Our talk just got selected as a keynote for the AI Engineer World's Fair 2026. So I want to share what @pauliusztin_ and I built: one memory for all 10,000+ of our notes. Everything I've learned and saved now lives in one structured memory my agents can actually use. It takes
TOOLS
-
Writer creates GOV.UK style guide derived writing skill for agents
By
–
I got tired of reading badly formatted agent written reports, so I put together a writing skill derived from the GOVUK style guide and content design principles: https://
gist.github.com/fofr/505e225f9
bf5e839d30c12ba6bfa0be2
… Content is a little out of date, but here you can see the effect of the skill: -
Irene Perrin uses ElevenLabs voice to teach at Windsor Castle
By
–
Motor Neurone Disease took Irene Perrin's speech. It didn't take her love of teaching.
— ElevenLabs (@ElevenLabs) 26 juin 2026
Today, she continues educating visitors at Windsor Castle using her ElevenLabs voice. pic.twitter.com/NyDecoWL5WMotor Neurone Disease took Irene Perrin's speech. It didn't take her love of teaching. Today, she continues educating visitors at Windsor Castle using her ElevenLabs voice.
-
LangSmith LLM Gateway enables flexible budget controls for teams
By
–
Before we shipped LangSmith LLM Gateway, we rolled it out internally. We don’t have to wait until the end of the month to understand spend We have been able to set budgets set by org, workspace, user, or API key Our teams can flexibly use coding agents without creating
-
Runway launches Agent 2.0 to turn prompts into full marketing campaigns
By
–
🆕Turn a prompt into a full campaign!
— Futurepedia – Learn to Leverage AI (@futurepedia_io) 26 juin 2026
Runway launches Agent 2.0: generate marketing briefs and campaign assets from a single prompt, then analyze performance to optimize and scale across platforms and markets. Built to be the most capable autonomous agent for real-world work.… pic.twitter.com/eWj0malr0PTurn a prompt into a full campaign! Runway launches Agent 2.0: generate marketing briefs and campaign assets from a single prompt, then analyze performance to optimize and scale across platforms and markets. Built to be the most capable autonomous agent for real-world work.
-
Confidence-Aware Tool Orchestration for Robust Video Understanding
By
–
Confidence-Aware Tool Orchestration for Robust Understanding
-
HyperExtract: LLM framework converting unstructured text to knowledge
By
–
/4 HyperExtract turns messy documents into actual knowledge systems. It is an LLM-powered framework for converting unstructured text into strongly typed Knowledge Abstracts. It can extract simple lists, Pydantic models, knowledge graphs, hypergraphs, and spatio-temporal graphs.
-
MinerU parses ugly documents into clean Markdown and JSON for LLM workflows
By
–
/5 MinerU parses ugly documents into clean Markdown and JSON for LLM workflows. It supports PDFs, DOCX, PPTX, XLSX, images, and web pages through a VLM + OCR dual engine. It can handle scanned docs, handwriting, formulas to LaTeX, tables to HTML, multi-column layouts, and
-
Agent needs better thinking: 22 ideation methods
By
–
/1 Your agent doesn’t need more prompts. It needs better ways to think. The creative-ideation skill gives Hermes a library of 22 ideation methods inspired by artists, thinkers, and creative frameworks. It reads the user’s situation, chooses the method that fits, then generates
-
Loop engineering automates coding agent workflows
By
–
/2 Prompting agents by hand is starting to look outdated. Loop engineering is a framework for turning coding agents into repeatable workflows. Instead of prompting Grok, Claude Code, Codex, or Cursor one step at a time, you define a recursive goal and let the agent iterate with