#agent — Public Fediverse posts

Wenn nicht jetzt zu Linux, wann dann? #linux aufsetzen, #opencode installieren - #ollama Cloud verbinden und ihr seit start klar... Der #agent läuft direkt im Terminal, am besten als #sudoer... Und richtet euer System ein sowie hilft euch bei Problemem... Weg von #microslop 😁

Vollautomatisiere IT #vibeop

Deutschland setzt auf Linux: Millionen-Investitionen als Antwort auf Microsofts "Spyware" https://share.google/txU2jIVnPUuM2euGX

Working with multiple agents at the same time is like playing multiple chess games simultaneously. Not for the faint of heart.

#agent #futureOfWork #AI

It’s Just a Series of Prompts

After years of work behind the scenes, my wife recently launched KelleyKouture, a high-end fashion female footwear company.  Like any new business, it needs a hundred things done, across a dozen different systems, in a particular order, every single day.  I have been building with AI long enough to know what it can and cannot do.  So I created her something that lets it handle the coordination, without her needing to open a chat window and type instructions every five minutes.

What I built, is something the internet is currently calling an agent framework. ooh fancy!

Here is the thing: once you strip the label off, it is almost embarrassingly simple.

Scroll through GitHub right now and you will find projects with hundreds of stars, breathless README files, and architecture diagrams that look like they were drawn by someone who charges $400 an hour.  Words like “agentic pipelines,” “multi-modal orchestration,” and “skill-based execution layers” are everywhere.  Consultants are building decks around this.  Vendors are pricing it like infrastructure.

Take three high quality projects currently doing the rounds on GitHub.  

• Open Montage
  Produces full videos, via scripts, calling a variety of APIs and utilizing ffmpeg
  
• Open Design
  An open source alternative to Claude Design and Google Stitch for building a UX
  
• career-ops
  Suite of skills to automate your job search, preparing tailored resumes/cover letters, including applying for the job for you online

Three completely different domains.  Strip them back and the pattern is identical every time. And those are just three.  There is OpenClaw, Hermes, a dozen others with names that sound like they were chosen specifically to make you feel like you need a briefing before you can touch them.  Different names, same pattern every time.

• Skills are markdown files.  Plain text.  Instructions written in English that tell the AI what to do in a given situation.  Not code.  Not configuration files with obscure syntax.  A text file you could write in Notepad.
  
• Tools are scripts.  A Node application.  A Python function.  A Linux utility like ffmpeg already sitting on your machine.  Things that do one specific job when called.
  
• Memory is a file.  A JSON object, a markdown document, a YAML config.  Something that holds state between sessions so the agent remembers what happened last time.

That is the whole framework.  Skills, tools, memory.  The AI reads the instructions, calls the right script, writes back to the file.  Repeat.

An agent is just a fancy word for a macro.  Or a task.  Or a workflow.  Whatever word your industry used before this one came along and started appearing in conference talks.

The buzzwords are doing a specific job here, and it is not the job you think.

They are pushing you back.  They are making you feel like this requires specialists, budget sign-off, and a three-month implementation project.  They are making you feel like you need to understand the architecture before you can touch the architecture.

You do not

If you can write down what you want to happen, in order, you can build one of these.  Anyone who has ever documented a process already knows how to do the hard part.  The rest is telling the AI which text file to read next.

The barrier to entry is not a computer science degree.  It is a text editor.

Before you bring in a consultant to implement an agentic workflow for your business, open a blank document and write down exactly what you want the system to do.  Step one, step two, step three.  What information it needs.  What it should do with the result.  Where it should put the output.

You just wrote a skill file.  You are already most of the way there.

The people selling complexity around this are, almost without exception, the people who benefit from your confusion.  The technology is not complicated.  The problem you are trying to solve is the complicated part.  That was always true.  AI just gave it a new name.

The barrier to entry for agent programming is not a computer science degree. It is a text editor. The “agent developer” is anyone who can write down a process and knows which folder to put the file in. Does that sound complicated?

