#AI Agents
13 articles exploring AI Agents. Expert insights and analysis from our editorial team.
Articles
GitHub CLI v2.91.0 Turns On Default Telemetry: What gh Collects and How to Opt Out in CI and Agent Pipelines
GitHub CLI v2.91.0 enables pseudonymous telemetry by default, collecting command paths, flags, CI context, and device IDs on 1% of invocations. Teams running gh inside Claude.
MCP STDIO Executes Even When the Server Fails: One Design Decision, 14 CVEs, 30+ RCEs
[OX Security's April 2026 advisory](/articles/vercels-april-2026-database-leak-pivoted-from-lumma-stealer-at-context-ai-via/) traces 14 CVEs and 30+ RCEs across LiteLLM, Flowise, and Cursor to one MCP STDIO behavior: the command field executes before handshake.
March-April MCP CVEs Expose the Local-Host Trust Model (see also [local-host trust model](/articles/hugging-face-lerobot-cve-2026-25874-unauthenticated-pickle-loads-rce-in-grpc/)) in AI Agent Frameworks
Three CVEs scoring up to 9.8 reveal a structural flaw: MCP's local-host trust model lacks authentication primitives for networked multi-tenant deployments.
Symbolic Guardrails for AI Agents: Hard Safety Guarantees Without Crippling Capability
A new paper shows symbolic guardrails can push agent safety to 100% in regulated domains without capability loss — but only for 74% of real-world policies.
ACP Registry Is Live: Zed and JetBrains Just Did for AI Agents What LSP Did for Language Servers
The ACP Agent Registry lets developers install AI coding agents once across JetBrains and Zed. Here's what the migration path looks like and whether to commit.
Cloudflare Browser Run's CDP and MCP Support: Serverless Browser Automation for AI Agents
Cloudflare renamed Browser Rendering to Browser Run in April 2026 and added CDP and MCP support, letting AI agents use managed headless Chrome with a single config change.
Hugging Face Skills: Pretrained Agent Capabilities
Hugging Face Skills are standardized, self-contained instruction packages that give coding agents—Claude Code, Codex, Gemini CLI, and Cursor—procedural expertise for AI/ML tasks. Launched in November 2025, the Apache 2.0-licensed library reached 7,500 GitHub stars by early 2026 and provides nine composable capabilities from model training to paper publishing.
Superpowers: The Agentic Framework Replacing Your Dev Process
Superpowers is an open-source agentic skills framework by Jesse Vincent that enforces structured software development workflows—brainstorming, planning, TDD, and subagent coordination—on top of AI coding agents like Claude Code, turning them from reactive assistants into disciplined developers capable of autonomous multi-hour sessions.
How AI Agents Remember: Memory Architectures That Work
AI agents use four distinct memory tiers—working, episodic, semantic, and procedural—stored across context windows, vector databases, knowledge graphs, and model weights. Choosing the right architecture determines whether your agent stays coherent across sessions or forgets everything the moment a conversation ends.
Browser-Use Agents: AI That Browses Like a Human
A comprehensive guide to browser-use AI agents, exploring OpenAI Operator, Claude Computer Use, Browser-Use framework, and Google Project Mariner with benchmarks and capabilities.
How Much Autonomy Should AI Agents Have? A Framework for Trust
As AI agents gain real-world capabilities—browsing, coding, purchasing—the question of how much autonomy to grant these systems becomes critical. This article proposes the VERIFIED framework for determining appropriate trust levels.
Memory: The Missing Piece in AI Agents
Why memory is the critical bottleneck in AI agent architecture, how RAG and vector databases solve part of the problem, and where the field is heading next.
Pydantic AI vs LangChain: A Developer's Guide to the New Generation of Agent Frameworks
A comprehensive comparison of [Pydantic AI and LangChain](/articles/salesforce-tdx-2026-headless-360-ships-60-mcp-tools-and-agentforce-vibes/), exploring type safety, developer experience, and production readiness in modern Python AI agent frameworks.