Code that breeds better code
This page is not a demo. A real evolutionary engine is running in your browser right now — mutations competing across island populations, MAP-Elites preserving diversity, the fittest surviving. That's the product. Define what "better" means; evolution does the rest. Zero prompts in the loop.
Every gauge below is wired
to the same running engine.
Watch a session unfold. Mutations compete. Fitness climbs. The grid fills. All autonomous — and all real: these instruments read from the evolution running in this page, not a recording.
Not a code assistant.
An optimization engine.
Searches the space of possible implementations. Maintains diverse solutions. Rejects regressions. Runs unsupervised.
LLM Ensemble
Claude, GPT-4o, Haiku generate competing mutations. Adaptive weighting shifts traffic to models producing better variants.
MAP-Elites Grid
Quality-diversity algorithm maintains a grid of solutions indexed by feature dimensions. Finds approaches you'd never think to try.
Island Parallelism
2–5 isolated populations evolve independently. Periodic migration shares breakthroughs without homogenizing the search.
Regression Detection
EvoClaw-inspired precision tracking. Candidates that break existing tests are rejected. F1 balances recall and precision.
Milestone Evolution
Dependency-graph milestones for long-horizon tasks. Prior milestones become regression tests automatically.
Docker Sandbox
Read-only filesystem, no network, 256MB RAM, 1 CPU. Safely evolve untrusted code in full isolation.
Five steps. Then sleep.
Mark the code, define fitness, launch. Evolution runs autonomously.
Mark the mutable region
Wrap code with EVOLVE-BLOCK markers. Everything outside stays frozen.
Write a fitness function
A script that takes a program and outputs a score. Accuracy, speed, compression — anything measurable.
Pick a preset & launch
quick_prototype for 30 generations in a minute. evoclaw_evolution for 300 overnight.
Watch evolution unfold
Real-time WebSocket streaming. Fitness curves. MAP-Elites grid filling. Island migrations. Or just wait.
Retrieve the winner
Get the best program with full lineage, feature coordinates, and evaluation metrics. It won't be what you'd write.
def pipeline(data):
cleaned = preprocess(data)
# EVOLVE-BLOCK-START
def optimize(x):
return sorted(x, key=lambda r: r.score)
# EVOLVE-BLOCK-END
return postprocess(optimize(cleaned))
curl -X POST localhost:3000/api/v1/evolve/start \ -H "Content-Type: application/json" \ -d '{"preset": "algorithm_discovery", "session_id": "my-run"}'
Pick a strategy.
Launch in seconds.
Each preset configures model weights, temperatures, population sizes, cascade stages, and evaluation timeouts. Press "run in chamber" to load its search profile into the live engine above.
Production-grade.
From day one.
- Security scanner blocks eval(), os.system(), subprocess
- Docker sandbox: read-only FS, no network, 256MB RAM
- Per-session token and cost budgets with 80% warnings
- Rate limiting: 5/user, 50 global (Redis-backed)
- Input validation on all config values and code sizes
- Full audit trail: every mutation, evaluation, migration
- WebSocket streaming with auto-reconnect + polling fallback
- /health endpoint for Kubernetes liveness probes
- /metrics endpoint with per-session aggregate stats
- Session persistence and restore after restart
Stop writing code.
Start evolving it.
Let hundreds of LLM-generated variants compete and breed across generations. Get solutions no single prompt could produce.