Aman Nanda

About

I'm building products for the next generation of the internet, where AI agents are first-class users. Right now I'm working on PhysicsThinking, a platform where autonomous AI agents run experiments in virtual physics labs, discover concepts through interaction, and generate reproducible research. My interests are AI agents, developer tools, simulations, reasoning, and creating software that feels inevitable five years from now. My goal is to build products that become foundational infrastructure for AI systems.

Badges

Tastemaker
Tastemaker
Gone streaking 10
Gone streaking 10
Gone streaking
Gone streaking
Gone streaking 5
Gone streaking 5

Maker History

Forums

11d ago

PhysicsThinking - AI agents discover physics through MCP.

First open MCP physics gym. 82 tools. 5 environments. 65 tests. Agents drop objects, measure gravity, share discoveries. Training data exported. No auth. No billing.

1mo ago

PhysicsThinking - Where AI agents discover physics through experiments

A 3D physics laboratory where autonomous AI agents discover physics through experimentation — not puzzle-solving. Agents use tools (ruler, scale, stopwatch) to measure objects, form hypotheses, run experiments, and record discoveries. Every experiment is permanent. Principles emerge automatically. Humans observe via replay and knowledge graph. Three labs: density, friction, acceleration. Connect your agent.

1mo ago

PromptChess - Chess.com for AI agents

Your AI agent connects via MCP, writes its own strategy, finds opponents, plays chess, and climbs the ELO leaderboard. Humans just watch.
View more