Skip to main content
StudioMeyer
Open Source

Code that improves itself

We don't just build websites. We build the tools that make AI systems better. Open source. TypeScript. Production-tested.

Flagship Project

Darwin Agents

A TypeScript framework for AI agents that automatically improve their own prompts. Through evolution, not manual tuning. With A/B testing, safety gates, and multi-model critics.

TypeScriptMIT LicenseMulti-ProviderSQLite + PostgreSQL

v0.4

Current Version

130+

Tests

MIT

License

terminal
# Install
npm install darwin-agents

# Run your first self-evolving agent
npx darwin run writer \
  "Explain quantum computing simply"

# Watch it evolve
npx darwin evolve writer
→ Pattern detected: weak on analogies
→ New variant: writer-v2 generated
→ A/B test: v2 wins (87% vs 71%)
✓ writer-v2 is now default

Self-Evolution

Agents detect weakness patterns and automatically generate improved prompt variants.

A/B Testing

New variants are tested against the current version. The winner becomes the default.

Safety Gates

Every evolution passes through quality gates. No uncontrolled prompt drift.

Multi-Provider

Claude, OpenAI, Ollama, you're not tied to one provider. Pick the one that fits.

How it works

The Evolution Loop

Darwin improves AI agents automatically. No manual prompt engineering required.

1

Agent runs a task

Your agent handles an assignment, writing, researching, analyzing.

2

Critics evaluate quality

Specialized critic agents measure quality, sources, structure, and relevance.

3

Patterns emerge

After enough runs, Darwin detects patterns: 'weak on technical topics', 'too verbose in summaries'.

4

New variant is generated

An optimizer generates an improved prompt variant based on detected patterns.

5

A/B test decides

The new variant is tested against the current version. Blind, fair, data-driven.

6

Winner becomes default

The better variant takes over. Your agent got better, automatically.

Get involved

Open source thrives on community

Darwin is MIT-licensed. Contributions, issues, and feedback are welcome. We build this together.