A Soccer Game Simulator Played by AI Agent
An LLM-powered soccer simulation where every player on the field is an AI agent. - GitHub - gangtao/AgentPitch: An LLM-powered soccer simulation where every player on the field is an AI agent.
A Soccer Game Simulator Played by AI Agent launched on May 4, 2026 with 5 votes, #2,008 of 20,538 launches that month and more than 75% of that year's launches.
What it does
An LLM-powered soccer simulation where every player on the field is an AI agent. Each player's decision logic is generated by a large language model and evolves between matches based on prior performance. Each player runs a decide(game_state, player_state, history) callback that you or an LLM writes in Python, JavaScript, or Rust. Before every match the Code Generation Pipeline asks an LLM to produce a strategy; after the match the Post-Match Evolution Pipeline feeds the match log back to the LLM so strategies improve over time. All generated code executes inside language-specific sandboxes — no arbitrary host access. Config (YAML/API) → Code Generation Pipeline (LLM writes decide() code) →…from github.com
Does a similar job
all alternatives →
Agent M - Powered by Floatbot.AI2023 · floatbot.ai · ▲268Generative AI powered Master Agent Developer Framework

I taught AI to commentate Pong in real time2025 · github.com · ▲207LLM-generated real-time commentary for Pong. Contribute to pncnmnp/xpong development by creating an account on GitHub.
OhMyGoat - AI based Soccer picks2023 · ohmygoat.fr · ▲86We use AI to alert you of betting opportunities

More ai this month
the category →



Paintings by AI models: programs run through a simulation of oil paint.
AI · 21d ago · stillwet.art
PixVerse R2▲381A real-time world model you can explore and change
AI · 30d ago · world.pixverse.video

Source: Show HN post ↗
Launched alongside, May 2026
the whole month →

Parallel agents, diff reviewer, and multi-model comparisons
Dev tools · May 2026 · kilo.ai



Hey HN, Henry here from Cactus. We open-sourced Needle, a 26M parameter function-calling (tool use) model. It runs at 6000 tok/s prefill and 1200 tok/s decode on consumer devices. We were always frustrated by the little effort made towards building agentic models that run on budget phones, so we conducted investigations that led to an observation: agentic experiences are built upon tool calling, and massive models are overkill for it. Tool calling is fundamentally retrieval-and-assembly (match query to tool name, extract argument values, emit JSON), not reasoning. Cross-attention…
Life & fun · May 2026 · github.com

🌱 Private, quiet space for thinking. Simple app for .md files. - zakirullin/files.md
Dev tools · May 2026 · github.com