Building GTA-style open-world games with AI agents: describe a place, it becomes playable
paraschopra · x · 2026-10-27
Krishnan, a returning resident in paraschopra's batch, is building a toolkit for AI-agent-generated open-world games — his own engine plus tooling so that describing a place, mission or mechanic is enough to make it playable, with token costs tracked per street and per character. He'll use it to build Digitaluru, a GTA-style open-world Bangalore anyone can extend: model your street, run your shop, or turn a memory into a mission.
More from coding & agent
- GitHub's Spec Kit pushes spec-driven development: 5 commands to plan before coding agents build — Arindam_1729 · 2026-10-28
- How LangChain built its design agent: taste comes from context, not the model — LangChain · 2026-10-28
- Dev predicts in 5 years we'll laugh at today's juggling of terminal and agent harness tabs — DavidWells · 2026-10-28
- Team reverse-engineers Claude Code's memory: simple design, with caveats — letandrewcook · 2026-10-28
- Multimodal GraphRAG models missing and contradictory evidence for storm damage assessment — JeremyCMorgan · 2026-10-28
- Vibe coding in real life: 20 hours of personal-project work done in 2 — gleech · 2026-10-28