Building AI harnesses
Hyderabad
Joined November 2022
- Tweets427
- Following308
- Followers1.2K
- Likes370
You can now choose which browser profile the harness should use with the /browser-profile command.
github.com/amankumarsingh77/…
Asked ChatGPT to conduct a mock system design interview, and it absolutely grilled me.
It even asked questions like, “Come up with a formula” for auto-scaling based on the system design.
Will try to do one grilling session with it atleast once 😴
Looks like we are picking up some downloads 😇
If you like visual explanation, this channel is a must try
youtube.com/@pawel_code_stuf…
I eventually settled on the following approach:
• Install and configure Herdr (herdr.dev/) on the host machine.
Think of Herdr as a tmux-like session manager for AI agents, allowing agent sessions to persist independently of your client connection.
👇
This keeps agent work isolated and makes it easy to reconnect to the exact session you were using, regardless of which device you're connecting from.
When I want to inspect or edit code, I connect to the same host using VS Code's Remote SSH extension.
👇
Recently, I've been working on a better setup for using coding agents like Codex, Claude Code, and Pi across multiple devices.
My goal was to run the agents on a dedicated host machine while controlling them from my laptop, so I could work from anywhere in the house. 🧵
Trying to build my own opinionated agent harness orchestration.
->Building upon the pi agent sdk.
-> Has custom tools
-> web search/fetch capabilities
-> Design’s mock
etc….
Will be writing about it soon with a demo 🙃
Every AI browser tool I've used is slow, burns through tokens, and spins up its own Chrome, making me log in again every single time.
So I built a browser harness for the pi coding agent package that fixes all of that, and gives the agent way better access to the page. 👇
For those who do not know what pi coding agent is : pi.dev/
