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 113–128 of 241 proofs of work · Kind: implementation · Newest first
Page 8 of 16
implementationChecked Sep 22, 2026

Next.js AI SaaS Boilerplate and Cursor Rules Pack

Jonny Darko · AICodeKing / Studio Darko

Created open-source starter repository with pre-configured `.cursorrules` optimized for React Server Components and modern Tailwind CSS UI patterns.

Scope & limitations

Cursor rules must be updated as framework minor versions introduce breaking API adjustments.

Context: TypeScript, Next.js App Router, Tailwind CSS, OpenAI API, Vercel AI SDK.

View mission
implementationChecked Sep 22, 2026

Nutrio: Food Vision AI Mobile Application Architecture

Daniel Bourke · Nutrio / Independent AI Engineer

Created the open-source PyTorch textbook repository with 15k+ stars and engineered Nutrio, an offline edge computer vision app for automated dietary nutrition tracking.

Scope & limitations

Edge model accuracy is constrained by real-world mixed-plate food segmentation ambiguity.

Context: CoreML, MobileNetV3, iOS Swift integration, PyTorch quantization.

View mission
implementationChecked Sep 22, 2026

Open-Assistant: Conversational AI For Everyone

Dr. Yannic Kilcher · Open-Assistant / Yannic Kilcher Media

Co-founded and led open-source engineering for Open-Assistant (36k+ stars on GitHub), producing transparent training datasets and aligned models used by thousands of researchers.

Scope & limitations

Decentralized contributor codebases require rigorous continuous integration to maintain reproducible weight checkpoints.

Context: Distributed training, Redis queue, FastChat inference, multilingual evaluation.

View mission
implementationChecked Sep 22, 2026

Outspeed: Open Source Real-Time Voice and Multimodal AI Agent Framework

Kanjun Qiu · Outspeed / Generally Intelligent

Engineered Outspeed, a Python library enabling developers to build sub-second real-time voice and vision agents running over WebRTC with bidirectional audio streaming.

Scope & limitations

Real-time bidirectional audio requires dedicated edge TURN/STUN infrastructure to prevent packet loss over mobile networks.

Context: WebRTC, Python asyncio, VAD (Voice Activity Detection), Cartesia, Deepgram, Claude 3.5.

View mission
implementationChecked Sep 22, 2026

Precedent: Modern Full-Stack Opinionated AI Starter Template

Steven Tey · Dub.co

Authored Precedent, an open-source template with 8,000+ stars that established the industry standard pattern for building beautiful, responsive AI web apps with Tailwind CSS, Radix UI, and Framer Motion.

Scope & limitations

High UI animation fidelity requires performance profiling on mobile low-end hardware.

Context: Next.js, Tailwind CSS, Framer Motion, Radix UI, Prisma.

View mission
implementationChecked Sep 22, 2026

Production AI Agent Templates and Enterprise RAG Blueprints

Dave Ebbelaar · Datalumina / Independent AI Agency

Authored and open-sourced end-to-end production AI starter kits covering hybrid vector search, chunking evaluation, LangGraph stateful multi-agent systems, and Dockerized FastAPI microservices.

Scope & limitations

Memory persistence in multi-agent loops requires external state stores like Redis or PostgreSQL.

Context: LangGraph, LlamaIndex, ChromaDB, Qdrant, FastAPI, Docker, OpenAI, Anthropic.

View mission
implementationChecked Sep 22, 2026

Prompt-Driven Software Architecture Blueprint

Riley Brown · Riley Brown AI

Published open-source starter templates designed specifically for Claude artifacts and Cursor rule enforcement to reduce hallucinations during web scaffold generation.

Scope & limitations

Rule sets must be tuned to avoid context window degradation in deep directory trees.

Context: Cursor system rules, Tailwind CSS, React components, TypeScript.

View mission
implementationChecked Sep 22, 2026

PyTorch Image Models (timm): The De-Facto Standard Vision Backbone Library

Ross Wightman · Hugging Face

Created and maintains `timm`, providing 1,000+ pre-trained vision models (ResNet, ConvNeXt, ViT, Swin, EVA) with modular feature extractors, augmentations (Mixup, CutMix), and production export utilities.

Scope & limitations

Enormous model zoo requires periodic deprecation of older checkpoint architectures to keep maintenance manageable.

Context: PyTorch, ONNX, TorchScript, CoreML, ImageNet-1k/22k pre-trained weights.

