AI research and projects
The research, projects, and explanations behind the people. Read the source, inspect verified code and models, and find a collaborator.
A source check confirms that a source supports the summary. It is not an independent replication or endorsement. Our methodology ↗
Chatbot UI: An Open Source AI Chat Interface for Frontier Models
Mckay Wrigley · Takeoff / Chatbot UIArchitected Chatbot UI, a Next.js and Supabase open-source application with 30k+ stars enabling local and cloud deployment of multi-model chats, prompt presets, file uploads, and custom vector search embeddings.
Client-side state management requires persistent database sync for multi-device conversation state.
Context: OpenAI, Anthropic, Mistral, Ollama, pgvector embeddings.
View missionChatGPT and Healthcare: Clinical Applications and Diagnostic Augmentation
Dr. Harvey Castro · Healthcare AI AdvisoryAuthored the first medical reference manual for physicians examining generative AI utility in clinical note generation, patient triage, and medical education.
Generative LLMs must never replace primary clinical diagnostic reasoning without board-certified physician oversight.
Context: Clinical documentation, HIPAA data privacy, emergency medicine triage.
View missionCognosys: Autonomous Multi-Agent Web Execution Platform
Sulaiman Ghori · CognosysEngineered Cognosys, an autonomous agent execution environment that decomposes user goals into hierarchical subtasks, executes web browsing and code execution steps, and summarizes multi-step outcomes.
Recursive agent loops risk infinite token consumption without strict cycle detection and step budgets.
Context: GPT-4, Claude 3, isolated Docker sandboxes, LangChain orchestration, Supabase.
View missionCollaborative Prompting: Conversational AI Workflows for Business Teams
Conor Grennan · NYU Stern / Generative AIFormulated the 'collaborative prompting' methodology taught across NYU Stern executive programs, replacing static prompt templates with iterative dialogic steering.
Iterative prompting relies on user critical thinking to recognize and steer model assumptions.
Context: GPT-4o, Claude 3.5 Sonnet, iterative conversational prompting, business communication.
View missionColorful Image Colorization with Deep Convolutional Neural Networks
Dr. Alexei Efros · UC BerkeleyPioneered automated black-and-white image colorization by formulating the task as multinomial classification over quantized Lab color space with class rebalancing, tricking human observers into believing synthesized colors are real.
Ambiguous objects (e.g. clothing, cars) can display desaturated or sepia tints if the model averages multimodal color distributions.
Context: CIE Lab color space, class-rebalanced cross-entropy loss, 1.3M ImageNet images.
View missionComputer Vision Road Map 2026
Murtaza Hassan · Computer Vision ZoneComprehensive video guide explaining bounding box regression, feature extraction, non-maximum suppression, and real-time GPU inference pipeline optimization.
Real-time edge performance drops under high occlusion and erratic low-light conditions.
Context: YOLOv8, OpenCV, CUDA, TensorRT, Python video streaming.
View missionConnectionist Temporal Classification: Labelling Unsegmented Sequence Data
Dr. Alex Graves · NNAISENSE / former Google DeepMindAuthored the monumental ICML 2006 paper introducing CTC loss, allowing RNNs to be trained directly on unsegmented, unaligned sequence pairs by integrating over all possible alignments with a blank token, with over 15,000 citations.
Assumes conditional independence between label outputs given the input sequence, necessitating external language models for grammar smoothing.
Context: Dynamic programming forward-backward algorithm, RNN sequence alignment.
View missionContrastive Multiview Coding and Self-Supervised Representation Learning
Dr. Phillip Isola · MITIntroduced Contrastive Multiview Coding (CMC), showing that maximizing mutual information across multiple views or sensory modalities learns invariant visual representations competitive with full ImageNet supervision.
Requires view-generation or multiple aligned cameras/modalities during pre-training to compute contrastive pairs.
Context: Multi-sensory embedding spaces, contrastive InfoNCE loss.
View missionCopy.ai Workflows: Enterprise-Scale Autonomous GTM Engine
Paul Yacoubian · Copy.aiArchitected Copy.ai Workflows, an enterprise workflow automation engine executing millions of autonomous prospect research, content localization, and pipeline enrichment jobs with multi-model fallbacks.
High-volume web scraping dependencies are susceptible to IP blocking and dynamic website anti-bot protections.
Context: Multi-model orchestration: GPT-4o, Claude 3.5 Sonnet, Azure OpenAI, CRM APIs.
View missionCrawl4AI: Open-Source LLM-Friendly Web Crawler and Extraction Engine
Minh Do · Crawl4AIDesigned and built Crawl4AI, a high-speed asynchronous web crawler that converts complex JavaScript-rendered web pages into clean, token-efficient Markdown formatted specifically for LLMs and RAG pipelines.
Aggressive anti-bot fingerprinting services (Cloudflare, Akamai) require proxy rotation.
Context: Playwright, AsyncIO, BeautifulSoup, LLM extraction schema, token minimization.
View missionCursor Rules and Autonomous AI Coding Harnesses
Dan Mindru · IndyDevDan / Independent AI EngineeringCreated widely adopted open-source `.cursorrules` configurations and automated CLI developer scripts that enforce code conventions and automated test-driven development.
Rules must be scoped per subfolder in monorepos to avoid rule conflicts between frontend and backend.
Context: Cursor system instructions, Next.js, TypeScript, Vitest.
View missioncvzone: Computer Vision Made Easy Open Source Library
Murtaza Hassan · Computer Vision ZoneCreated cvzone, a widely used Python wrapper library with over 1M downloads simplifying OpenCV and MediaPipe integrations for hand tracking, facial mesh, and pose estimation.
MediaPipe hand landmarks require unhindered direct line of sight to camera sensor.
Context: MediaPipe, OpenCV, Python, real-time spatial coordinate calculation.
View missionData Science as a Service | Kumo AI Full Walkthrough
James Briggs · James Briggs AI / Vector Search AdvisoryAuthored technical video investigation comparing dense vector embeddings versus reciprocal rank fusion (RRF) with BM25 sparse vectors, demonstrating 28% improvement in Mean Reciprocal Rank (MRR).
Two-stage retrieval pipelines introduce 100-250ms of additional network latency for the reranking stage.
Context: Pinecone, Cohere Rerank, BM25, text-embedding-3-large, LangChain.
View missionDecision Intelligence: The Unifying Framework for AI Strategy
Cassie Kozyrkov · Data ScientificFormulated the foundational principles of Decision Intelligence, integrating managerial science, behavioral economics, and machine learning to improve executive AI decision-making.
Framework requires quantitative literacy across executive leadership teams.
Context: Decision intelligence, statistical hypothesis testing, AI error budgeting.
View missionDeep Learning and Reinforcement Learning Project Blueprints
Nick Renotte · Nicholas Renotte MediaMaintains open-source code repositories with dozens of practical applied AI implementations, including real-time sign language detection and Mario reinforcement learning bots.
Deep reinforcement learning convergence requires millions of simulation steps and careful reward shaping.
Context: OpenAI Gym, Stable-Baselines3, PyTorch, OpenCV.
View missionDeep Speech: Scaling up End-to-End Speech Recognition
Dr. Awni Hannun · Apple Machine Learning ResearchFirst author of the landmark Baidu Deep Speech paper, proving that replacing complex phonetic acoustic pipelines with a single recurrent neural network trained end-to-end with CTC achieves state-of-the-art accuracy in noisy real-world speech.
End-to-end recurrent models without attention mechanisms struggle to maintain alignment over multi-minute audio streams.
Context: Bidirectional RNNs, CTC loss, custom GPU parallel prefix beam search decoders.
View mission