Slay the Spire

Orak

Benchmark for training and evaluating language-model agents across 12 video games, Slay the Spire among them, with a public leaderboard.

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.
MCPTheSpire — Slay the Spire mod that runs an MCP server inside the game (Streamable HTTP on port 8080) with tools to read state, play cards, choose options and start runs, so language-model agents can play.
slay_the_spire_agent — Knowledge-grounded language-model agent for Slay the Spire on Communication Mod, with an operator dashboard, decision traces and replay.
slay-the-spire-bench — Benchmark of language-model planning on Slay the Spire tasks: turn sequencing, combat, card recognition and Act 1 rollouts, including a comparison of JSON and plain-English prompts.
SlayTheSpireAI — Lets any language model play Slay the Spire through Communication Mod.

Related