A new open specification landed: Agent Plugins 1.0, with an initial technical steering committee made of Amazon, Cursor, Microsoft, OpenAI and Vercel. It defines a portable package format for extending agents, so an extension is authored once instead of being repackaged per client.
Remotely Save, synchronizes an Obsidian vault with cloud storage you already have: Dropbox, OneDrive, Google Drive, any WebDAV server, or S3-compatible object storage (AWS S3, Cloudflare R2, MinIO, Backblaze B2, and similar). It is a lightweight alternative to Obsidian Sync for people who prefer to
OpenRouter extended its "one API for every model" promise to speech-to-text. A new endpoint (`POST /api/v1/audio/transcriptions`) accepts base64-encoded audio and returns the transcript as JSON, using the same API key as chat completions. No separate STT provider, no extra server.
While every model announcement brags about bigger context windows, OpenAI went the other way: the Codex model's context size dropped from 372k to 272k tokens. No announcement; the change surfaced as a pull request in the open-source Codex CLI repo, and promptly hit the Hacker News front page because
The Notebook Navigator plugin for Obsidian just hit a milestone: it's now the #1 most popular plugin in the Obsidian community directory, and should pass a million downloads within weeks. Not bad for a file explorer replacement.
Tools
Obsidian automation is three layers stacked on one idea: your notes are plain files, so anything can operate on them. Here is the complete map, from your first template to an AI Operating System.
Tools
Dataview turns your vault into a database you can query. But a result that only exists at render time is not knowledge you own. Here is everything Dataview can do, everything it cannot, and what I changed after 15,116 queries.
Tools
A color-coded status line for Claude Code showing context, git, session cost, and the rate limits Anthropic doesn't surface — including per-model weekly caps.
Luca Rossi makes a point about AI coding that matches my thinking: most AI coding workflows optimize the INNER loop, the rapid cycle of describing a feature and generating code. But that's a fraction of software delivery. The OUTER loop (deciding what to build, shaping the solution, releasing, learn
Give deterministic code everything it can handle (routing, scheduling, data transformation, file writes), and reserve the Large Language Models (LLMs)) for the parts that need judgment (interpreting ambiguous, unstructured input).
According to Rahul Garg (Thoughtworks, on martinfowler.com), the real value of a subagent is what it keeps OUT of the orchestrator's context, not how fast it runs. Context isolation is more valuable than parallelism.
Google's framework for building AI agents, available in Python (since March 2026) and Go. Version 2.0 is a response to a production reality: agents that orchestrate everything through the LLM prototype well and then fall apart in production, with infinite loops, hallucinated routing, and runaway cos
A clear roadmap to building your own knowledge system. Subscribe and get it straight to your inbox.
6,000+ readers. No spam. Unsubscribe anytime.
