PUBLISHED AI RESEARCH AND PROJECTS

AI research and projects

The research, projects, and explanations behind the people. Read the source, inspect verified code and models, and find a collaborator.

Clear all filters

A source check confirms that a source supports the summary. It is not an independent replication or endorsement. Our methodology ↗

Showing 81–96 of 241 proofs of work · Kind: implementation · Newest first
Page 6 of 16
implementationChecked Sep 22, 2026

cvzone: Computer Vision Made Easy Open Source Library

Murtaza Hassan · Computer Vision Zone

Created cvzone, a widely used Python wrapper library with over 1M downloads simplifying OpenCV and MediaPipe integrations for hand tracking, facial mesh, and pose estimation.

Scope & limitations

MediaPipe hand landmarks require unhindered direct line of sight to camera sensor.

Context: MediaPipe, OpenCV, Python, real-time spatial coordinate calculation.

View mission
implementationChecked Sep 22, 2026

Deep Learning and Reinforcement Learning Project Blueprints

Nick Renotte · Nicholas Renotte Media

Maintains open-source code repositories with dozens of practical applied AI implementations, including real-time sign language detection and Mario reinforcement learning bots.

Scope & limitations

Deep reinforcement learning convergence requires millions of simulation steps and careful reward shaping.

Context: OpenAI Gym, Stable-Baselines3, PyTorch, OpenCV.

View mission
implementationChecked Sep 22, 2026

Diffusion Transformers (DiT): The Architectural Backbone of Sora

William Peebles · OpenAI

Engineered and released the open-source DiT PyTorch framework, proving that Transformer scaling laws reliably predict image and video generation fidelity across FLOPs and parameter scales.

Scope & limitations

High sample step requirements (e.g. 50-100 DDIM steps) necessitate distillation techniques for real-time interactive generation.

Context: Latent Diffusion Model (LDM) latents, ViT architecture, adaLN conditioning.

View mission
implementationChecked Sep 22, 2026

DOM Pruning and Interactive Element Tagging for AI Agent Harnesses

Magnus Müller · Browser-Use

Designed algorithms that extract interactive DOM nodes, filter non-clickable elements, and assign unique visual bounding boxes to minimize context window bloat during agent browsing.

Scope & limitations

Canvas-rendered and WebGL interfaces lack accessible DOM nodes, requiring purely visual coordinate fallbacks.

Context: Playwright CDP (Chrome DevTools Protocol), JavaScript tree walker, Claude 3.5 Sonnet.

View mission
implementationChecked Sep 22, 2026

Dub.co: Open Source Enterprise Link Management & Analytics Engine

Steven Tey · Dub.co

Architected Dub.co, an open-source platform handling millions of redirects with edge middleware, geo-targeting, automated AI link preview generation, and comprehensive Redis caching.

Scope & limitations

Global edge routing requires eventual consistency guarantees for analytics rollups.

Context: Next.js App Router, Upstash Redis, Tinybird analytics, Vercel Edge Runtime.

View mission
implementationChecked Sep 22, 2026

Enterprise Agent Routing with Model Cascades and Latency Guardrails

Tuhin Sharma · Bionic / Independent AI Advisory

Architected semantic routing proxies that direct routine classification to cheap SLMs while escalating complex reasoning tasks to frontier LLMs, slashing cloud compute costs by 65%.

Scope & limitations

Threshold calibration requires ongoing monitoring to prevent misrouting edge-case queries to smaller models.

Context: Semantic router, embedding cosine similarity, GPT-4o, LLaMA-3-8B-Instruct.

View mission
implementationChecked Sep 22, 2026

Enterprise Agentic Automation Blueprints with Make and Zapier AI

Paul Couvert · Paul.ai / Independent AI Agency

Designed end-to-end multi-step autonomous workflows integrating web scraping, LLM classification, CRM updates, and automated email generation with human-in-the-loop review triggers.

Scope & limitations

No-code integration middleware introduces execution latency and API rate-limiting bottlenecks on high volume.

Context: OpenAI Assistant API, Webhooks, Airtable, Make.com, HubSpot.

View mission
implementationChecked Sep 22, 2026

Enterprise Generative AI Engineering Curriculum

Ed Donner · Ed Donner AI / Independent Advisory

Authored modular open-source coding labs teaching engineers retrieval-augmented generation, function calling, evaluation frameworks, and guardrails.

