Nicheloom

Market intelligence for builders — see what's gaining traction before it's crowded.

A real-time strategy game that AI agents can play

Details

External ID
47149586
Source
HN
Company
—
Product
A real-time strategy game that AI agents can play
Website domain
llmskirmish.com
Launched
Feb. 25, 2026
Cohort
—
Upvotes
220
Upvotes percentile
0.9555256064690026
Tags
—
Fetched at
Sept. 7, 2026, 9:25 p.m.
Updated at
Sept. 7, 2026, 9:25 p.m.

Description

I've liked all the projects that put LLMs into game environments. It's been a weird juxtaposition, though: frontier LLMs can one-shot full coding projects, and those same models struggle to get out of Pokémon Red's Mt. Moon.Because of this, I wanted to create a game environment that put this generation of frontier LLMs' top skill, coding, on full display.Ten years ago, a team released a game called Screeps. It was described as an "MMO RTS sandbox for programmers." The Screeps paradigm of writing code and having it executed in a real-time game environment is well suited to LLMs. Drawing on a version of the Screeps open source API, LLM Skirmish pits LLMs head-to-head in a series of 1v1 real-time strategy games.In my testing I found that Claude Opus 4.5 was the most dominant model, but it showed weakness in round 1 as it was overly focused on its in-game economy. Meanwhile, I probably spent a third of all code on sandbox hardening because GPT 5.2 kept trying to cheat by pre-reading its opponent's strategies.If there's interest, I'm planning on doing a round of testing with the latest generation of LLMs (Claude 4.6 Opus, GPT 5.3 Codex, etc.).You can run local matches via CLI. I'm running a hosted match runner with Google Cloud Run that uses isolated-vm. The match playback visualizer is statically served from Cloudflare.I've created a community ladder that you can submit strategies to via CLI, no auth required. I've found that the CLI plus the skill.md that's available has been enough for AI agents to immediately get started.Website: https://llmskirmish.comAPI docs: https://llmskirmish.com/docsGitHub: https://github.com/llmskirmish/skirmishA video of a match: https://www.youtube.com/watch?v=lnBPaZ1qamM

Enrichment

Theme
AI agent frameworks and developer tools
Vertical
Media & entertainment
Function
Agent / copilot
Audience
B2C
AI stance
AI-native
Project type
Commercial product
Normalized one-liner
real-time strategy game for ai agents
Manually corrected
False

Could you build this?

Yes The system adapts the open-source Screeps engine or a custom 2D grid simulator to run Sandboxed JavaScript bots generated via standard LLM API calls and calculate ELO ratings.

Discussion

20 comments analyzed.

Competitors mentioned: StarCraft AI competitions, OpenAI Five (Dota 2), Beyond All Reasons, Core War, C++Robots

Concerns raised: Turn-based autobattler misrepresented as RTS, Unclear if LLMs actually learn across rounds or improve win rates, Game state may be too token-intensive for LLMs to perceive effectively, LLMs attempting to cheat by accessing opponent strategies

Feature requests: Light mode, Support for hierarchical agents and communication protocols between teammates, Human-playable game mode, Multi-agent team-based matches (not just 1v1)

Competitors

Other products that read as similar to this one — 116 launches clear the similarity bar, closest 8 shown.

Attention rank: #5 of 117 (itself plus its competitors, highest first — normalized so YC and Product Hunt are compared fairly).

Launched 112 days after the earliest competitor.

Other launches for this product

Same idea, different domain

Nobody's really built a agent / copilot tool for Agriculture yet.