Claude in Chrome starts syncing conversation sessions across devices
Skills and connectors used in the browser now carry over to desktop and mobile, rolling out first for Max and Team plans
20
Tag
harness
DeepSeek Forms Harness Team, Takes Aim at Claude Code
Company opens official WeChat account and starts hiring for AI agent development
10
Claude Opus 5 leads spreadsheet-analysis AI test with 54%
Artificial Analysis unveils new agent benchmark AA-AnalystAgent. 57% of failures traced to early hypothesis lock-in.
00
Shepherd, open-source runtime for rewinding agent execution unveiled
Northeastern and Stanford researchers unveil a Python runtime that branches, replays, and recovers agent execution like Git
00
n8n Officially Supports AWS Bedrock AgentCore Harness
Open-source community node enables no-code production agents with memory and tools
10
AWS Brings Open-Source Agent Skills to Bedrock Automated Reasoning Policies
Six published skills let coding agents handle the full lifecycle from policy authoring to deployment
00
Together AI Publishes DeepSeek·GPT-5.6 Luna Cascade Test Results
DeepSeek-first cascade solves more tasks than Luna alone on DeepSWE benchmark
00
AWS Bedrock AgentCore adds controls for agent action sequences
Temporal policies built on new open-source policy language Dogwood, plus gateway rate limiting, aim to block cumulative risk
00
OpenAI Unveils Agent Plugin Standard with AWS, Cursor, GitHub and Others
Combines Agent Skills packaging and MCP server configuration into a single reusable format across agent clients
00
Prime Intellect unveils self-improving agent harness 'Prime Agent'
An RLM harness for coding and long-running autonomous tasks, built around a structure that modifies its own harness state
10
That's the last story.