K

.md Directory

All Documents New Popular

K

All Documents — .md Directory | Neura Market

All Documents

3,528 documents available

ARCHITECTURE.md

LocalLLM Technical Architecture Documentation

LocalLLM is a high-performance Android application designed to run Large Language Models (LLMs) locally on-device. It leverages the `llama.cpp` library for efficient inference, enabling users to interact with state-of-the-art AI models without an internet connection, ensuring complete data privacy. The application supports text generation, vision capabilities (multimodal), and Retrieval Augmented Generation (RAG) for document analysis.

aillmrag

Soham-Kamathi

EMBEDDINGS.md

Tensorus Demo Script: Showcasing Agentic Tensor Management

This demo showcases the key capabilities of Tensorus, an agentic tensor database/data lake. We'll walk through data ingestion, storage, querying, tensor operations, and how to interact with the system via its UI and APIs.

aiagentrag

tensorus

ARCHITECTURE.md

DevFlow Cognitive Task+Memory System - Project Context

DevFlow is a sophisticated cognitive computing framework built with TypeScript that provides intelligent task management and persistent memory systems. The project implements a structured approach to handling cognitive workloads with built-in memory persistence, semantic search capabilities, and multi-platform AI orchestration.

aiagentrag

fulvian

RAG.md

Feature Deep Dive: Retrieval-Augmented Generation (RAG)

This document explains the implementation of the Retrieval-Augmented Generation (RAG) system, which forms the backbone of the agent's ability to answer general, open-ended questions about the codebase.

aiagentllm

EuclidStellar

RAG.md

Socrates Development Plan

- Create two top-level folders: `backend/` and `frontend/`

aiagentllm

jaypee15

SPEC.md

Self-Improving Job Applier — Technical Implementation Spec

**Audience:** LLM or developer implementing this system.

aiagentllm

wmarzella

SPEC.md

Technical Requirements Document (TRD)

**Origin:** [Peter Steinberger's tweet](https://x.com/steipete/status/2023057089346580828) requesting AI tooling for PR/Issue deduplication and triage on OpenClaw (180K+ stars, 3100+ open PRs)

aiworkflow

Sauhard74

SPEC.md

scope

A Python-based tool to download video transcripts and comments from YouTube channels for market research. The goal is to inform a market garden and orchard business plan focused on regenerative agriculture. The system performs a multi-stage AI processing pipeline on the raw data, structuring it into a normalized database of topic-based summaries and atomic insights. A hybrid search system combines full-text search with AI-powered semantic search via vector embeddings for comprehensive data disco

aiprompt

suffering-git

EMBEDDINGS.md

ReachInbox Email Aggregator - Development Plan

Build an AI-driven email onebox aggregator with real-time IMAP synchronization, intelligent categorization, and RAG-powered reply suggestions using TypeScript and Node.js.

airaggemini

ALANAK777

EMBEDDINGS.md

BigLake Iceberg Pipeline — Demo Scenarios

Demo data: `thelook_ecommerce` from BigQuery public dataset (7 tables).

aiagentprompt

anthonymm-google

RAG.md

Building a RAG Pipeline from Scratch

**Retrieval-Augmented Generation (RAG)** is the technique behind most production AI assistants today. Instead of asking an LLM to recall facts from training, you give it relevant context at query time. The result is more accurate, grounded, and up-to-date answers.

aillmrag

chapagainmanoj

SPEC.md

arXiv Knowledge Base — Specification

**Last updated:** 2026-01-31

airagmcp

Orolol

DEPLOYMENT.md

AI Code Migration Assistant — Architecture (Deployment‑Ready)

- **Frontend/BFF**: Next.js 14 (App Router) on Vercel; Server Actions for clone tokens & exports; SSR dashboards.

aiagentrag

derril-tech

RAG.md

Multilingual Agentic RAG (venv, Qdrant, NiceGUI, Gemini-001)

- venv only; Windows-first; no WSL

aiagentllm

AyushDhimann

RAG.md

Contract RAG MVP — Plan

A standalone MVP application where:

aillmrag

ipushpie

RAG.md

RAG System Documentation

Detailed documentation of the Retrieval-Augmented Generation (RAG) implementation in Tu2tor.

airagprompt

yorhagengyue

EMBEDDINGS.md

Legal Brief Matcher: Technical Documentation

- **Primary Model**: `all-MiniLM-L6-v2` base model with legal domain fine-tuning

aiworkflow

arpansethi30

SOP.md

Delivery Shield - Setup Guide

This guide will help you set up and run the Delivery Shield x402 refund system.

airaggemini

AbhayRathi

RAG.md

plan

AI-Powered Supplementary Learning Platform

airaggemini

nekrei

SPEC.md

Software Requirements Specification (SRS)

Project: Context-Aware Corporate Knowledge Assistant

aillmrag

dheerajgaurgithub

EMBEDDINGS.md

Vesper — Implementation Plan

> Source of truth for what to build. Every task must be checked off before moving to the next.

di5ha

EVALS.md

Hallucination Guard - System Documentation & Literature Review

**Hallucination Guard** is a state-of-the-art AI trust engine designed to detect, analyze, and mitigate hallucinations in Large Language Model (LLM) outputs. As LLMs become integrated into critical workflows, the risk of "hallucinations"—plausible-sounding but factually incorrect or nonsensical statements—presents a significant challenge. This project provides a scientific dashboard for real-time verification using multiple advanced methodologies.

aillmrag

MKJaswanth

RAG.md

Schema-Driven Document Extraction Service (Gently Take-Home)

Building Option 1 from Gently's take-home challenge: a service that ingests documents, classifies them against user-defined schemas, extracts structured data, and makes it queryable. Framed for ERP domain (invoices, purchase orders, receipts, contracts).

aillmprompt

benjgrad

DEPLOYMENT.md

AI DevOps Copilot — ARCH.md

- **Frontend/BFF**: Next.js 14 (App Router) on Vercel (SSR for timelines, Server Actions for webhooks/exports).

aiagentrag

derril-tech

Page 84 of 147