#AI编程
9716 related articles
AI Agent Security Guardrails in Practice: Permission Control, Input/Output Validation, and Risk Isolation
Learn how to implement AI Agent security guardrails: middleware hooks, permission control, input/output validation, data desensitization, and two protection strategies.
No Root Required: 4 Technical Approaches to Letting AI Send WeChat Messages Autonomously
How can AI send WeChat messages without root? This article compares 4 technical approaches—accessibility service, system assistant, root/hook, and official API—and demos a one-line command that lets AI send a message autonomously.
What Is Harness Engineering? The Origins and Real-World Applications of Agent Harnessing
What is Harness Engineering? Explore its origins, core engineering principles, and mature products like OpenCloud and Codex to understand what makes AI Agent projects production-ready.
LangChain Getting Started: Why LLM Applications Can't Do Without It
A beginner's guide to LangChain: understand its role as an LLM application framework, the three core limitations of standalone LLMs, and how LangChain addresses them to power RAG and Agent applications.
Dify in Practice: Building an ECharts Data Visualization Assistant with Workflows
A step-by-step breakdown of building an ECharts data visualization assistant with Dify workflows — covering document extraction, format conversion, parameter extraction, and code execution nodes.
Claude Opus 5.5 Lands on Devin: Top Benchmark Performance at a Fraction of the Cost
Claude Opus 5.5 is now integrated into Devin Desktop and CLI. It tops FrontierCode 1.1, outperforming Fable 5 and GPT-6 Astra, at less than one-tenth the cost of Fable 5.
Vercel AI SDK Releases @ai-sdk/tui 1.0.111 Patch Update
Vercel AI SDK releases @ai-sdk/tui 1.0.111 patch update, syncing the core dependency to ai@7.0.110. Learn what changed and what it means for developers.
Vercel AI SDK Vue Releases 3.0.288 Patch Update
Vercel AI SDK releases @ai-sdk/vue@3.0.288 patch update, synced with ai@6.0.288 core package. Learn about the update, versioning strategy, and upgrade tips for Vue developers.
Vercel AI SDK Releases @ai-sdk/vue 2.0.263 Patch Update
Vercel AI SDK releases @ai-sdk/vue 2.0.263 patch update, syncing with core package ai@5.0.263. Learn what changed, the engineering release cadence, and upgrade advice for Vue developers.
Vercel AI SDK Update: @ai-sdk/workflow 2.0.41 Release Notes
Vercel AI SDK's @ai-sdk/workflow updated to 2.0.41 patch release. Core change: dependency sync to ai@7.0.110. Learn about the workflow module and upgrade guidance.
Vercel AI SDK Vue Package Releases Patch Update 4.0.110
Vercel AI SDK releases @ai-sdk/vue@4.0.110 patch update, syncing the underlying ai@7.0.110 dependency. Learn about the changes and what they mean for Vue developers.
Claude Opus 5.5 Deep Dive: Intelligence, Performance, and Pricing — A Three-Dimensional Review
A three-dimensional deep dive into Claude Opus 5.5 — evaluating Anthropic's flagship LLM on intelligence benchmarks, response speed, and token pricing to help developers assess the capability premium.
Vercel AI SDK Releases workflow-harness 1.0.120 Patch Update
Vercel AI SDK releases @ai-sdk/workflow-harness 1.0.120 patch update, syncing dependency versions. A look at what this means for AI app developers.
WorkBuddy Desktop AI Agent Beginner's Guide: Installation & Key Configuration
A beginner's guide to WorkBuddy desktop AI agent: installation, workspace path setup, disabling data collection, adjusting tone, custom instructions, and enabling memory.
AI + Playwright Automated Testing: A Framework That Writes Its Own Test Cases
Playwright is replacing Selenium as the new standard for Web automation testing. This article compares both tools and shows how AI enables frameworks that write their own test cases.
Building a Test Case Generation Agent from Scratch: A Deep Dive into Testing Agents and Intelligent Testing Platforms
A deep dive into intelligent testing with DeepSeek Harness: building Web automation agents, optimizing agent speed with No-Thinking mode, and using workflows, RAG, and knowledge graphs to generate high-coverage test cases.
Chinese Open-Source Agent CyberCode Integrates JEF: Real-World Speed Tests for Coding & Browser Automation
CyberCode 1.1.24 integrates JEF fast judgment engine to cut AI coding latency via intelligent context pruning and browser automation. Setup guide and honest speed analysis.
Complete Guide to Building Your Hermes AI Employee: From Claude Code Deployment to Automated Social Media
Step-by-step guide to building a Hermes AI agent: Claude Code deployment, Hetzner server setup, Composio integrations, Unipile social DM automation, and 35 scheduled tasks running 24/7.
Open-Source QA Agent in Practice: An End-to-End Testing Workflow That Tackles AI Hallucinations and Testing Bottlenecks
Open-source QA Agent by Ming Dui: an 8-Skill end-to-end testing pipeline that fights AI self-evaluation hallucinations and solves testing bottlenecks in AI Coding workflows.
AI Large Model Testing in Three Phases: The New Paradigm from Assertions to Evaluation
AI testing is shifting from assertions to evaluation. This guide covers Testing with AI, alongside AI, and of AI — plus LLM, RAG, and Agent evaluation layers, version pinning, and Promptfoo.