AI

Terminals are a firehose. IDEs already have a notification system. Notification Bridge bolts the two together so my coding agent can tap me on the shoulder.

Your IDE already knows your SDK, dependencies, terminals, and project structure. All that data is locked inside the process. I built two JetBrains plugins to fix that — and I think it's a pattern every local tool should follow.

I've run over 11,000 AI agent tasks this year with a 99.4% success rate. Here's what actually works, what fails spectacularly, and why boring agents beat brilliant ones.

Eighty lines of TypeScript and an MCP server turn Terminal Bridge into a full AI terminal integration. Here's the code, the patterns, and the hard lesson about terminal naming I learned at 2 AM.

I run 6-10 Claude sessions at once. Dispatch and remote control are single-session tools. So I built a mobile PWA that wires into IntelliJ via Terminal Bridge and Tailscale — here's the architecture.

I built four IntelliJ plugins that give AI agents full IDE access — terminals, builds, notifications, project intelligence. Here's what happened when I stopped pasting Maven commands and started letting agents operate the IDE directly.

I shipped Run Configuration Bridge, then ripped out 430 lines of terminal polling code and replaced them with three API calls. Exit codes beat regex. Here's what happened when I ate my own dogfood.

Terminal Bridge started as survival code at 2 AM. Now it's a freemium IntelliJ plugin on the JetBrains Marketplace — built on new APIs, solving a real problem. Here's how it got there.

Terminal Bridge exposes your IntelliJ terminal tabs through a local REST API. I built it because AI coding assistants are blind to your terminal layout — and that needed to change.