K

.md Directory

All Documents New Popular

K

All Documents — .md Directory | Neura Market

All Documents

3,528 documents available

SKILL.md

Traul — Personal Intelligence Engine

description: Personal Intelligence Engine CLI for syncing, searching, and monitoring messages from Slack, Telegram, Discord, Linear, Gmail, Claude Code sessions, Markdown files, and WhatsApp. Use when working with traul commands, message sync, search, signals, briefings, or browsing chat history.

airagclaude

dandaka

FAILURE_MODES.md

uwot (development version)

* New parameter: `n_build_threads`. Controls the number of threads used to build

jlmelville

FINE_TUNING.md

Transformer Model Technical Research Analysis

This document provides an analysis of the hyperparameters and configurations of the given Transformer model, focusing on dimensions, depth, and heads, as well as an architectural overview of their meanings and use cases.

kyegomez

EMBEDDINGS.md

Go-Attention API Documentation

This document provides a complete reference for all exported APIs in the go-attention library.

takara-ai

ARCHITECTURE.md

Version 1 Mental Model

- **chris-additional-details.md** — Source of truth for supplementary Chris details. Structured with `**Topic:**` bold headers that the parser splits on. Content lives below the `---` separator.

aipromptsafety

cfornesa

RAG.md

vlite Documentation

vlite is a simple and blazing fast vector database. It allows you to store and retrieve data semantically using embeddings.

sdan

ARCHITECTURE.md

Qwen3-TTS — Model Reference

Models: `Qwen/Qwen3-TTS-12Hz-0.6B-CustomVoice` and `Qwen/Qwen3-TTS-12Hz-1.7B-CustomVoice`

aillm

gabriele-mastrapasqua

RAG.md

Loop #1 – RAG Pipeline

Building a YouTube video RAG pipeline for an AI coach agent. The pipeline pulls transcripts from a specific YouTube channel, chunks them, embeds them, and stores them in a vector database for agent retrieval.

aiagentrag

gek007

MCP.md

Criterion MCP Server

Connect Criterion's semantic Islamic search to AI assistants like Claude Desktop, Cursor, and other MCP-compatible clients.

aiagentmcp

BalajSaleem

EMBEDDINGS.md

Embedding-Based Memory Recall — Implementation Plan

Replace LIKE keyword search with semantic vector search for MemoryFS memory

aillmrag

project-ax

RAG.md

FastEmbed-rb Roadmap

This document outlines features from the original [FastEmbed Python library](https://github.com/qdrant/fastembed) that are not yet implemented in fastembed-rb.

aieval

khasinski

RAG.md

Implementation Plan: codeindex

We're building a local semantic index for codebases that augments Claude Code's Glob/Grep/Read tools with embedding-based search. The design is informed by OpenViking (AST skeletons, bottom-up directory summaries, score propagation), Augment Context Services (single retrieval tool for agents), sigma-ralph-grindset (`claude --print` as LLM backend), and db-harness (Bun-native dual-database skill pattern).

aiagentllm

smart-knowledge-systems

EMBEDDINGS.md

Building SupportX AI Assist: A Multi-Agent IT Support System

**Published:** February 9, 2026

aiagentllm

iftikar0016

ARCHITECTURE.md

Part 2: Latent Action Prediction Model

This part focuses on building a model that can infer latent actions between consecutive frames. Following the LAPA paper, we'll use a VQ-VAE-inspired approach to learn a discrete codebook of latent actions that explain the transitions between frames.

airag

paraschopra

PRD.md

Product Requirements Document — `codex-prompt-refinery`

Local tool that ingests **OpenAI Codex CLI** history under `~/.codex/**`, extracts prompts and nearby assistant replies, deduplicates and groups related prompts, and auto-synthesizes **atomic** and **workflow** prompts via the **OpenAI Responses API** using **Structured Outputs**. Single **SQLite** database with **FTS5** keyword search and **sqlite-vec** semantic search. Minimal **Streamlit** UI to search, view, specialize, and copy prompts. Optional daily automation via **systemd** on WSL2.

aiagentprompt

BjornMelin

EMBEDDINGS.md

Dynamic Coattention Networks For Question Answering

This paper aims to provide a model for QA. It encorporates a novel co attention system between the question and the passage. The basic gist of this paper is that attention is usually calculated for a single entity, or vector.

karanchahal

RAG.md

The Annotated Encoder-Decoder with Attention

bastings

SKILL.md

Memory Compass - 记忆罗盘 ⭐⭐⭐⭐⭐

> **「在数字沧海中，找到你的方向」**

aiagent

wbin0001

EMBEDDINGS.md

Agent Learnings - Papr Memory Python SDK

This document captures important learnings and best practices discovered while building and maintaining the Papr Memory Python SDK, specifically around on-device processing and Core ML integration.

aiagent

Papr-ai

FAILURE_MODES.md

ChronoMind Development TODO

This document outlines the current state of the ChronoMind project and provides a roadmap for future development. It's designed to help new developers quickly understand what has been done and what needs to be done next.

airageval

JtPerez-Acle

FINE_TUNING.md

Model Documentation

CodeOriginClassifier uses **microsoft/codebert-base** as its pre-trained encoder. CodeBERT is a RoBERTa-base model (12 transformer layers, 768 hidden dimensions, 125M parameters) that was further pre-trained on the CodeSearchNet corpus using two objectives:

aillmrag

CyberKatsu

FINE_TUNING.md

- The bellow results for BERT is not valid now. because BERT is used as feature-based currently.

rageval

dsindex

DEPLOYMENT.md