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.
v0.4
Current Version
130+
Tests
MIT
License
# 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 defaultSelf-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.
Agent runs a task
Your agent handles an assignment, writing, researching, analyzing.
Critics evaluate quality
Specialized critic agents measure quality, sources, structure, and relevance.
Patterns emerge
After enough runs, Darwin detects patterns: 'weak on technical topics', 'too verbose in summaries'.
New variant is generated
An optimizer generates an improved prompt variant based on detected patterns.
A/B test decides
The new variant is tested against the current version. Blind, fair, data-driven.
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.