Agent Protocol Stack: MCP, A2A, and AG-UI

• Introduction to the Agent Protocol Stack: MCP, A2A, and AG-UI
• Architecture and Core Components of the A2A Protocol
• Typical Interaction Flow in the A2A Protocol
• Architecture, Workflow, and Core Technical Features of AG-UI

CrewAI: The Leading Multi-Agent Framework

• Two Automation Modes in CrewAI: Crews & Flows
• Flow Control Logic of CrewAI Flows
• Three Modular Components of CrewAI Crews (Agents, Tasks, Crews)
• CrewAI Use Case: Stock Analysis System

Mem0: A Memory Layer Framework for Empowering AI Agents

• Distinguishing Memory-Related Concepts
• What Problems Does Mem0 Solve?
• Mem0 Technical Architecture
• Mem0 Performance

Using n8n to Build a Telegram Personal Assistant

• What is n8n and How to Use n8n
• Creating a Telegram Bot
• Setting Up Telegram Trigger in n8n
• Complete Workflow

BERT, ColBERT and ColPali

• BERT
• ColBERT
• ColPali

AI Code Editor Source Code Exploration

• Introduction to Void AI Code Editor
• Overall Source Code Architecture
• Key Functional Source Code Details

MCP Technical Overview

• Concept, Evolution, and Significance of MCP
• MCP Architecture, Core Components, and Function Types
• MCP Client and MCP Server
• How Different Roles Use MCP

EasyR1 + Verl + Ray + QwenVL + GRPO

• Background Introduction
• GRPO Four Main Steps
• Implementation of GRPO Training Code Using EasyR1
• Practical Record of GRPO Training Details

SFTTrainer Source Code Exploration: Prepare Train

• Prepare Train Overall Logic
• Prepare Train Code Details
  • _inner_training_loop
  • training_step
  • compute_loss
  • PeftModelForCausalLM.forward
  • Linear4bit.forward

SFTTrainer Source Code Exploration: Prepare Dataset

• Prepare Dataset Overall Logic
• Prepare Dataset Code Details
  • SFTTrainer.init
  • DataCollatorForLanguageModeling
  • _prepare_dataset