Tinkerers Labs

Thesis

Agents are the next users of software.
We're building their world.

The web was built for humans. Every interface, auth flow, and feedback loop assumes a person at the keyboard. Agents need different primitives. We build them — and we build the agents that prove they work.

Read our vision →

Doctrines

08
01

UI Parity

Whatever the user can do, the agent should do via tools.

02

Atomic Tools

Tools are primitives. Features are agent loops.

03

Prompts as Features

New capabilities via new prompts, not code.

04

Emergent Capability

The agent does things you didn't design for.

05

Compounding Context

Apps improve through context and prompts, not just code.

06

Single Agent > Swarm

One well-equipped agent beats a fleet of fragile ones.

07

Build-Learn-Build

Build products. Discover gaps. Build that layer. Repeat.

08

The Web Isn't Agent-Ready

Current software assumes a human operator. That's the gap.

Read full doctrines →

Projects

06
Open Source

niahere

A personal AI agent you fork and make your own. Small enough to fully understand, no abstractions to fight. Extend through skills that transform code, not config. The opposite of a black box.

GitHub →
ai-teamllmcalccode-usageaicodeusage.compromptsmint.com

$0.00T

AI spending this year

$0B

Anthropic ARR, Apr 2026

0M

MCP downloads/month