FareedKhan-dev

A straightforward method for training your LLM, from downloading data to generating text.

A 2.78-trillion-parameter Kimi K3 running inference on a single CPU in 8.24 GB of RAM. Portable C99: no BLAS, no framework, no GPU.

35 production-grade agentic AI architectures (Reflexion, LATS, GraphRAG, MemGPT, Voyager, BrowserAgent, ...) — a Python library and runnable textbook with multi-provider LLM support and a 17-task...

Implementation of all RL algorithms in a simpler way

Core 7 layers of production grade agentic system

Building DeepSeek R1 from Scratch

A step by step implementation of a complex RAG pipeline to solve real world situations

Building a Multi-Agent AI System with LangGraph and LangSmith

9 Different Ways to Optimize AI Agent Memories

23 Components of the Claude Code Architecture

Converting Unstructured Data to a Knowledge Graph: An End-to-End Pipeline

Understand and code every important component of RAG architecture

In this blog, we will build a small scale text-to-video model from scratch. We will input a text prompt, and our trained model will generate a video based on that prompt.

Agentic RAG to achieve human like reasoning

Self improving agentic rag pipeline

LLaMA 3 is one of the most promising open-source model after Mistral, we will recreate it's architecture in a simpler manner.

Building a 2.3M-parameter LLM from scratch with LLaMA 1 architecture.

Handling 10M+ docs using RAG with zero hallucinatons

A scalable RAG platform combining LangGraph agents, hybrid retrieval (Vector+Graph), and Ray orchestration on Kubernetes.

Agentic RAG, Multi-Agent Systems, and Vision Reasoning are three pipelines to find the perfect LLM

A Deep Thinking RAG Pipeline to Solve Complex Queries

Implementation of Deep Thinking Trading System

Core concepts - where to apply parallelism in agentic solution

Optimizing Dynamic Knowledge Base Using AI Agent

Maximizing the Performance of a Simple RAG using RL

Implementation of contextual engineering pipeline with LangChain and LangGraph Agents

Building a Senior Staff Engineer with Sub-Agent Teams in Claude Code

Implemented a stable diffusion architecture using PyTorch.

LLM Based NLP Library.

A Straightforward, Step-by-Step Implementation of a Video Diffusion Model

Some words that LLM regularly uses

A Step-by-Step Implementation of Qwen 3 MoE Architecture from Scratch

A Step-by-Step Implementation of Google Veo 3 Architecture from Scratch

Building LLaMA 4 MoE from Scratch

Implementation of a GPT-4o like Multimodal from Scratch using Python

Training architecture for self-improving AI agents.

GLM-5.2, a 744 billion parameter mixture of experts model, in a pure C inference engine: quantized to int4, experts streamed from disk, deployed and benchmarked. Generates in 16 GB of RAM.

Different Types of Prompt Engineering Techniques

Building a Tiny GPU to understand AI hardware engineering

Building a Claude-like agentic system.

Knowledge-graph RAG built from structured metadata instead of LLM extraction. 929M edges, zero LLM calls, 83.2% on held-out PubMedQA. Case study: the full PubMed 2026 baseline.

Building a Production-Grade MCP Server Architecture with a Multi-Agent System

A multi-agent system trained with GRPO for reliable long-horizon task planning and execution.

A detail Implementation of handling long-term memory in Agentic AI

AI agent that controls a computer

An 18 notebook course that isolates and measures each component of agentic loop engineering on real, industry standard software datasets.

Train a 29M parameter GPT from Scratch

Deep research agentic system using Time Test Diffusion

Implementation of 12 AI agents evaluation techniques

Layered guardrails to make agentic AI safer and more reliable.

A step by step implementation to build an agent that runs for week to complete a task and self improve.