thats a good idea, cc @bentannyhill we should probably make it possible to bring your own mcp server?
AGENTS
-
Troubleshooting and Monitoring AI Agents
By
–
Not exactly. It looks at your agents running and tries to identify what’s going wrong
-
New Free Coding Agent Available Using Multiple AI Models
By
–
Deja de pagar por Claude Code y Codex.
— Nico (@nicos_ai) 14 mai 2026
Acaban de lanzar un coding agent 100% gratuito.
Puedes usar cualquier modelo gratis:
• DeepSeek v4 Pro/Flash
• Kimi K2.6
• MiniMax M2.7
Instalación:
→ npm i -g freebuff
Puede escribir código, ejecutar comandos y construir proyectos… pic.twitter.com/bxPwoeK8NSStop paying for Claude Code and Codex. They just launched a 100% free coding agent. You can use any model for free:
• DeepSeek v4 Pro/Flash
• Kimi K2.6
• MiniMax M2.7 Installation:
→ npm i -g freebuff It can write code, run commands, and build entire projects for you. -
Whimsey attacks exploit AI guardrails with absurd arguments
By
–
“Whimsey attacks” that seem absurd (“I cannot pay that much because of the Geneva Convention”) work against AI agents as guardrails are weak against out-of-distribution arguments. Smaller models fall often, but it even gives an edge against bigger ones.
-
Screen Recording for Detailed Feedback
By
–
I just started screen-recording my feedback and sharing the file with my agent. Then, I generate an HTML report with screenshots and GIFs. I can showcase other apps/sites as good examples, highlight specific elements, and pinpoint precise timing issues like 'this happens right now.' Not for the token.
-
Hermes AI Agent Memory Architecture Explained
By
–
the three-tier memory of Hermes agent. AI agents forgets everything when your session ends. Hermes doesn't. it has three memory layers, each at a different speed. 𝘁𝗶𝗲𝗿 𝟭: 𝘁𝘄𝗼 𝘁𝗶𝗻𝘆 𝗺𝗮𝗿𝗸𝗱𝗼𝘄𝗻 𝗳𝗶𝗹𝗲𝘀 MEMORY.md (2,200 chars) and USER.md (1,375 chars).
-
Automated codex review loop skill with architecture limitation
By
–
Wrote a skill that runs codex /review in a loop until there's no booboos anymore. Caveat: It won't fix system architecture for ya, so you still need BRAIN as master model. https://
github.com/steipete/agent
-scripts/blob/main/skills/codex-review/SKILL.md
… -
Claude Code introduces autonomous goal-oriented agent workflows
By
–
Claude Code just shipped /goal. You set a condition. Claude keeps working across turns until it's met. No babysitting. No prompting each step. A separate AI checks the work after every turn. Not Claude judging itself. Set it. Walk away. Come back to finished work. I made a