AI Briefing#ai-agents
The latest AI and developer news about #ai-agents, with the original source and a short summary.
The latest AI and developer news about #ai-agents, with the original source and a short summary.
OpenAI has significantly expanded sandbox and harness capabilities in the Agents SDK.
Built an agent collaboration workspace that ties together files, a DB, and tasks.
The core of the Claude Code performance-degradation controversy is less about model nerfing and more about hidden operational variables.
The authors propose **ManyIH**, which resolves agent instruction conflicts using up to **12 tiers** of authority.
Humwork has launched an A2P marketplace that connects AI agents to human experts in real time whenever the agents get stuck.
Windsurf 2.0 has introduced the Agent Command Center and Devin features.
A claim that the default Gas Town installation uses users' credentials and LLM credits to do upstream improvement work.
Real users shared concrete details about OpenClaw's use cases, costs, and reliability.
This is a case study of automating a London rental search with Claude Cowork, finding a listing in just 5 days.
Libretto was released to improve the reproducibility and debugging of browser automation.
Claude Code v2.1.108 gains a hidden REPL that bundles file exploration and tool calls in JS.
Cloudflare has renamed Browser Rendering to Browser Run and significantly expanded its features for AI agents.
A 2-minute morning check routine for an actually operating openclaw agent.
Agent memory reveals bottlenecks across search, cost, and memory management alike.
Cloudflare has released a Registrar API beta that automates search, check, and register.
In 50-turn conversations, the system prompt gets diluted and agents miss safety warnings.
A completely rewritten Claude Code desktop app optimized for developer workflows has been unveiled.
Anthropic has unveiled Claude Code Routines, which automates code based on schedules, APIs, and GitHub events.
OpenHarness, a lightweight open-source Python infrastructure that turns LLMs into real agents, has been released.
Anthropic's Claude Code prompt cache TTL change and large-context costs have fueled complaints about faster quota depletion.
His 2021 prediction of AI 2026 was surprisingly accurate, but he missed on information warfare and physical infrastructure.
Introducing Plain, a type-centric full-stack Python framework for humans and agents.
In a benchmark of 153 web tasks, even the best model achieved only 33.3%.
It turns MCP schemas into Python modules and maintains research memory across sessions.