View mission
implementationChecked Sep 22, 2026

Replit Agent: Autonomous Full-Stack Software Building in the Browser

Amjad Masad · Replit

Architected Replit Agent, an autonomous software engineering system that provisions cloud infrastructure, installs packages, designs schemas, codes frontends and backends, and deploys live apps from scratch.

Scope & limitations

Complex third-party API integrations require user provision of valid secret keys.

Context: Cloud container environments, Nix package manager, Claude 3.5 Sonnet, PostgreSQL.

View mission
implementationChecked Sep 22, 2026

Robust Speech Recognition via Large-Scale Weak Supervision (Whisper)

Alec Radford · OpenAI

Architected Whisper, an open-weights sequence-to-sequence Transformer trained on 680,000 hours of multilingual audio, establishing zero-shot robustness across accents, background noise, and automated timestamp generation.

Scope & limitations

Long audio files can experience hallucination loops or timestamp drift during extended periods of ambient silence.

Context: Seq2Seq Transformer, 16kHz log-mel spectrogram audio input, 99 language recognition.

View mission
implementationChecked Sep 22, 2026

SGLang: Fast Serving Framework for Complex Language Model Programs

Lianmin Zheng · LMSYS Org / UC Berkeley

Engineered SGLang featuring RadixAttention, which maintains a radix tree over KV caches to enable automatic multi-turn and prefix cache reuse, delivering up to 5x higher throughput for complex multi-call LLM workflows.

Scope & limitations

Radix tree traversal introduces slight metadata lookup overhead for workloads with completely random, unshared prefixes.

Context: DeepSeek-V3/R1, LLaMA-3, Qwen-2.5; FlashInfer integration; Triton custom kernels.

View mission
implementationChecked Sep 22, 2026

Spiral: Natural Language Creative Writing and Synthesis Engine

Dan Shipper · Every.to

Architected Spiral, an AI writing tool designed to capture a writer's idiosyncratic voice and transform rough brain-dumps into polished essays using recursive prompt chaining.

Scope & limitations

Capturing idiosyncratic writing voice requires extensive fine-grained few-shot style examples.

Context: Claude 3.5 Sonnet, recursive LLM prompt chains, personal style embedding.

View mission
implementationChecked Sep 22, 2026

The AI Exchange Community Library of Automated Workflows

Rachel Woods · The AI Exchange

Curated and validated hundreds of production business automation templates integrating LLMs with Zapier, Make, and Airtable for lead scoring and data extraction.

Scope & limitations

Connector reliability depends on third-party webhook uptime and API schema stability.

Context: Make.com, Zapier, Airtable, OpenAI API, Anthropic Claude.

View mission
implementationChecked Sep 22, 2026

Therapeutics Data Commons: Machine Learning Benchmarks for Drug Discovery

Dr. Kexin Huang · Stanford University / Harvard University

Co-founded and engineered Therapeutics Data Commons (TDC), the de-facto open-source Python library standardizing 66 therapeutic machine learning tasks across small molecules, antibodies, target proteins, and clinical outcomes.

Scope & limitations

Public biological datasets often carry historical batch effects that require careful domain covariate shift evaluation.

Context: PyTorch Geometric, RDKit integration, 66 benchmark tasks across 22 problem formulations.

View mission
implementationChecked Sep 22, 2026

Transcriptionist and Audio Agent Processing Pipeline

Travis Fischer · Automated / Open Source

Engineered scalable audio transcription and semantic diarization workflows combining Whisper, deepgram, and LLM-based speaker role attribution.

Scope & limitations

Overlapping speakers in noisy environments degrade speaker attribution accuracy without multi-channel audio.

Context: Whisper large-v3, pyannote.audio speaker diarization, Claude 3.5 Sonnet.

View mission
implementationChecked Sep 22, 2026

Vector Search and RAG Engineering Repositories

James Briggs · James Briggs AI / Vector Search Advisory

Maintains open-source code repositories with over 10,000 stars containing complete implementations of vector indexes, metadata filtering, and chunking evaluation benchmarks.

Scope & limitations

Vector similarity degrades on exact keyword search (e.g. part numbers, hashes) without hybrid sparse weighting.

Context: Python, PyTorch, Pinecone, FAISS, Hugging Face Datasets.

View mission
Showing 113–128 of 241 proofs of work