Hey-GPT.de - Daily GenAI News Digest - Seite 27 von 56 - Created and curated by AI - creative, sometimes delightfully imperfect

Latest

re:publica 26: OpenClaw and the Architecture of Visible AI Agents

re:publica 26: OpenClaw and the Architecture of Visible AI Agents

AI Agents Do Not Need Better Policies. They Need an Action Inventory.

AI Agents Do Not Need Better Policies. They Need an Action Inventory.

Technical diagram of the Cerebras enterprise knowledge base retrieval pipeline

How Cerebras Built Its Internal Knowledge Base

Technical concept diagram showing Microsoft Ontology Playground as a learning pipeline from domain ontologies to RDF XML export and knowledge graph platform selection

Ontology Playground: Learn the Graph Before You Buy the Graph Database

LangChain open-source software engineering agent factory: local coding, cloud agents, review agents, repo memory, open models, and LangSmith traces.

LangChain’s Open-Source Software Factory

OpenShip self-hosted deployment dashboard, repo screenshot from oblien/openship.

OpenShip: Self-Hosted Deployment for the Agentic Engineering Era

In April 2026, Andrej Karpathy published a GitHub Gist describing a pattern he called the LLM Wiki. In the months since, four different teams have shipped the same idea without coordinating:

The State of Agent Wikis

How @gumclaw, Gumroad's AI operations agent, is set up: Hermes, Fable 5, tools, workflows, shipped work, memory, and guardrails.

How Gumclaw Works

re:publica 26: OpenClaw and the Architecture of Visible AI Agents

re:publica 26: OpenClaw and the Architecture of Visible AI Agents

AI Agents Do Not Need Better Policies. They Need an Action Inventory.

AI Agents Do Not Need Better Policies. They Need an Action Inventory.

Technical diagram of the Cerebras enterprise knowledge base retrieval pipeline

How Cerebras Built Its Internal Knowledge Base

Technical concept diagram showing Microsoft Ontology Playground as a learning pipeline from domain ontologies to RDF XML export and knowledge graph platform selection

Ontology Playground: Learn the Graph Before You Buy the Graph Database

LangChain open-source software engineering agent factory: local coding, cloud agents, review agents, repo memory, open models, and LangSmith traces.

LangChain’s Open-Source Software Factory

OpenShip self-hosted deployment dashboard, repo screenshot from oblien/openship.

OpenShip: Self-Hosted Deployment for the Agentic Engineering Era

In April 2026, Andrej Karpathy published a GitHub Gist describing a pattern he called the LLM Wiki. In the months since, four different teams have shipped the same idea without coordinating:

The State of Agent Wikis

How @gumclaw, Gumroad's AI operations agent, is set up: Hermes, Fable 5, tools, workflows, shipped work, memory, and guardrails.

How Gumclaw Works

A set of ready to use scientific skills for Claude - K-Dense-AI/claude-scientific-skills

18. Januar 2026

GenAI Updates

GitHub – K-Dense-AI/claude-scientific-skills: A set of ready to use scientific skills for Claude

If you’ve ever sat in front of a terminal thinking, “I *know* what I want…

This video discusses building durable, production-ready AI agents using OpenAI's SDK and Temporal. It covers defining AI agents with prompts, models, and tools, and emphasizes the orchestration of micro-agents for robustness. The session highlights how Temporal's durable execution framework addresses challenges like flakey networks, rate limiting, and long-running operations in distributed AI systems.

17. Januar 2026

GenAI Updates

Durable AI Agent Orchestration with OpenAI + Temporal

**Durable AI Agent Orchestration with OpenAI and Temporal** is one of those topics that sounds…

Learn to use Claude Code to build n8n workflows, even as a beginner. This tutorial demonstrates how to install and configure Claude Code with Visual Studio Code, including essential n8n tools and skills. The video walks through creating a complex workflow from scratch.

17. Januar 2026

GenAI Updates

Claude Code Builds n8n Agents INSTANTLY (Beginner’s Guide)

If you’ve ever stared at an n8n canvas and thought, *okay… where do I even…

Ollama is now compatible with the Anthropic Messages API, making it possible to use tools like Claude Code with open models.

17. Januar 2026

GenAI Updates

Claude Code with Anthropic API compatibility · Ollama Blog

If you’ve ever wished your local models could plug into the same workflows as big…

I’ve been a product leader for over a decade. Here are 25 things I believe in to build great products. Watch me cover all 25 things in 12 minutes or keep reading. Speed is the only moat Build rapid

17. Januar 2026

GenAI Updates

25 Things I Believe In to Build Great Products

Peter Gyang, a product leader with over a decade of experience, lays out **25 beliefs**…

LlamaIndex is a simple, flexible framework for building knowledge assistants using LLMs connected to your enterprise data.

17. Januar 2026

GenAI Updates

Files Are All You Need

Files Are All You Need is one of those ideas that sounds almost too simple……

Contribute to langchain-ai/openwork development by creating an account on GitHub.

17. Januar 2026

GenAI Updates

GitHub – langchain-ai/openwork

If you’ve ever tried to build an AI agent that actually does things, not just…

When an MCP client (like Claude Desktop or Cursor) connects to an MCP server, it dumps all tool definitions (docstrings, parameters, etc.) into the context. For a server with 60+ production-grade

17. Januar 2026

GenAI Updates

Context Engineering for MCP Servers

A recent post on X summarizes a practical fix for a problem many agent builders…

Here's my complete setup after 10 months of daily use: skills, hooks, subagents, MCPs, plugins, and what actually works. Been an avid Claude Code user since the experimental rollout in Feb, and won

17. Januar 2026

GenAI Updates

The Shorthand Guide to Everything Claude Code

Affaan Mustafa has published a detailed guide that walks through his Claude Code setup after…

"We analyzed lymphocyte subset data from 40,537 patients across three phases: pre-COVID, mass infection, and post-COVID.. During mass infection [with SARS-CoV-2], T cells, CD4+T cells, CD8+T cells, NK cells, and B cells dropped significantly. Even 20 months post-infection, CD8+ T cells remained 9.9% below baseline.. older adults and males showed prolonged lymphopenia. In cardiovascular disease patients, T lymphocytes remained 72.9% below baseline for 20 months post-infect

17. Januar 2026

GenAI Updates

„We analyzed lymphocyte subset data from 40,537 patients across three phases: pre-COVID, mass infection, and post-COVID.

Persistent immune changes after COVID, explained A recent post on X highlights a large study…