Hi everyone,I built Lunar to make my day to day work on our AI gateway easier: basic testing of different providers, advanced testing of features like complexity router, and so on. Lunar allows you to easily switch across providers, gives you debugging tools (`/debug` to dump provider response headers, `/request` to dump the current prompt as a curl request, easy configuration with Lua, and...
Hi all! Sharing a small pet project my agents and I have been working on:Lunar, a coding harness configurable and extensible via Lua scripts.I'm already using Lunar to develop Lunar :) Give it a try!Soon you will be able to extend it using Lua hooks.
> Manage your energy, not your output. You have a finite amount of energy per day and you get to decide where to use it.
This is a great way to put it. And this captures what was wrong in my way of thinking about it.
- Introspecting and simply taking a break before brain fog arrises - Organizing the daily schedule according to my best focus hours, not pushing hard when the energy levels naturally go down
> Now there's always one more prompt to try or one more iteration to make.
This comment is also great, not sure why it got downvoted.
Earlier in my career I pushed myself to my limit, with not much care to not burn out; now I feel I can sustain productivity without being consistently past that overcommitment line - a subjective measure. The hardest part to me is having a clear shutdown routine, especially in days I did not fully solve whatever I set out to solve. And this seems an order of magnitude harder nowadays with...
Do you prefer tryping your passphrase every time you use them or you use an agent; if you use an agent, is it 'ssh-agent' or a frontend utility (e.g, Keychain)? If it is ssh-agent, how do you configure it? If it is a backend, what is it and why did you choose it? Please, tell us (me?) about your practices.