https://cubxxw.com/tags/ai/ Tech blog by Xinwei Xiong — AI Builder, open source contributor and digital nomad sharing Kubernetes, Go, AI projects and travel. https://cubxxw.com/assets/og-image.png https://cubxxw.com/ Hugo -- gohugo.io en-us Mon, 29 Jun 2026 09:30:00 +0800 https://cubxxw.com/growth/posts/2026-03-thought-notes/ Tue, 31 Mar 2026 23:59:59 +0800 Mon, 22 Jun 2026 18:48:25 +0800 熊鑫伟 (Xinwei Xiong) https://cubxxw.com/growth/posts/2026-03-thought-notes/ March 2026 thought notes, 468 entries across 31 days. Covers travel impressions (Cambodia Siem Reap, Angkor Wat, Phnom Penh history), AI Agent architecture and multi-agent system design, Khmer civilization engineering aesthetics, and self-narrative cognitive exploration. Core topics: Gewu/AI (53 entries), Gewu/Cambodia (38 entries), Gewu/Angkor Wat (23 entries), Gewu/Hinduism (15 entries), Guannwo (14 entries), Gewu/Vietnam (11 entries). Growth Blog Monthly Notes Personal Growth Travel Self-Discovery AI https://cubxxw.com/ai-technology/posts/dissecting-open-lovable/ Mon, 29 Jun 2026 09:30:00 +0800 Mon, 29 Jun 2026 23:33:51 +0800 熊鑫伟 (Xinwei Xiong) https://cubxxw.com/ai-technology/posts/dissecting-open-lovable/ A full dissection of firecrawl/open-lovable (27k★, paste a URL and get a working React app in seconds), from product to code. Its most interesting trait isn't that it generates code — it's that it uses no agent framework, no Claude Agent SDK, no native tool-calling. Instead it hand-rolls an entire harness on top of the raw LLM API: a text DSL protocol, streaming regex parsing, truncation detection and recovery, manual context orchestration, plus a swappable cloud sandbox layer (E2B / Vercel Sandbox). This is a case study in taming the raw API. AI & Technology AI Agent LLM Architecture Sandbox Harness https://cubxxw.com/growth/posts/super-individual-ai-product-and-solo-builder-stack/ Wed, 24 Jun 2026 14:55:00 +0800 Wed, 24 Jun 2026 15:27:30 +0800 熊鑫伟 (Xinwei Xiong) https://cubxxw.com/growth/posts/super-individual-ai-product-and-solo-builder-stack/ As the model layer commoditizes and 40% of enterprise AI projects are headed for cancellation, the super-individual finally has the full primitive set to cut into a $4.6T services market. This essay assembles the most current 2025-2026 methodologies into one executable map: the core thesis, six product directions, five ops stacks, the Soul Core + Harness Engineering foundations, and a 12-month roadmap. Growth Super Individual Solo Builder Indie Hacker AI Agent Harness Engineering MCP Product Strategy Personal Growth The Super-Individual Stack: AI-Native Product Directions and Solo Builder Ops in 2026 https://cubxxw.com/ai-technology/posts/relay-agent-architecture-design/ Wed, 24 Jun 2026 10:00:00 +0800 Wed, 24 Jun 2026 14:18:19 +0800 熊鑫伟 (Xinwei Xiong) https://cubxxw.com/ai-technology/posts/relay-agent-architecture-design/ Using the Relay open-source job-search Agent project as a case study, this article fully breaks down every key design decision in a production-grade multi-agent system: why split a single Agent into 5, how to implement HITL checkpoints with LangGraph, how a three-tier LLM router precisely tracks costs, how a fabrication guard validates at runtime, and how a hybrid backend (Hono/Bun + FastAPI/Python) decouples cleanly. Whether you are building your first Agent PoC or pushing toward production, there are design patterns here you can take away. AI & Technology AI Agent LangGraph LLM Architecture TypeScript Python Technical diagram showing the five-layer architecture of the Relay job-search Agent system: UI layer, API orchestration layer, Agent execution layer, shared services layer, and data and integration layer https://cubxxw.com/ai-technology/posts/context-engineering-the-new-foundation/ Mon, 22 Jun 2026 03:30:00 +0800 Tue, 23 Jun 2026 15:16:04 +0800 熊鑫伟 (Xinwei Xiong) https://cubxxw.com/ai-technology/posts/context-engineering-the-new-foundation/ Why context engineering supersedes prompt engineering — a systematic look at context assembly, retrieval, compression, and eviction patterns, drawing from Anthropic, Karpathy, LangChain, and Manus. AI & Technology Context Engineering AI LLM Agent MCP A wide schematic of context engineering: the Write / Select / Compress / Isolate pillars feeding an AI, a laptop with notes, and a local-first world line https://cubxxw.com/ai-technology/posts/agent-engineering-the-98-percent-harness/ Wed, 17 Jun 2026 09:30:00 +0800 Wed, 24 Jun 2026 14:18:30 +0800 熊鑫伟 (Xinwei Xiong) https://cubxxw.com/ai-technology/posts/agent-engineering-the-98-percent-harness/ A panoramic map that treats Agent Engineering as a discipline. Starting from the widely cited claim that only 1.6% of Claude Code is AI decision logic while 98.4% is infrastructure, it walks the eight pillars one by one — orchestration, context, memory, tools, reliability, evaluation, cost, governance — explaining the gap each fills, its minimal implementation, and its failure boundary. It fuses 2025 to 2026 frontline engineering from Anthropic, OpenAI, Cognition, Manus, and Temporal, and lands on one line: the model is bought, the harness is built, and your entire engineering leverage lives in that 98.4%. AI & Technology AI Agent LLM Context Engineering Architecture MCP A technical diagram with a tiny agent loop at the center, surrounded by concentric rings of the eight pillars: orchestration, context, memory, tools, reliability, evaluation, cost, governance https://cubxxw.com/ai-technology/posts/agent-identity-from-locke-to-openclaw/ Sun, 05 Apr 2026 20:00:00 +0800 Mon, 22 Jun 2026 18:48:25 +0800 熊鑫伟 (Xinwei Xiong) https://cubxxw.com/ai-technology/posts/agent-identity-from-locke-to-openclaw/ AI agent amnesia isn't a functional defect—it's a fundamental gap in the trust account. Starting from Locke's 1689 theory of identity, this article dissects the complete engineering stack for agent identity continuity in 2026: file-as-identity (SOUL.md paradigm), Harness as environmental condition, four-layer memory architecture and Gene Capsule protocol, self-positioning in multi-agent topology, and evaluation as the ultimate identity verification challenge. For practitioners building or designing AI agent systems, and researchers deeply thinking about the boundaries of AI autonomy. AI & Technology AI Open Source Monthly Notes Locke Identity Spec — Agent Identity Engineering Stack https://cubxxw.com/growth/posts/weight-of-self-in-ai-age/ Sat, 04 Apr 2026 22:00:00 +0800 Mon, 22 Jun 2026 18:48:25 +0800 熊鑫伟 (Xinwei Xiong) https://cubxxw.com/growth/posts/weight-of-self-in-ai-age/ When AI can replace our thinking, execution, and even creation, where does the weight of "self" come from? This isn't an article about career crisis—it's one person's attempt to figure out why they're still here. Growth AI Personal Growth Self-Discovery How to Maintain the Weight of Self in an Age When You Are No Longer Needed https://cubxxw.com/projects/ai-recommend/ Wed, 23 Apr 2025 10:39:04 +0800 Mon, 22 Jun 2026 18:48:25 +0800 熊鑫伟 (Xinwei Xiong) https://cubxxw.com/projects/ai-recommend/ Exploring AI-powered recommendation systems and how to build personalized content discovery engines. Projects AI Open Source https://cubxxw.com/projects/notebooklm/ Mon, 21 Apr 2025 22:59:57 +0800 Mon, 22 Jun 2026 18:48:25 +0800 熊鑫伟 (Xinwei Xiong) https://cubxxw.com/projects/notebooklm/ Exploring Google NotebookLM as an AI-powered research and note-taking assistant. Projects AI Open Source https://cubxxw.com/projects/tdd/ Mon, 21 Apr 2025 15:52:34 +0800 Mon, 22 Jun 2026 18:48:25 +0800 熊鑫伟 (Xinwei Xiong) https://cubxxw.com/projects/tdd/ Applying Test-Driven Development principles to AI and LLM application development. Projects AI Open Source https://cubxxw.com/projects/markitdown/ Mon, 21 Apr 2025 15:41:21 +0800 Mon, 22 Jun 2026 18:48:25 +0800 熊鑫伟 (Xinwei Xiong) https://cubxxw.com/projects/markitdown/ A deep-dive into Microsoft MarkItDown: an open source Python tool for converting PDF, Word, PowerPoint, Excel, images, audio, and more into Markdown. Covers architecture, installation, hands-on tutorials, LLM integration, security considerations, and comparisons with similar tools. Projects AI Open Source Python LLM RAG https://cubxxw.com/projects/langgraph/ Sat, 19 Apr 2025 15:19:20 +0800 Mon, 22 Jun 2026 18:48:25 +0800 熊鑫伟 (Xinwei Xiong) https://cubxxw.com/projects/langgraph/ Deep dive into LangGraph for building stateful, multi-actor LLM workflows and agent orchestration. Projects AI Open Source https://cubxxw.com/projects/langchain/ Wed, 16 Apr 2025 17:36:45 +0800 Tue, 07 Jul 2026 14:23:03 +0800 熊鑫伟 (Xinwei Xiong) https://cubxxw.com/projects/langchain/ A practical guide to building LLM applications with LangChain — chains, agents, RAG, and the LangChain 1.0 create_agent + middleware model — with hands-on quick-start cases, 2025–2026 frontier updates, and common interview questions. Projects AI Open Source LangChain Agent RAG https://cubxxw.com/projects/ai-gateway/ Wed, 16 Apr 2025 17:36:12 +0800 Mon, 22 Jun 2026 18:48:25 +0800 熊鑫伟 (Xinwei Xiong) https://cubxxw.com/projects/ai-gateway/ A deep dive into AI gateway architecture for managing LLM API traffic, rate limiting, and multi-model routing. Projects AI Open Source https://cubxxw.com/projects/independent-developer/ Tue, 15 Apr 2025 20:53:12 +0800 Mon, 22 Jun 2026 18:48:25 +0800 熊鑫伟 (Xinwei Xiong) https://cubxxw.com/projects/independent-developer/ Reflections on the journey of becoming an independent developer in the AI era. Projects AI Open Source https://cubxxw.com/projects/gpt-researcher/ Mon, 14 Apr 2025 16:17:27 +0800 Mon, 22 Jun 2026 18:48:25 +0800 熊鑫伟 (Xinwei Xiong) https://cubxxw.com/projects/gpt-researcher/ An analysis of the GPT Researcher open source project — autonomous AI agents for deep research tasks. Projects AI Open Source https://cubxxw.com/projects/jina/ Sat, 12 Apr 2025 13:01:59 +0800 Mon, 22 Jun 2026 18:48:25 +0800 熊鑫伟 (Xinwei Xiong) https://cubxxw.com/projects/jina/ Exploring Jina AI's multimodal embedding and search infrastructure for production AI applications. Projects AI Open Source https://cubxxw.com/ai-technology/posts/sora-ease-guide-mastering-sora-ai-for-developers/ Thu, 14 Mar 2024 08:44:13 +0800 Tue, 07 Jul 2026 15:43:20 +0800 熊鑫伟 (Xinwei Xiong) https://cubxxw.com/ai-technology/posts/sora-ease-guide-mastering-sora-ai-for-developers/ This comprehensive guide introduces Sora AI, offering developers an accessible, automated, and swift path to harnessing its potential. Dive into various scenarios, master commanding Sora, and explore the multi-faceted applications of this AI model trained to understand and simulate the physical world in motion. Whether you're seeking the latest Sora news, development projects, or open-source contributions, this article is your gateway to the expansive world of Sora AI development. AI & Technology Blog sora AI github https://cubxxw.com/ai-technology/posts/exploring-sora-technology-for-enthusiasts-and-developers/ Sat, 24 Feb 2024 13:30:15 +0800 Tue, 07 Jul 2026 15:43:20 +0800 熊鑫伟 (Xinwei Xiong) https://cubxxw.com/ai-technology/posts/exploring-sora-technology-for-enthusiasts-and-developers/ Dive into the world of Sora Technology, a groundbreaking platform for AI-driven video generation. This post is designed for both tech enthusiasts and developers eager to unlock the potential of Sora. Discover how you can leverage Sora to create stunning, AI-generated videos with ease, and join a community of innovators transforming the digital landscape. AI & Technology Blog sora AI chatgpt https://cubxxw.com/ai-technology/posts/vector-database-learning/ Sat, 20 Jan 2024 12:57:15 +0800 Mon, 22 Jun 2026 18:48:25 +0800 熊鑫伟 (Xinwei Xiong) https://cubxxw.com/ai-technology/posts/vector-database-learning/ An introduction to vector databases for AI applications. Starts from the prerequisites, the basics of vectors, similarity measures such as cosine similarity, and database indexing, then explains how vector databases differ from traditional databases and where they fit in AI. AI & Technology Blog AI Database https://cubxxw.com/ai-technology/posts/use-auto-gpt/ Sat, 18 Mar 2023 16:28:30 +0800 Mon, 22 Jun 2026 18:48:25 +0800 熊鑫伟 (Xinwei Xiong) https://cubxxw.com/ai-technology/posts/use-auto-gpt/ Learn how to install and use Auto-GPT for autonomous AI task automation, including setup, configuration, and practical use cases. AI & Technology Blog AI autogpt