Scope & limitations

Synthetic lab evaluation data cannot fully replicate messy, ambiguous enterprise customer queries.

Context: Python, LangChain, LlamaIndex, Pytest, LangSmith.

View mission
implementationChecked Sep 22, 2026

Enterprise Generative AI Transformation and Training Blueprints

Martin Musiol · GenerativeAI.net

Developed corporate training code repositories with practical implementations of structured prompt chains, retrieval evaluation, and self-hosted inference.

Scope & limitations

Production deployment requires custom observability instrumentation for token drift detection.

Context: Hugging Face, vLLM, FastAPI, Streamlit, LangChain.

View mission
implementationChecked Sep 22, 2026

Everart: Enterprise Generative Image Studio with Style Consistency

Pietro Schirano · Everart

Engineered Everart, a generative creative suite allowing brand teams to train private LoRA style models in minutes and generate production-grade marketing imagery with zero style drift.

Scope & limitations

Style convergence requires 15-20 high-fidelity reference images with diverse composition.

Context: SDXL, Flux-1, LoRA training pipeline, custom canvas UI.

View mission
implementationChecked Sep 22, 2026

Factory Droids: Autonomous Enterprise Software Engineering Agents

Shubhro Saha · Factory

Architected Factory's agentic Droids that integrate with GitHub, understand monorepo dependency graphs, autonomously write unit tests, and resolve complex pull request reviews.

Scope & limitations

Large monorepos with circular package dependencies require multi-pass compilation checks.

Context: AST parsing, GitHub API, Claude 3.5 Sonnet, automated test verification sandboxes.

View mission
implementationChecked Sep 22, 2026

Fireship AI and Modern Web Application Open Source Repositories

Jeff Delaney · Fireship.io

Authored and released educational software templates with hundreds of thousands of forks covering AI chatbots, real-time Firestore sync, and edge API deployments.

Scope & limitations

Ultra-fast instructional code requires refactoring for enterprise-grade multitenancy and RBAC.

Context: TypeScript, React, Node.js, Vercel AI SDK, Firebase, Supabase.

View mission
implementationChecked Sep 22, 2026

FutureTools.io: Curated Index and Categorization of AI Software

Matt Wolfe · FutureTools / Matt Wolfe Media

Built and maintains FutureTools.io, an index of over 3,000 verified AI applications with comprehensive categorization, feature filtering, and weekly community upvoting utilized by over 1,000,000 monthly visitors.

Scope & limitations

Rapid proliferation of AI tools requires rigorous manual editorial review to filter low-utility wrappers.

Context: Automated scraping, LLM content summarization, relational database search.

View mission
implementationChecked Sep 22, 2026

Genie: Early Landmark Demonstration of Natural Language Text-to-App Generation

Pietro Schirano · Everart

Created the viral early demonstration proving that GPT-4 could generate complete functional web applications (calculators, games, productivity tools) from a single prompt.

Scope & limitations

Single-file generation cannot maintain state across complex multi-route enterprise applications.

Context: GPT-4, HTML5 Canvas, single-file JavaScript execution.

View mission
implementationChecked Sep 22, 2026

Grimoire: Natural Language Code Wizard and Prompt Architecture

Nick Dobos · Grimoire / Independent AI Builder

Engineered Grimoire, a comprehensive 20-rule prompt engine incorporating code scaffolding, recursive self-correction, hotkey command shortcuts, and preview deployment instructions, executing 1.5M+ software build sessions.

Scope & limitations

Context window exhaustion in long multi-file projects requires modular file chunking.

Context: Custom GPT system prompt instructions, code-interpreter sandbox, single-prompt deployment.

View mission
implementationChecked Sep 22, 2026

High-Throughput Vector Indexing and Resume/Portfolio Tooling

Debarghya Das · Glean / Independent Investor

Created open-source developer tooling and resumes with over 25k stars on GitHub, demonstrating minimal parsing and structured document rendering.

Scope & limitations

Static document compilers require containerized sandboxes when executing untrusted community templates.

Context: LaTeX, C++, Python, distributed document indexing.

View mission
Showing 81–96 of 241 proofs of work