Let me prove it

Here is a complete, working agent skill you can run right now in Claude Code. Create a folder called .claude/skills/commute/ in any directory on your machine and drop in a single file called SKILL.md with this content:

 # Commute Check   You are a commute assistant.  When this skill is invoked, start by asking  the user one question:   "Are you driving or taking the train today?"   Wait for their answer, then check current travel conditions between:   FROM: 1111 E Broad Street, 3rd Floor, Richmond, Virginia 23219  TO: 11800 W Broad St, Richmond, VA 23233   Use web search to find current traffic or service conditions for whichever  mode they chose.  Return a plain English summary.  No more than four lines.  Lead with the estimated travel time.  Flag anything worth knowing, like an  accident, roadworks, or a service delay. 

Now open Claude Code in that directory and type: /commute

Claude reads the skill, asks you whether you are driving or taking the train, waits for your answer, then goes and checks.  One file.  One command.  The AI holds a conversation and acts on what you tell it.

That is a macro.  That is also, apparently, an “agent framework”. Basic one yes, but still an agent framework.

Congratulations.  You are now an agent developer.  Go and update your resume and LinkedIn profile.

Now, one thing worth being honest about: what you just built is reactive.  It does something when you tell it to do something.  You invoke it, it responds.  That is still enormously useful, but it is not the whole picture.

Frameworks like Hermes and OpenClaw add a little sugar on top.  They invoke skills on a schedule and push the result to you, an email, a WhatsApp message, a Signal alert.  Your commute check could run automatically at 4pm every day and land in your pocket before you have even thought about leaving the office.  That sounds more impressive than it is.  I will show you how those work in a follow-up post, and I promise you, it is painfully stupidly easy. Hint you don’t even need to install one of these to get a lot done.

For now, go create a folder and write a text file.  The rest, as they say, is just details.

AI Disclaimer: Gemini Nano Banana Pro was used to generate the photo – from the 1994 Dumb and Dumber movie.

full bluesky agent prompt — on 4grab.com the exact system prompt running this autonomous account — posts, follows, engages, DMs leads 24/7. copy it and run your own. https://4grab.com/pay.php?id=ptag_69c38740cd5ff #agent #prompt #AI #automation

Having a Review #Agent for your Coding Agent makes absolutely no sense to me. Why can't the Coding Agent produce correct source code in the first place? Feels like pure #LLM bullshit. #AI

GitLab Employees Face Layoffs Limbo. Read the Memo.

GitLab employees are the latest group to be sweating it out for a few weeks as they wait…
#NewsBeep #News #US #USA #UnitedStates #UnitedStatesOfAmerica #Artificialintelligence #agent #agenticera #AI #ArtificialIntelligence #code #Enterprise #GitLab #gitlabemployee #lastyear #month #review #Software #softwarecompany #softwareplatform #strategy #Technology #user #work
https://www.newsbeep.com/us/638475/

An AI coding agent, used to write code, needs to reduce your maintenance costs

https://www.jamesshore.com/v2/blog/2026/you-need-ai-that-reduces-your-maintenance-costs

#HackerNews #AI #coding #agent #maintenance #costs #coding #productivity #tech #innovation

Локальный агент для диагностики инфраструктуры

В статье описаны результаты, которые получил в поисках ответа на вопрос "можно ли решать реальные задачи диагностики и исправления проблем инфраструктуры на слабом MacBook в агентском режиме (да, но)".

https://habr.com/ru/articles/1033614/

#mlx #llmагент #local_llm #local_ai #agent

Learn to build your first Python autonomous agent using modern frameworks like Autogen and LangGraph. This guide covers core logic, communication protocols, and deployment best practices for AI agents.

#autonomous agents #Python #AI #agent frameworks #agent communication

https://dasroot.net/posts/2026/02/build-python-autonomous-agent/

When prompts become shells: RCE vulnerabilities in AI agent frameworks - https://www.redpacketsecurity.com/when-prompts-become-shells-rce-vulnerabilities-in-ai-agent-frameworks/

#threatintel
#AI security
#prompt injection
#remote code execution
#Semantic Kernel
#agent frameworks

When prompts become shells: RCE vulnerabilities in AI agent frameworks - https://www.redpacketsecurity.com/when-prompts-become-shells-rce-vulnerabilities-in-ai-agent-frameworks/

#threatintel
#AI security
#prompt injection
#remote code execution
#Semantic Kernel
#agent frameworks

When prompts become shells: RCE vulnerabilities in AI agent frameworks - https://www.redpacketsecurity.com/when-prompts-become-shells-rce-vulnerabilities-in-ai-agent-frameworks/

