v0.4 · open source · MIT

DarwinLoop

Your AI Agents smarter at each user interaction

DarwinLoop is an open-source Python and Node.js library that detects implicit user feedback signals, computes prompt quality metrics, and autonomously evolves your agent's prompt — without touching your infrastructure, storing conversations, or requiring labeled data.

How it works
The problem

You ship your agents. And they stay just the way they are.

Evolving your agents is expensive

Reading conversation logs to find failure patterns is economically irrational at production volume.

Most of your complaining customers get ignored

Every re-prompt, correction, and session abandoned by users is diagnostic data. Today it vanishes on every turn.

Prompts don't age well

Production agents accumulate failure modes silently. There's no alert when your prompt starts degrading.

How Darwin works

Finally an easy way to close the loop

Click a step to see how it works.

Step 01 · Intercept
UserYour Agentdarwin.wrap(...)LLMOne line. Zero latency. No code changes.
Zero-config setup

One wrap call. Your agent now evolves itself.

python
import darwin

agent = darwin.wrap(
    agent=my_agent,          # any LangChain, OpenAI, Anthropic agent
    agent_id="support-bot",
    llm_api_key=OPENAI_KEY   # BYOK — for the mutation engine only
)

# That's it. Darwin runs in the background.
# Your agent now evolves autonomously.
Works with
Anthropic SDKOpenAI SDKLangChainLangGraphCrewAIOpenAI Agents SDKn8n
What you get

Production-grade primitives, not a science project.

Privacy by design

Raw conversations never leave your process. Darwin stores hashes and anonymized summaries only.

Three mutation levels

Injection (session-scoped), Soft Edit (auto-apply to new sessions), Hard Edit (GitHub PR for human approval).

Local-first

SQLite by default. PostgreSQL/Supabase via pluggable interface. No SaaS dependency. pip install and go.

Statistical validation

Fisher exact test, Student's t-test, or threshold-based. Configurable. Mutations only promote when provably better.

Genetic Evolutionary Algorithm mutation engine

Prompt evolution via reflective reasoning + Pareto-optimal candidate selection. The algorithm that beat Claude Opus 4.1 on enterprise benchmarks at 90× lower cost.

Early access

Join the waitlist for DarwinLoop

We're onboarding teams in small batches. Drop your email and we'll send you an invite as soon as a slot opens up.

No spam. One email when you're in.