzes columns when you upload an Excel file to display metrics, charts, and tables (React + Vite, no backend).
AI translation
An immutable SQL database for application development, time-travel reporting and data compliance. Developed by @juxt
CalCOFI Explorer — a single browser-native app for station, hexagon, cruise, region, and section grains (calcofi.io/explore)
AI translation
権利を一件ずつ確かめた世界の民話 1113 話を、多言語 Embedding で横断して眺めるアトラス。出典と権利は全話に付いており、AI の推定は原資料と見た目で区別している。
Translation pending
Monitor the climate control of 512 schools in Fortaleza with a map and execution status.
AI translation
AI summary · website and README
Analyze War Thunder match logs to split battles by type and calculate RP goals
Translation pending
AI summary · website and README
Complementary to AQI, tracking intensity, persistence, and volatility of air pollution across India.
Translation pending
Research agent that turns an emerging Colombian artist's name into a structured, source-cited A&R report
2世代の GTFS フィードを比較し、路線・便数・時刻・停留所の変化を自動で読み解きます。GTFSデータリポジトリの公開フィードにも対応。/ Compare two GTFS feed versions and see what changed — routes, trips, times, stops.
Translation pending
Brazilian public financial data, ingested daily and served to people and AI agents
View the print-ready weather layout in your browser and save it as a PNG.
AI translation
AI summary · README
Vortex is an extensible, state-of-the-art columnar file format, with associated tools for working with compressed Apache Arrow arrays in-memory, on-disk, and over-the-wire.
Explore the Amazon river system and tributaries on an interactive map with zoom and pan controls
AI summary · website and README
Public spending, businesses, and territories: official Italian data with explicit sources and boundaries.
AI translation
FireCMS is the open-source Firebase CMS and Firestore CMS: manage your data in a visual admin panel. Go live with managed Cloud, or self-host for full control.
Pacific Northwest drought, hydrology, and Tribal Treaty regional mapping. ATNI Climate.
Translation pending
Un mapa navegable del gasto público del Estado nacional argentino.
Translation pending
TopPIC suite is a software suite for proteoform identification by top-down mass spectrometry.
Scan a barcode. It tells you which GS1 office sold the company its number — not where the product was made. This shows the difference.
Scalable data pre processing and curation toolkit for LLMs
Evaluate outdoor playspaces by what children can actually do, feel, and experience there.
Translation pending
Built it? Time to show it.
One command in your project folder. Built with AI is enough; AI features are optional.
/nomorevibeSee how to list