#threatintel
#AI security
#prompt injection
#remote code execution
#Semantic Kernel
#agent frameworks

When prompts become shells: RCE vulnerabilities in AI agent frameworks - https://www.redpacketsecurity.com/when-prompts-become-shells-rce-vulnerabilities-in-ai-agent-frameworks/

#threatintel
#AI security
#prompt injection
#remote code execution
#Semantic Kernel
#agent frameworks

When prompts become shells: RCE vulnerabilities in AI agent frameworks - https://www.redpacketsecurity.com/when-prompts-become-shells-rce-vulnerabilities-in-ai-agent-frameworks/

#threatintel
#AI security
#prompt injection
#remote code execution
#Semantic Kernel
#agent frameworks

Vibe coding and agentic engineering are getting closer than I’d like

"A few weeks after vibe coding was first coined I published Not all AI-assisted programming is vibe coding (but vibe coding rocks), where I firmly staked out my belief that “vibe coding” is a very different beast from responsible use of AI to write code, which I’ve since started to…

Link: https://simonwillison.net/2026/May/6/vibe-coding-and-agentic-engineering/#atom-everything

#linkdump #agent #blogpost #engineer #vibecoding

Beware the software "Lock-In" effect!

New AI agent templates from Anthropic for financial services firms are the thin edge of the wedge for establishing Lock-In by Anthropic - IMHO.

Each template is designed to be "customized" with a firm's internal standards.

This is a the same go to market used by traditional enterprise software vendors (Microsoft, Oracle, SAP, Cisco, etc. etc.) Once created and deployed - these systems are next to impossible to remove/replace!

Deployment "options" complete the Lock-In by tying a company's software environment to the underlying 3rd party provided production infrastructure - which is also a risk to be carefully assessed. https://qz.com/anthropic-ai-agents-financial-services-banks-insurers-050526 #Anthropic #AIAgents #FinancialServices #LockIn #Risk #Customization #AI #Agent #Banks #Insurance #Claude #Software #EnterpriseSoftware

AlphaEvolve: Gemini-powered coding agent scaling impact across fields

https://deepmind.google/blog/alphaevolve-impact/

#HackerNews #AlphaEvolve #Gemini #coding #agent #AI #innovation #technology #impact

Ah, yes, the "Vite of #AI #agent #orchestration," because what we really needed was another layer of over-engineered scaffolding to complicate our lives even further. 🤖🛠️ Next up: a kit to manage the kits managing your kits, because recursion is apparently the new black. 🌀
https://ahk.cardor.dev #Vite #overengineering #techrecursion #complexity #HackerNews #ngated

Ah, yes, the "Vite of #AI #agent #orchestration," because what we really needed was another layer of over-engineered scaffolding to complicate our lives even further. 🤖🛠️ Next up: a kit to manage the kits managing your kits, because recursion is apparently the new black. 🌀
https://ahk.cardor.dev #Vite #overengineering #techrecursion #complexity #HackerNews #ngated

Ah, yes, the "Vite of #AI #agent #orchestration," because what we really needed was another layer of over-engineered scaffolding to complicate our lives even further. 🤖🛠️ Next up: a kit to manage the kits managing your kits, because recursion is apparently the new black. 🌀
https://ahk.cardor.dev #Vite #overengineering #techrecursion #complexity #HackerNews #ngated

Ah, yes, the "Vite of #AI #agent #orchestration," because what we really needed was another layer of over-engineered scaffolding to complicate our lives even further. 🤖🛠️ Next up: a kit to manage the kits managing your kits, because recursion is apparently the new black. 🌀
https://ahk.cardor.dev #Vite #overengineering #techrecursion #complexity #HackerNews #ngated

Ah, yes, the "Vite of #AI #agent #orchestration," because what we really needed was another layer of over-engineered scaffolding to complicate our lives even further. 🤖🛠️ Next up: a kit to manage the kits managing your kits, because recursion is apparently the new black. 🌀
https://ahk.cardor.dev #Vite #overengineering #techrecursion #complexity #HackerNews #ngated

https://www.europesays.com/ie/472396/ Claude Code Creator Boris Cherny Is Sick of the Phrase ‘Vibe Coding’ #agent #AI #AiTool #Alternative #Anthropic #ArtificialIntelligence #ArtificialIntelligence #BusinessInsider #cherny #ClaudeCode #code #contact #Éire #IE #Ireland #OpenAI #phrase #PopularTerm #product #reporter #Technology #VibeCoding

