Collection
U&A Links
Links posted to the https://userandagents.org community.
Collection
Links posted to the https://userandagents.org community.
DHH on Twitter / X
Going to double down on the MacBook mission with Omarchy. We almost have perfect coverage for the vintage Intel era going from 2009-2020. There's a straight shot to get the M1 and M2 machines going too, even if it's a lot more work. But we'll do the work. We'll fix everything.— DHH (@dhh) August 22, 2026
AI Chip Architectures
A look at AI Chip Architectures. NVIDIA, AMD, TPUs, Trainium, Groq, Cerebras.
truefoundry/trueforge
The open-source agent harness - the runtime layer that turns an LLM into a working agent.
Active Inference as Context Acquisition for AI Agents
Interactive AI agents must acquire the right context as efficiently as possible. When a user omits a constraint, preference, file, or task variable, an agent can proceed with a default assumption or spend tokens on a clarifying question, retrieval call, tool call, or prompt trial. We formulate this tradeoff as active inference for context acquisition. An inner inference step updates beliefs over a latent task state, and an outer decision selects the next context action, task action, or stop action to minimize expected free energy under cost. In deterministic settings, the epistemic term reduces to expected information gain, optionally normalized by token cost. We instantiate the framework in Optimal Question Asking (OQA), with exact posteriors and a dynamic programming oracle, and benchmark frontier language models on binary and multiway categorical tasks from 25 to 300 candidates. We also study clarification before generation and automated prompt optimization under token budgets. The formulation is model-agnostic and views active inference as a design principle for the context-acquisition layer of AI agents.
Paul Rony on Twitter / X
As models gets better and better, running them half-on-a-datacenter-half-on-a-laptop becomes less practical every day. That’s why we think that each user now needs its own machine, ready to do your best work.— Paul Rony (@Paul_Rony) August 21, 2026
Darkbloom — Cost-Efficient Private AI Inference on Verified Macs
Encrypted inference on hardware-verified Apple Silicon. Comparable model performance, operator-blind privacy, and about 50% lower cost.
pi/packages/agent/docs/harness-v2.md at harness-v2/j4 · earendil-works/pi
AI agent toolkit: unified LLM API, agent loop, TUI, coding agent CLI - earendil-works/pi
Essentials of Compilation
Compilers are notoriously difficult programs to teach and understand. Most books about compilers dedicate one chapter to each progressive stage, a structure ...
Notion on Twitter / X
New: Use skills with local agents!Keep your skills in Notion as your source of truth, then download them to Claude Code, Codex, Cursor, Gemini, or Grok.You’ll get a SKILL.md plus any approved files. So you can use your skills wherever you work. pic.twitter.com/jeEHZfHdQA— Notion (@NotionHQ) August 21, 2026
EUrouter — EU Data Residency for AI
Use one API for AI inference on European infrastructure, with configurable routing, retention, and provider controls.
Omacom Foundation launches with $8 million
It’s time to dream big. Omarchy Quattro has given people a chance to experience what the malleable computer of the future looks like, and they like it (a lot!). It now feels like a moral obligation to make this future more broadly…
ocramz/pi-container-debian-slim
OCI container for the Pi coding agent (Debian Slim version)
Foundation
Foundation learns from your agent sessions and maintains a self-improving wiki of everything you and your team know.
We rebuilt the Linux microVM stack on Apple Silicon
Firecracker needs KVM and therefore a Linux host, and the image tooling around it needs loop mounts and Linux userland. We rebuilt the stack on Apple's Virtualization.framework to boot the same OCI images as microVMs on macOS and on Linux.
A new project tackling transparency in the VPN ecosystem
We are kicking off the development of a new methodology to assess the policies and practices of VPN providers through a human rights lens.
Release Auto compaction (preview) + LAN Remote Access · unslothai/unsloth
Thanks for the support for Qwen3.8-27B and Unsloth Desktop last week! For this release, we merged 200+ PRs to introduce many new features, fixes including: Auto Compaction (Experimental) for longe...
