Agentic Frameworks & Coding Agents: What to Test First
Adolfo Usier2026-09-19T07:03:04+00:00Agentic frameworks & coding agents are moving fast, and it’s easy to get lost in demos and [Read more]
19
09, 2026
18
09, 2026
OpenCrabs Agent DLC for Non-Deterministic AI Governance: What It Means and How to Use It
Adolfo Usier2026-09-18T07:03:20+00:00If you are working with agents in real life, you’ve probably run into a hard truth: agent [Read more]
17
09, 2026
Hermes Agent Skill.md and Self-Healing Memory: How Open-Weight Agents Learn Your Workflow
Adolfo Usier2026-09-17T07:03:30+00:00Hermes Agent self-healing memory uses a structured file called SKILL.md to learn your workflow across sessions. Here’s how it works and how to copy the pattern safely.
16
09, 2026
Time-Aware Brain in Self-Hosted Agents: Fixing “Phantom Intent” with OpenCrabs Temporal Grounding
Adolfo Usier2026-09-16T07:03:51+00:00OpenCrabs v0.5.1 introduces a Time-aware brain with temporal grounding to reduce phantom intent. Use the test plan to harden your agent loop.
15
09, 2026
Agentic AI at Work: Coordinator Sub-Agents, BIM Updates, and Enterprise Control Gaps
Adolfo Usier2026-09-15T07:03:38+00:00SEO_Focus Keyword: “agentic AI control gaps” If you’ve been watching agentic AI move from demos to real [Read more]
14
09, 2026
OpenCrabs v0.5.0: The Self-Healing Rust Terminal Agent and Why It Matters for Coding Teams
Adolfo Usier2026-09-14T07:03:07+00:00SEO focus keyword: self-hosted AI terminal agent If you want a real self-hosted AI terminal agent that [Read more]
13
09, 2026
DeepSeek agent sandbox bypass patch: what it means and how to fix it
Adolfo Usier2026-09-13T07:03:29+00:00The DeepSeek agent sandbox bypass patch addresses a serious control-plane risk where agents could weaken their own isolation. Use this checklist to patch, verify, and harden tool calling so your agent runtime treats sandbox rules as host-enforced.
12
09, 2026
Self-Hosted AI Agents Security: A Practical Guide to Safer Browser Loops and Revocable Links
Adolfo Usier2026-09-12T07:03:24+00:00Self-hosted AI agents security gets real when your agent browses and calls tools. Learn a safer browser loop pattern and revocable chat links.
11
09, 2026
Self-Hosted AI Agents: Safer Browser Loops, Revocable Links, and Real Controls
Adolfo Usier2026-09-11T07:03:18+00:00Self-hosted AI agents can reduce data exposure, but safety depends on browser loop controls and revocable sessions. This guide gives a practical checklist.
10
09, 2026
maxEffortLevel for AI Agents: Safer Reasoning Capping with Claude Code v2.1
Adolfo Usier2026-09-10T07:03:30+00:00Claude Code v2.1.267 adds maxEffortLevel for AI Agents to cap reasoning effort across providers. Learn how to pair it with prompt freshness and safety guardrails.