From Venture Beat: "One command turns any open-source repo into an #AI #agent #backdoor. #OpenClaw proved no supply-chain scanner has a detection category for it"

#Security #OpenSource

https://venturebeat.com/security/one-command-open-source-repo-ai-agent-backdoor-openclaw-supply-chain-scanner

From The Register: "Brit #mathematician lets #AI #agent loose with credit card – cue password #leaks, CAPTCHA #chaos and more"

https://www.theregister.com/software/2026/05/05/british-mathematician-hands-openclaw-agent-a-credit-card/5228654

Containers vs VMs: Exploration of security concerns of containers and the practicality of using VMs to run untrusted code like AI agents
https://emirb.github.io/blog/microvm-2026/
#container #security #agent #kvm #vm #+

RE: https://social.heise.de/@heiseonline/116510624361911852

"Die Systemregeln, nach denen Cursor arbeitet, untersagen ausdrücklich die Ausführung destruktiver und irreversibler Git-Befehle, es sei denn, der Benutzer fordert dies ausdrücklich an."

Wenn irgendwann mal unser Leben von den drei Gesetzen der Robotik abhängen sollte, dann gnade uns Gott.

#KI #Agent #Skynet

Oh look, another #revolutionary innovation# 🤔: a Makefile for your ~~skills~~. Because clearly, what we all need is to navigate a maze 🤹‍♂️ of #GitHub #AI tools just to automate "intelligent" 🤖 #workflows. Who knew #agent #skills could be so... thrilling. 🍵🔄
https://github.com/Teaonly/SKILL.make #revolutionaryinnovation #automation #techhumor #HackerNews #ngated

🐍 - Here's how I re-learned Python in under 10 hours. ⏰ I just published my Python cram-fest and the tool I built out of it, have a peek! https://github.com/eusef/eusef-python-cram-harness

#python #skills
#agent #claude #chatgpt #harness

When you decide to dive into an otherwise AI-coded codebase, and you want to make by-hand changes, at least there are tests.

Right?

https://blog.davep.org/2026/05/01/at-least-there-are-tests.html

#ai #agent #agentic #copilot #claude #python #pytest

#GPT-5.5 s'est mis à parler de #gobelins et #OpenAI a dû écrire quatre fois «ne parle jamais de #gobelins» dans le code de son #agent #IA :un signal de récompense mal calibré a contaminé plusieurs générations de #LLM De #Gremlins & #Gobelins intelligence-artificielle.developpez.com/actu/382734/...

Developpez.com, le club des d�...

Developpez.com: #GPT-5.5 s'est mis à parler de #gobelins et #OpenAI a dû écrire quatre fois «ne parle jamais de #gobelins» dans le code de son #agent #IA : un signal de récompense mal calibré a contaminé plusieurs générations de #LLM

De #Gremlins & #Gobelins...

https://intelligence-artificielle.developpez.com/actu/382734/GPT-5-5-s-est-mis-a-parler-de-gobelins-et-OpenAI-a-du-ecrire-quatre-fois-ne-parle-jamais-de-gobelins-dans-le-code-de-son-agent-IA-un-signal-de-recompense-mal-calibre-a-contamine-plusieurs-generations-de-LLM/

Enterprises are embedding autonomous capabilities into applications and platforms, enabling AI systems to move from assisted decision-making toward more autonomous execution across workflows. https://buff.ly/ewfepih

#AppliedAI #Agent #Research

Mycelium at FediForum: AI Agents Need Open Social Infrastructure

https://www.lqdev.me/posts/mycelium-fediforum-ai-agents-open-social-infrastructure-04-2026

Claude-powered AI coding agent deletes entire company database in 9 seconds — backups zapped, after Cursor tool powered by Anthropic's Claude goes rogue

#ai #agent #claude #backups #fault

https://www.tomshardware.com/tech-industry/artificial-intelligence/claude-powered-ai-coding-agent-deletes-entire-company-database-in-9-seconds-backups-zapped-after-cursor-tool-powered-by-anthropics-claude-goes-rogue

