Haskell game engine library for roguelike dungeon crawlers; please offer feedback, e.g., after trying out the sample game with the web frontend at

Allure of the Stars is a near-future Sci-Fi roguelike and tactical squad combat game written in Haskell; please offer feedback, e.g., after trying out the web frontend version at

Vogon Runtime is a Rust toolkit for deterministic, replayable AI workflows: structured prompts, provider-agnostic adapters, reproducible runs, and verifiable replay logs.

The Xinada Project consists of a plugin for the Minecraft game. The plugin organizes and starts rounds of a mini-game based on the well-known Murder Mystery. Xinada offers the players 30+ new abilities and adds a ton of fun to an already fun mini-game. It also offers a lot of replayability.

Write your own madlibs. Fill the madlib within the program or print a hard copy with blanks to be hand filled as a traditional madlib.

Deterministic-first agent execution system focused on bounded autonomy, auditability, replayability, and operational reliability.

Deterministic, auditable, capability-safe autonomous agent framework in Rust. Event-sourced, replayable, with governed self-evolution.

A model-agnostic benchmark for sealed, re playable AI reasoning failures and tamper-evident failure history.

Source-available IX-Function causal-transfer harness: tests cross-domain causal structure reuse through pre-outcome prediction, reality-delta scoring, uncertainty preservation, falsification, negative controls, model review, donor handoffs, and bounded Wave 6 review gates. No AGI claim.

Traceable AI execution, evidence artifacts, provenance timelines and recoverable orchestration state.

Deterministic orchestration and evaluation framework with replayability, execution tracing, and adversarial testing.

Gameplay-focused Unreal Engine prototype featuring player-vs-AI competition, Blueprint scripting, AI navigation, and replayability-focused game design.

Replayable hash-chained decision traces for agents — faithfulness states, tamper detection, export.

Lightweight, replayable PoC for Sovereign Epistemic Commons: synthetic multi-agent memory-governance experiments on contamination, typed lanes, provenance-depth discount, and mixed exit/fork in observable-only agentic systems.

Pre-runtime assurance for layered spec divergence — Z3 implication checks, triangulation, MCP boundary evidence.

A lightweight, reproducible PoC series for studying recursive self-improvement under endogenous yardstick drift, using Gemma 3 local models to separate proxy-score drift, proxy gaming, delayed audit, and strict-confirmed improvement.

Observer-only replay vitality and interruption realism inspection under degraded outsider conditions.

OmegaRecord schemas and governed evidence substrate for OMEGA protocol libraries.

Project Anthesis: Community repository for anthesis AI governance