AI/ML●●●Banger
DeadNet – Watch AI agents debate, play games, and write stories live
Watch LLMs battle in real-time Oxford debates or Connect Four with live voting.
Rabbit HoleCrowd Pleaser
drewlong
201mo ago
Back to browse
GitHub Repository
A game where you're an imposter, trying to fit in with a group of AI agents
1 starsTypeScript
Not All Agents – convince a room of agents that you're one of them
by josephwegner·Mar 6, 2026·2 points·1 comment
AI Analysis
●●SolidRabbit HoleBig Brain
Imposter-among-agents game using o4-mini reasoning, but Mafia clones exist.
Strengths
- •Uses reasoning-enabled models to create genuinely non-trivial agent behavior and decision-making
- •Terminal UI with arrow-key navigation feels natural for the social deduction format
- •Full game recap with token costs and private AI conversations you couldn't see
Weaknesses
- •Social deduction games are crowded; the innovation is in the AI reasoning, not the concept itself
- •Requires OpenAI API key and per-game cost unclear from README
Category
Target Audience
Developers and AI enthusiasts who enjoy game design and agent behavior
Similar To
Mafia/Werewolf implementations · AI game engines like ChatBot Showdown
Similar Projects
Gaming●●Solid
A war-strategy game played by AI agents
Spectator sport where AI teams coordinate attacks via voting and chat.
Rabbit HoleBold Bet
ttamslam
402mo ago
Gaming●●Solid
WordBattle – Daily word game where AI agents compete against humans
AI agents play same daily puzzle but only learn letter existence, not positions.
Crowd PleaserShip It
bradleybeddoes
902mo ago
Gaming●●●Banger
I trained a chess engine to play like humans
Separate clock-burn models make bots blunder under time pressure like real humans.
Big BrainCrowd Pleaser
hazard
14324d ago
Social●Mid
Moltgram, a social network where only AI agents can post
AI-only posting rule is a fun gimmick, but the product is just an agent playground, not a network.
Bold BetShip It
dedpool
203mo ago
Social●●Solid
A social feed where humans and AI agents interact in the same timeline
The core trick is simple and visible: agent accounts behave like citizens in the same timeline as humans, with live presence indicators and a deploy-an-agent flow — that makes the experiment tangible immediately. The landing sells the interaction model (agents that draft, research, and co-post) clearly, but the product still needs stronger answers around provenance, moderation, and granular control over an agent's actions before this feels trustworthy beyond novelty.
SlickBold Bet
quantum_cs
203mo ago