157 related articles

LangChain is the leading open-source framework for LLM application development, supporting GPT-4, GLM, and other mainstream models. This article dives into its three core concepts: Components, Chains, and Agents.

In-depth Grok 4.5 hands-on review: priced at a fraction of Opus 4.8, twice the token efficiency of peers, and coding ability in the top tier. A real-project breakdown of its strengths, highlights, and shortcomings.

Microsoft SQL team's major updates: Azure SQL adds AI embeddings and dynamic data masking, Fabric SQL gets a Migration Assistant and Fabric Apps, SQL Server CU5 brings memory improvements, SSMS adds a SQL Formatter and Agent mode, and DP-800 certification is now open.

OpenAI has dropped SWE-Bench Pro as a recommended AI coding benchmark, exposing deep issues like data contamination and metric limitations. We explore the trust crisis and where evaluation is headed.

LangChain is an open-source framework connecting LLMs with external data. This guide explains its three core components: Components, Chains, and Agents for enterprise AI development.

Learning Python from scratch? This article breaks down the three learning stages—Fundamentals, Intermediate, and Practice—covering variables, OOP, scraping, and data analysis to help you plan a systematic Python path.

Want to learn Python from scratch but don't know where to begin? This article breaks down three stages—basic syntax, advanced mastery, and hands-on practice—with real projects in crawling, automation, and data analysis to help you build programming thinking.

A comprehensive introduction to FastAPI's core concepts: frontend-backend separation, RESTful API design, JSON data exchange, HTTP methods, and idempotency explained clearly.

In-depth look at DryFox v0.3.3's three core features: multi-role agent team collaboration, one-click reusable team templates, and block-style composable UI panels. With Stop Hook, file mailbox comms, and hot-reload plugins.

An in-depth analysis of LangGraph's core concepts: short-term and long-term storage mechanisms, its differences from LangChain, the MIT open-source license, and private deployment solutions for enterprise Agent development.

Claude Code is Anthropic's local AI coding assistant featuring full project context, auto error correction, and high-accuracy code generation. Compare it with Cursor, Trae, and Codex.

Deep dive into LangChain 1.0's architecture: LangChain framework, LangGraph multi-Agent orchestration, and LangSmith observability platform, with hands-on RAG and intelligent customer service projects.

Creator Ajiang burned 10B Tokens on Codex to migrate cc-haha from Tauri 2 to Electron. A deep dive into Codex's long-horizon engineering, Computer Use, costs, and practical advice for developers.
The Open Source AI Landscape: How the …
Current AI's Open Source AI Gap Map catalogs 421 products across models, tools, datasets, and hardware, tracking ~24,800 entries. All data is MIT-licensed and open on GitHub.
sqlite-utils 4.0rc2 Released: Major Ve…
Simon Willison releases sqlite-utils 4.0rc2, with most code written by Claude at just $149.25 in API costs. A deep dive into AI-assisted development costs and human-AI collaboration.
Claude Leads sqlite-utils 4.0 Developm…
Simon Willison reveals sqlite-utils 4.0 was mostly written by Claude for $149.25. A deep dive into this AI-led development experiment and what it means for developers.

Deep dive into LangChain's core Model and Agent concepts, covering unified model interfaces, agent tool calling, middleware mechanisms, and key principles for building LLM applications.

Learn FastAPI from the ground up: understand frontend-backend separation, Starlette's ASGI architecture, and RESTful API design before writing a single line of code.

Build a complete project with AI from scratch! This guide covers Cursor's three chat modes (Agent/Ask/Manual), Claude model selection, and a Python student management system walkthrough.

Learn how to build a Python student management system from scratch using Cursor AI — covering Agent/Ask/Manual modes, Claude model selection, auto error fixing, and environment setup.