Theo Browne's free, MIT-licensed GUI for the coding agents already on your machine: threads, branches, diffs and PRs in 1 place, on desktop, web and phone.

Open-source Chromium browsers from a YC startup: BrowserOS neo, a second browser your Claude Code or Codex agents drive with your real logins, and BrowserOS, an AI browser for humans.

Danielle Morrill's setup for giving Claude Code agents real credentials: 1Password as the source, a read-only service account per Mac, and the macOS keychain as the cache.

Composio connects AI agents to 1,000+ apps with managed OAuth, per-user sessions, triggers and a sandbox, through an SDK, a CLI or MCP.

Open-source, self-hosted control plane that runs a team of AI coding and work agents like a company: org chart, tickets, budgets and approvals.

An open-source testing framework for web and mobile apps: an AI agent drives the app from plain-English steps, then replays the recorded actions with no model calls until the app changes.

Google's open-source toolkit of agent skills that find, reproduce and patch security vulnerabilities in a codebase, from threat model to verified fix and report.

Dutch cloud service for full Linux VMs that boot in milliseconds, fork while running and sleep when idle: persistent computers for developers and AI coding agents.

A cloud drive that shows up in Finder but takes no disk space: files stream on demand, every save is a version, and agents can work on instant copies of a whole drive.

How I configure Claude Code for NicAI: layered CLAUDE.md files, hooks, auto-memory, permissions, skills, connectors and the output conventions.

What NicAI has cost me in time and services, what failed on the way, and the lessons I would give anyone building their own AI layer.

My personal AI layer: what it is, why I am building it, how it started in 2022, and where it stands in September 2026.

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.

Dwarkesh Patel's 80-minute interview with OpenAI's Noam Brown: how 10,000-agent swarms work, what maths progress says about RSI, and the alignment problem it raises.

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.

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