Alibaba's official tech channel, featuring all of its technology innovations.
This article details the design, operation, and continuous improvement of a six‑agent autonomous system, covering memory management, protocol design, self‑healing mechanisms, and practical engineering lessons for building reliable, self‑evolving AI workflows.
This article analyses the nature of memory for LLM‑based agents, arguing that memory is a closed‑loop system composed of a raw ledger, derived views, and a policy layer, and explores how non‑parametric designs, system‑2 architectures, temporal structuring, and skill‑based execution can bridge the gap between parametric and non‑parametric memory while highlighting key bottlenecks and practical design guidelines.
The article explains why large‑language‑model agents often lose context and violate architectural rules when generating code, and proposes a Harness framework that treats the repository as an operating system, adds layered linting, pre‑validation, automated verification, and cross‑model review to keep agents on track.
The article explains how OpenClaw’s “use‑more‑you‑use‑more” effect stems from a self‑evolving markdown file system that records agent identity, user profile, skills, memory, and lessons, enabling continuous learning, precise retrieval, and personalized AI behavior without changing the underlying model.
This article analyzes why over 40% of Agentic AI projects fail due to inadequate observability, outlines three common pain points—trace blindness, uncontrolled token costs, and untraceable failures—and demonstrates a practical ADB MySQL solution that reconstructs logs, classifies failures with AI functions, quantifies token waste, and generates prompt‑optimization suggestions, all with a few SQL statements.
This article explains how a DuckDB‑backed observability plugin transforms opaque OpenClaw AI agent responses into structured, searchable traces, enabling developers to see every hidden step, diagnose issues within seconds, and iteratively improve the system based on concrete metrics.
This article analyzes the emerging paradigm of Harness Engineering, explaining how prompt, context, and feedback-loop innovations enable AI agents to act as controllable, scalable digital workers, and illustrates the concept with four real‑world case studies and open‑source projects that push the limits of AI‑driven software development.
This article examines how Taobao Flash Sale’s AI Agent uses Alibaba Cloud’s Tair as a high‑performance short‑term memory layer, detailing data model design, latency impact, concurrency control, elastic scaling, bandwidth handling, and TTL‑based cleanup to achieve sub‑second response times during massive traffic spikes.
This article details a three‑day deep dive into OpenClaw, demonstrating how a self‑iterating AI assistant for bank relationship managers can be built, validated, and refined through autonomous agent communication, scheduled tasks, and memory‑driven reflection.
This guide explains why OpenClaw agents lose context, how the Mem0‑Tablestore combination provides automatic, cloud‑hosted, and fully controllable memory, and walks you through step‑by‑step installation, configuration, and verification on Alibaba Cloud.
