Focused on deep research and development of large-model applications. Authors of "RAG Application Development and Optimization Based on Large Models" and "MCP Principles Unveiled and Development Guide". Primarily B2B, with B2C as a supplement.
This guide walks through the MemOS open‑source memory framework, showing how to create a graph‑based memory ChatBot, add and retrieve memories incrementally, enable asynchronous memory reorganization, and seamlessly integrate the system into LangChain 1.x agents using middleware.
This article explains the order‑blindness of Transformer self‑attention, why naïvely adding raw position indices harms semantics, and walks through sinusoidal, learnable, and rotary positional encodings together with PI and YaRN techniques for extending sequence length.
This article explains MemOS’s novel approach to treating AI memory as an operating‑system resource, detailing its layered architecture, core modules, three memory forms, and practical SDK usage for cloud or self‑hosted deployments, while highlighting performance benefits and engineering constraints.
This article explains the inherent limitations of single-head attention in Transformers, illustrates them with a linguistic example, and then details how multi-head attention works through independent projection matrices, splitting and concatenation, ultimately boosting model expressiveness, robustness, and interpretability.
This article explains how to bring Anthropic's Skills concept into the open‑source LangChain DeepAgents framework by detailing the discovery, system‑prompt injection, progressive loading, and execution phases, and provides a complete code‑driven example using a web‑research Skill.
This article explains the A2UI (Agent‑to‑UI) protocol, a declarative JSON‑based UI description format that enables AI agents to generate and update interactive interfaces safely across platforms, detailing its challenges, design principles, workflow examples, and its relationship with AG‑UI and CopilotKit.
This guide shows how to use the open‑source BISHENG low‑code platform, ByteDance’s Seed‑1.6 and Seedream‑4.5 models, and a custom MCP server to build a workflow that uploads documents, performs RAG, generates structured PPT outlines with LLMs, creates page images via text‑to‑image models, and assembles a downloadable PDF, all while incorporating human‑in‑the‑loop controls.
This article breaks down Anthropic’s latest Agent engineering concepts—MCP, Programmatic Tool Calling (PTC), Skills, and Subagents—showing how they work together to reduce latency, token cost, and context overload while enabling modular, scalable AI workflows.
This article examines the limitations of LLM short‑term context windows and compares three open‑source long‑term memory frameworks—Mem0, Graphiti, and Cognee—by detailing their architectures, storage modes, integration steps, code examples, strengths, drawbacks, and practical selection guidance for building smarter AI agents.
This article breaks down the end‑to‑end engineering pipeline that converts a knowledge source such as a URL or PDF into a narrated PPT‑style video, detailing six core stages—from knowledge extraction and script generation to image creation, voice synthesis, and final video stitching—while highlighting practical model choices, prompt design, and stability tricks.
