MinigamesBenchmark
A benchmark of seventy minigames for computer use agents, testing a variety of skills. Think your agent can beat them all?
Get picks like this daily. The day's top launches, AI/tech news, and a weekly opportunity spotlight — straight to your inbox.
This is 1 of 244 launches in modular skills for AI agents — see how it stacks up on momentum and crowding →
1774 other launches read as similar to this one →
Details
- External ID
- 1406614389
- Source
- GITHUB
- Company
- —
- Product
- MinigamesBenchmark
- Website domain
- github.com
- Launched
- Oct. 6, 2026
- Cohort
- —
- Upvotes
- 23
- Upvotes percentile
- 0.49
- Tags
- —
Enrichment
- Niche
- modular skills for AI agents
- Vertical
- Horizontal
- Function
- Observability & eval
- Audience
- Developer
- AI stance
- AI-native
- Project type
- Hobby / open-source project
- Normalized one-liner
- minigame benchmark for computer use ai agents
- Manually corrected
- False
Could you build this?
Partial A web gallery showing 70 minigames is simple, but building a reproducible benchmarking harness that safely executes agent actions across diverse environments requires non-trivial sandbox infrastructure.
What it would actually take: The architecture requires containerized virtual desktop environments (e.g., Docker with headless X11/VNC, xvfb) combined with standardized agent evaluation protocols (OSWorld-style or Anthropic Computer Use APIs). The hard part is building robust deterministic scoring across 70 interactive games, state resets, anti-cheat verification, and reliable screenshot/action capture pipelines without flaky tests.
Competitors
Other products that read as similar to this one — 1774 launches clear the similarity bar, closest 8 shown.
Attention rank: #788 of 1775 (itself plus its competitors, highest first — normalized so YC and Product Hunt are compared fairly).
Launched 342 days after the earliest competitor.
- Miniswap: The Marketplace for Tabletop Games · yc · 2025-11-11 · 32 upvotes · similarity 0.63
- Skill-up · hn · 2026-07-30 · 5 upvotes · similarity 0.62
- agent-skills · github · 2026-09-15 · 16 upvotes · similarity 0.59
- Agent-skills-eval · hn · 2026-05-07 · 79 upvotes · similarity 0.59
- minigame · github · 2026-09-16 · 12 upvotes · similarity 0.58
- SkillGraph · hn · 2025-11-12 · 19 upvotes · similarity 0.57
- Continue? Y/N: A 60-second game about AI agent permission fatigue · hn · 2026-05-28 · 386 upvotes · similarity 0.57
- pi-jev-skill-picker · github · 2026-09-20 · 30 upvotes · similarity 0.57
Other launches for this product
- No other launches for this product.