LearnTheSpire

Early experiment (2018) training a feed-forward network on local run files to predict which card a player picks, with cards encoded as 1×234 vectors.

AgenticSTS — Research testbed for long-horizon language-model agents on Slay the Spire 2, built around bounded, typed memory instead of a growing transcript. Reports 3/10 wins at Ascension 0 without learned skills and 6/10 with them.
ai-spire — Slay the Spire 2 mod that asks an OpenAI-compatible model (DeepSeek by default) for decisions, adds Spire Codex card data to its prompts, and falls back to a rule engine when the API call fails.
AutoClad — Imitation-learning pipeline on sts_lightspeed: it generates scenarios, records a scripted agent's choices, trains a network to copy them, and exports it for C++ inference. Early work aimed at A20 Ironclad.
Bottled AI — Full-run bot on Communication Mod using hand-built priority lists for choices and a simulated search over hand orderings in combat. The README reports a 52% win rate with its best Watcher strategy.
CombatSolver — In-game combat solver for Slay the Spire 2 single player. It simulates hands, draw piles, enemy intents, potions and relics across turns in the background, then recommends a line or plays it automatically.
slay_the_spire_agent — Knowledge-grounded language-model agent for Slay the Spire on Communication Mod, with an operator dashboard, decision traces and replay.

Related