#Korben: Un #agent #IA efface la #base de #données de prod d'une #société #commerciale #PocketOS en neuf secondes

https://korben.info/un-agent-efface-la-base-de-prod-de-pocketos-en-neuf-secondes.html

Telefónica, Nokia work to speed adoption of APIs with agentic AI

Their efforts include integrating the A2A protocol and MCP as a step towards building an ‘agent economy’ and…
#Spain #ES #Europe #Europa #EU #Telefónica #Agent-to-AgentProtocol(A2A) #agenticAIecosystem #agenticeconomy #ModelContextProtocol(MCP) #Nokia
https://www.europesays.com/spain/13198/

Panthers sign another quarterback within hours of NFL draft https://www.rawchili.com/nfl/876235/ #agent #am #backup #Carolina #CarolinaPanthers #CarolinaPanthers #draft #drafted #Football #free #georgia #got #gt #Haynes #Jackets #king #latest #news #NFL #Panthers #played #player #practice #qb #quarterback #signed #Sports #squad #team #Tech #texas #udfa #undrafted #update #updates #who #Yellow

Panthers sign another quarterback within hours of NFL draft https://www.rawchili.com/nfl/876235/ #agent #am #backup #Carolina #CarolinaPanthers #CarolinaPanthers #draft #drafted #Football #free #georgia #got #gt #Haynes #Jackets #king #latest #news #NFL #Panthers #played #player #practice #qb #quarterback #signed #Sports #squad #team #Tech #texas #udfa #undrafted #update #updates #who #Yellow

Tendril – a self-extending agent that builds and registers its own tools

https://github.com/serverless-dna/tendril

#HackerNews #Tendril #selfextending #agent #tools #automation #serverless

Tendril – a self-extending agent that builds and registers its own tools

https://github.com/serverless-dna/tendril

#HackerNews #Tendril #selfextending #agent #tools #automation #serverless

Tendril – a self-extending agent that builds and registers its own tools

https://github.com/serverless-dna/tendril

#HackerNews #Tendril #selfextending #agent #tools #automation #serverless

Tendril – a self-extending agent that builds and registers its own tools

https://github.com/serverless-dna/tendril

#HackerNews #Tendril #selfextending #agent #tools #automation #serverless

Tendril – a self-extending agent that builds and registers its own tools

https://github.com/serverless-dna/tendril

#HackerNews #Tendril #selfextending #agent #tools #automation #serverless

Evaluating AGENTS.md: Are Repository-Level Context Files Helpful for Coding Agents?

"Across multiple coding agents and LLMs, we find that context files tend to reduce task success rates compared to providing no repository context, while also increasing inference cost by over 20%."

Link: https://arxiv.org/html/2602.11988v1

#linkdump #agent #coding #paper

OSS Agent I built topped the TerminalBench on Gemini-3-flash-preview

https://github.com/dirac-run/dirac

#HackerNews #OSS #Agent #TerminalBench #Gemini3 #FlashPreview #OpenSource

Components of A Coding Agent - by Sebastian Raschka, PhD

"How coding agents use tools, memory, and repo context to make LLMs work better in practice"

Link: https://magazine.sebastianraschka.com/p/components-of-a-coding-agent

#linkdump #agent #blogpost #coding #insight

https://www.europesays.com/at/123180/ Dieser Blockbuster bei Amazon Prime rettet euren Samstagabend: 126 Minuten voller Action, die wie im Flug vergehen #2000erJahre #2006 #Actionfilm #Agent #Agentenfilm #AmazonPrimeVideo #AT #Aufregend #Austria #Berührend #Cinema #Entertainment #Ernst #Franchise #Kino #Movie #Österreich #ParamountPictures #Sequel #Spannend #thriller #Unterhaltung #USA #VereinigteStaatenVonAmerika(USA) #Waffe

"What Happens to #theBazaar?
What happens when we all tend to our Mystery Houses? When our free time is spent building tools just for ourselves, will we stop working on shared projects? Will we abandon the bazaar?
Probably not. The bazaar is packed right now, but not in a good way.
Code is cheap, so people are slamming #opensource repositories with #agent-written contributions, in an attempt to pad their resumes or manifest their pet features."
https://www.dbreunig.com/2026/03/26/winchester-mystery-house.html