#PyTorch Foundation
323 related articles
Product Reviews·4 min
AI Coding Tools Compared: Free Plans for Students Using Trae/Cursor/Claude Code
Compare Trae CN, Cursor, VS Code plugins, and Claude Code across cost, ease of use, and flexibility. Get free and low-cost AI coding setup recommendations for students.
Read more →
Tutorials·3 min
Build a Local Image Generation MCP Server with One Prompt: Let Codex Batch Generate and Edit Images
Learn how to build a local image generation MCP Server with one Prompt, letting Codex call Flux models for zero-token batch image generation and editing.
Read more →
Tutorials·4 min
2025 LLM Career Transition Roadmap: A Three-Phase Plan from Foundations → Frameworks → Real-World Projects
A systematic 2025 LLM career transition roadmap covering Python, Transformers, LangChain, LlamaIndex, RAG, Agent development, and fine-tuning across three phases achievable in 2-3 months.
Read more →
Deep Dives·3 min
MCP Protocol Explained in 3 Minutes: The USB-C Standard for AI
A clear breakdown of MCP (Model Context Protocol): its core concepts, three standard primitives, real-world use cases, and ecosystem status. Learn how Anthropic's open-source unified tool integration standard is changing AI development.
Read more →
Tutorials·3 min
AI Agent Learning Roadmap: A Complete Guide from LangChain to Enterprise Deployment
In-depth analysis of the popular GitHub project ai-agents-from-zero, covering LangChain, LangGraph, RAG, MCP and more, with a complete learning path from beginner to enterprise AI Agent development.
Read more →
Product Reviews·3 min
GPT-5.5 Hands-On Review: Image Generation at Just 3 Cents Per Image, Plus a Full Breakdown of Coding Capabilities and API Costs
Hands-on review of GPT-5.5 image generation and coding abilities. API image generation costs as low as 3 cents per image. Full breakdown of quality, capabilities, and cost comparisons.
Read more →
Tutorials·2 min
Dify Java Client: Best Practices for Integrating AI into Java Projects
dify-java-client is an open-source Java client library for integrating Dify's generative AI capabilities. It supports chat, text generation, workflows, and knowledge base APIs with streaming responses and type-safe wrappers for enterprise scenarios.
Read more →
Product Reviews·3 min
BuildingAI Open Source Project Deep Dive: Building AI Apps Like Stacking Blocks
Deep dive into BuildingAI, an open source block-based AI app builder with 1600+ Stars. Explore its architecture, use cases, and how it compares to Dify and Coze.
Read more →
Tutorials·3 min
NVIDIA Nemotron Labs Open Source Contribution Guide: A Complete Playbook for Developers Joining AI Open Source Projects
A comprehensive guide to contributing to NVIDIA Nemotron Labs open source projects, covering NeMo framework contributions, community participation, and career benefits for AI developers.
Read more →
Deep Dives·3 min
Claude Code Source Code Leak Revealed: Seven Core Mechanisms of the Harness Architecture Explained
Deep analysis of the Claude Code source code leak, revealing seven core mechanisms of its Harness architecture including context management, tool call orchestration, and state tracking for AI Agent developers.
Read more →
Deep Dives·3 min
Deep Dive into Tencent's Open-Source WeKnora: An All-in-One Knowledge Platform with RAG + Agent + Wiki
Deep dive into Tencent's open-source LLM knowledge platform WeKnora, covering RAG, autonomous reasoning Agent, and self-maintaining Wiki capabilities, plus its Go-based architecture and enterprise use cases.
Read more →
Tutorials·3 min
4-bit QLoRA Fine-tuning LLaMA 3 in Practice: A Guide to Training 8 Billion Parameter LLMs on Consumer GPUs
Learn how to fine-tune LLaMA 3 8B on consumer GPUs using QLoRA and Unsloth. Covers 4-bit quantization, LoRA adaptation, Alpaca data format, training pipeline setup, and model deployment—runs on RTX 3090.
Read more →
Deep Dives·4 min
Hugging Face Transformers: Deep Dive into the 160K-Star Open Source AI Framework
Deep dive into Hugging Face Transformers: the 160K-Star open-source framework covering Pipeline API, Auto Classes, multi-modal models, and the full HF ecosystem for AI inference and training.
Read more →
Tech Frontiers·3 min
Karpathy Open-Sources autoresearch: A Deep Dive into the AI-Powered Automated Research Tool with 80K Stars
Andrej Karpathy open-sources autoresearch, an AI Agent tool that automates nanochat training experiments on a single GPU. With 80K+ GitHub Stars, we break down its architecture and impact.
Read more →
Tutorials·2 min
Ruby-OpenAI: A Complete Guide to Integrating GPT-5 and WebRTC Real-Time Voice in Rails
ruby-openai is an open-source library with 3,200+ GitHub stars, supporting GPT-5 and WebRTC real-time voice. Learn how to integrate OpenAI API into Ruby on Rails for AI-powered apps.
Read more →
Tutorials·3 min
The Complete Guide to MLflow: An Open-Source AI Engineering Platform from Experiment Tracking to LLM Deployment
A deep dive into the MLflow open-source AI engineering platform, covering experiment tracking, LLM evaluation, model deployment, and monitoring to help teams efficiently manage the ML lifecycle.
Read more →
Tutorials·3 min
Hermes Agent Chinese Guide: 16 Volumes, 300K Words from Beginner to Multi-Agent Orchestration
Deep dive into hermes-agent-guide: a 16-volume, 300K-word Chinese manual covering installation, memory systems, skill ecosystems, multi-Agent orchestration, and enterprise deployment.
Read more →
Product Reviews·3 min
Micro-Agent: Fudan University's Open-Source Lightweight AI Agent Framework Built for Vertical Domains
Micro-Agent is a lightweight AI Agent framework open-sourced by Fudan University, focused on vertical domain applications. It offers streamlined architecture, low learning costs, and high customization flexibility compared to heavyweight frameworks like LangChain.
Read more →
Tutorials·3 min
Pixelle-Video Open Source Tutorial: Deep Dive into the AI Fully Automated Short Video Engine with 14K Stars
Deep dive into Pixelle-Video, a trending open-source AI short video engine with 14K+ GitHub Stars. Explore its end-to-end automation, architecture, use cases, and how to get started.
Read more →
Tutorials·2 min
Unsloth Tutorial: A Guide to Fine-Tuning LLMs Locally with Reduced VRAM and Faster Training
Learn how Unsloth enables efficient local LLM fine-tuning with LoRA optimization, supporting Gemma 4, Qwen3, and DeepSeek while reducing VRAM usage by 50% and boosting training speed 2-5x.
Read more →