All Documents
3,528 documents available
An Introduction to Transformers
Presents a slide deck introducing transformer architecture, attention mechanisms, and a PyTorch implementation from scratch.
Self-Improving Job Applier — Technical Implementation Spec
Defines a self-improving job application pipeline that scrapes Seek, classifies job descriptions into four archetypes, tracks outcomes via Gmail, and triggers resume rewrites based on market drift.
Tensorus Demo Script: Showcasing Agentic Tensor Management
Walks through six demo scenarios for Tensorus, covering ingestion, querying, tensor operations, MCP integration, and forecasting.
LocalLLM Technical Architecture Documentation
Documents the architecture of an Android app that runs LLMs locally using llama.cpp, with RAG support.
🔥 FIRE — Freedom Intelligent Routing Engine
Routes customer support tickets through LLM classification, geocoding, and a cascade of business rules to assign each to the best manager.
AI Research Assistant Usage Guide
Guides researchers through installing and using a tool that combines knowledge graphs, semantic search, and AI agents for paper analysis.
⚒️ StudyForge: Implementation Plan
Outlines a phased implementation plan for an AI-powered study app that ingests PDFs, generates quizzes and flashcards, and runs locally via Ollama.
Enso Atlas: Technical Specification
Describes a modular, on-premise pathology AI platform with swappable foundation models, classification heads, and config-driven cancer-type projects.
Startup Ecosystem Platform — Implementation Plan
Breaks a full-stack startup platform into 10 ordered phases with checklists for backend, AI, and frontend implementation.
DevFlow Cognitive Task+Memory System - Project Context
Documents a TypeScript cognitive framework with hierarchical task management, SQLite-based persistent memory, and multi-platform AI orchestration.
Development Summary
Documents the development journey of an AI agent server, covering AI-assisted vs hand-written code, bugs, architecture, and production plans.
Feature Deep Dive: Retrieval-Augmented Generation (RAG)
Explains a RAG system that indexes a codebase into a vector store and retrieves relevant chunks to answer general questions via an LLM.
Delivery Shield - Setup Guide
Guides setup of a monorepo refund system with mock and production modes, including MongoDB, Gemini AI, and CDP integration.
Vesper — Implementation Plan
Breaks a journal app build into 5 sequential phases with checkboxes, exit criteria, and file references for each task.
CineChoice RAG Implementation Plan
Plans a RAG movie recommendation system with vector embeddings, semantic search, and AI-generated responses.
Multilingual Agentic RAG (venv, Qdrant, NiceGUI, Gemini-001)
Defines a multilingual agentic RAG pipeline using Gemini embeddings, Tesseract OCR, Qdrant, and NiceGUI with CPU-first defaults.
Software Requirements Specification (SRS)
Defines functional and non-functional requirements for a RAG-based corporate knowledge assistant with citation and hallucination guardrails.
Legal Brief Matcher: Technical Documentation
Documents a legal brief matching system that uses embeddings, citation analysis, and multi-factor confidence scoring to align arguments between opposing briefs.
RAG System Documentation
Documents a full RAG pipeline using MongoDB text search and Gemini for AI answers from user-uploaded study materials.
1. System Architecture
Blueprints a RAG-based SaaS for generating quizzes and summaries from uploaded documents using a decoupled Next.js, FastAPI, and Supabase stack.
plan
Maps a full-stack AI learning platform with Next.js 15, PostgreSQL, Gemini API, and RAG across 8 implementation phases.
🚀 Vectro+ Visual Demo Guide
Walks through embedding compression, quantization, search, and benchmarking commands for the Vectro+ CLI tool.
Quick Start Guide
Walks through installing dependencies, creating Supabase tables, and configuring API keys for a multi-agent AI assistant.
AI Scientist Lab Notebook — Architecture (V1)
Defines the full architecture for an AI scientist lab notebook with RAG, ingestion, and plotting pipelines.