Glad to see more projects building on top of Lost City. This looks super fun and I can't wait to try it out. Writing RuneScape bots was how I first learned programming, and I think it's one of the most interesting ways to interact with the game.

Botting runescape is how many of us got into programming. Long live botting. If you want to do it, do it on an account that doesnt effect the economy.

AutoRune and SCAR! Though, I never cared much for Delphi.

This is also how I learned programming, though mainly with Simba, the spiritual successor to SCAR: https://github.com/Villavu/Simba

for me it was autoHotKey, amazing programming language with a built in recorder!

Great scripting language, but has a pretty troubled past.

Once the original creator moved on from ownership, the new owner also had a business with Runescape botting.

The story is that it didn't go well for the maintainers of Autohotkey until another person took the reigns.

Paris/ins3 (the RuneScape botting-related owner of AHK) had a fairly checkered past from what I understand, but most of it was before my time.

The direction RSBot took under his leadership was less than ideal. I lamented the loss of RSBot 2 and local scripts. The subsequent versions, dependent on the SDN, were never as good.

Don't forget color bots!

Happy to answer any questions! I think one of the most interesting elements here is the way that the grounding a game environment allows agents to ratchet their engineering progress and run more autonomously than you might be able to for normal engineering tasks.

The demo gif uses Claude Code but looking at the readme it seems like the idea is for it to be a good environment for various machine/reinforcement learning type tasks.

If that's the case what led to the inspiration to use Runescape and are there any notable non-LLM machine/reinforcement models you think might have an interesting time with this?

I am super curious about using and fine-tuning smaller vision-language-action style models! There are also some interesting RL projects out there focused only on PvP: https://github.com/Naton1/osrs-pvp-reinforcement-learning