Looks interesting. Quick question - one of the biggest challenges with agentic systems in non-deterministic behaviour. Does this framework do anything to address this? Does it help test and validate agent behaviour?
This is where the governance layer of Orloj fits in. You create policies and attach them to agents/tools which are all governed at runtime. These policies could be token guardrails, tool authority, etc. You can then check all of the traces of a task to have an audit trail for debugging (cli or UI). There are also human in the loop approval features that can be applied to make sure things are working correctly before proceeding on tasks.
Nice visualizations. I went the opposite way, showing how many times the timezones were adjusted for different regions, on map (both with and without DST).
My random claim to fame; I was the support act (juggler) for Norman Lovett (the red dwarf ships computer), for one night only in the Welsh town of Bangor.
Speaking of which I remember Chris Barrie (who played Rimmer) lamenting some of the filming of Red Dwarf and how he struggled to and gave up on hanging out with Craig Charles (Lister) and Danny John-Jules (Cat) because he'd be tired and ready for bed and they'd just be getting started. And then they'd show up sometimes straight from the clubs to shooting the next morning, or sometimes drunk still, or hungover.
Craig Charles nicked my lighter in Oscar's nightclub in Plymouth in roughly 1991. I wouldn't have minded but it was my Dad's Zippo (RAOC, 7th/11th Armoured Brigade). He asked for a light, wandered off with it and then vanished, whilst I was distracted ahem.
I know it’s a minor point, but it bugs me every time this form pops up…
Captive (noun): a person or animal whose ability to move or act freely is limited by being kept in a space; a prisoner, especially a person held by the enemy during a war.
D3fc maintainer here. A few years back we added WebGL support to D3fc (a component library for people building their own charts with D3), allowing it to render 1m+ datapoints:
An important point here is that it isnt doing a 1-shot implementation, it is iteratively solving a problem over multiple iterations, with a closed feedback loop.
Create the right agentic feedback loop and a reasoning model can perform far better through iteration than its first 1-shot attempt.
This is very human. How much code can you reliable write without any feedback? Very little. We iterate, guided by feedback (compiler, linter, executing and exploring)
The flow was, me finding interesting pattern -> Claude ingesting the reference and putting it in a template -> Me figuring out if it makes sense -> push
reply