×
AI Agents

HiClaw Joins AgentScope, Partnering with CoPaw to Build Multi-Agent Infrastructure

This article introduces HiClaw joining AgentScope to partner with CoPaw in building enterprise multi-agent infrastructure.

Qwen3.6-Plus: Towards Real World Agents

Following the release of the Qwen3.5 series in February, we are thrilled to announce the official launch of Qwen3.6-Plus.

Alibaba Unveils Qwen3.6-Plus to Accelerate Agentic AI Deployment for Enterprises and Alibaba’s AI Applications

New model brings advanced agentic coding and refined reasoning to real-world deployment

Is Your OpenClaw Truly Under Control?

This article details how to build a comprehensive observability and security audit system for OpenClaw AI Agents using Alibaba Cloud Simple Log Service (SLS).

Alibaba Cloud ClawHub Skill Scan: Security Metrics Across 30,000 AI Agent Skills

Analysis of 30k Alibaba Cloud ClawHub Skills reveals critical security metrics. It highlights high-risk threats, emphasizing the urgent need for specialized detection to protect agent ecosystems.

4 Real Cases | Harness Engineering is Becoming the New Moat

This article introduces Harness Engineering, a paradigm shift from coding to designing control systems that enable reliable AI agent execution.

Alibaba Bets Big on Agentic AI: A Multi-Trillion Dollar Market Opportunity

This article introduces Alibaba’s strategic bet on agentic AI—positioning AI agents as “virtual knowledge workers” to capture a multi-trillion-dollar market opportunity.

40+ Commits Daily: HiClaw v1.0.6 Lands; Credential-zero Security, Skills + MCP > 2

HiClaw just bridged the gap between AI experimentation and enterprise security. Stop leaking credentials. Start orchestrating.

Alibaba Cloud's New Launch: Agent ID Guard, Who Will Manage the Identity Security of These "Claws"?

This blog post introduces Alibaba Cloud's new Agent ID Guard, a security solution designed to protect the identity of autonomous AI agents, popularly known as "Little Lobsters" (OpenClaw).

Alibaba Open Sources "OpenClaw" Combo Is Here: HiClaw & CoPaw, Significantly Reduces Memory Footprint

Alibaba open-sourced HiClaw and CoPaw, a lightweight AI agent combo that drastically cuts memory usage and enables local automation.

Alibaba Cloud's Major New Release: Agent Security Center, an Integrated Defense Platform for AI Agents under a New Security Framework

This blog post introduces Alibaba Cloud's new Agent Security Center, a unified defense platform designed to secure AI agents like OpenClaw under a robust new security framework.

Deep Dive: How Kimi's AI Agent Runs on Alibaba Cloud

This article explains how Kimi leverages Alibaba Cloud's ACK and ACS to build a secure, instantly elastic infrastructure capable of supporting hundreds of thousands of concurrent AI Agent sandboxes.

SysOM MCP: Open-Source Intelligent O&M Assistant for AI-Powered System Diagnostics

This article introduces SysOM MCP, an open-source O&M assistant that enables AI Agents to perform automated system diagnostics via natural language using MCP.

OpenClaw Launches on Alibaba Cloud Simple Application Server

Alibaba Cloud is proud to announce that OpenClaw is officially supported on its Simple Application Server.

The More the Agent Is Used, the Smarter It Becomes? The AgentScope Java Online Training Plugin is Here!

This article introduces AgentScope Java's online training plugin for self-evolving AI agents using real production data and Trinity-RFT reinforcement learning.

Why Does Alibaba Cloud Want to Open Source the Data Collection Development Kit

The article introduces Alibaba Cloud’s open-sourcing of LoongSuite, a high-performance, low-cost data collection kit for AI Agent observability.

Is Your AI Agent Getting Dumber? Alibaba Cloud AnalyticDB Unveils AI Context Engineering

This article introduces AI Context Engineering, a framework on Alibaba Cloud's AnalyticDB that prevents AI agents from "getting dumber" by intelligently managing their context and memory.

From ReAct to Ralph Loop A Continuous Iteration Paradigm for AI Agents

The article introduces the Ralph Loop—a continuous, self-iterating paradigm that keeps AI programming agents working until tasks are verifiably complete.

Container Technology Evolution for LLMs and AI Agents

The article outlines how container technology is advancing to support LLMs and AI agents across data processing, training, inference, and deployment.

Hello AgentScope Java

This article presents AgentScope Java, a ReAct-powered framework for scalable, transparent AI agent development.