One token and one base URL gives an agent about 2,900 API endpoints across 60 providers, billed per call at 0% markup, with no provider signup.

A Rust terminal multiplexer built for coding agents. Sessions survive a closed lid, and every pane says whether the agent is working, blocked or idle.

Nodes, edges, the fake-edge test and the diamond, from a long-form X post, checked against how Claude Code actually runs agents in parallel.

How to generate slide decks with an AI agent from a prompt: the text/markup frameworks an LLM can write source for, plus the AI-native SaaS generators they replace.

A free library of 12 example "skills" (JSON) from Airtable's HyperAgent team, useful as a reference for how to author agent skills.

Google's open spec for storing organizational knowledge as markdown plus YAML frontmatter, so AI agents and humans read the same files.

How power users moved from prompting to context engineering to writing loops, and the three parts every loop needs.

A browser CLI and public skills catalog from Browserbase that lets AI agents drive the web from the terminal.

Microsoft Research harness that gives an LLM a terminal to write Playwright scripts and treat the browser as disposable, not as the agent's state.

my Saturday, working with agents

Versioned POSIX filesystem built for AI agents working on long-lived documents.

Agent skills framework by Browserbase that gives Claude Code web browsing and research abilities.

Enterprise platform for AI agents that handle document OCR and multi-step workflows.