SkillOpt is a text-space optimizer that trains reusable natural-language skills for frozen LLM agents through trajectory-driven edits, validation-gated updates, and deployable best_skill.md artifacts.
- agent-skills
- self-evolving-agents
47,133 repositories indexed
1–10 of 10 · Most stars
SkillOpt is a text-space optimizer that trains reusable natural-language skills for frozen LLM agents through trajectory-driven edits, validation-gated updates, and deployable best_skill.md artifacts.
Main development repository for Rigs of Rods soft-body physics simulator
The server and client used in transit map simulations like swisstrains.ch
OPAL: a reactive optimizer. A coding agent rewrites the optimizer while your model trains.
A simple 2D game written in C# with .NET Core. Development is streamed live on https://twitch.tv/davidwengier and past streams available on YouTube at http://bit.ly/trains-net-videos
Roblox Luau Language Server based on Lua by sumneko.
A smart picker for Snacks.nvim that trains a neural network with your file picking preferences.
A Python toolkit for generating human-readable timetables from GTFS data; uses PANDAS and gtfs_kit
Reactive Live London Tube trains status
Iran Railway-Trains (Raja-Fadak-Safir) all in one package for DotNet (Api-WebService)