OpenViSTAI · Agents · Blockchain · Crypto
Submit a project
Menu
Trading & Crypto Agents

Darwinia

Darwinia is a Python-based, MIT-licensed trading-agent system that evolves Bitcoin strategies through genetic selection, backtesting and adversarial self-play.

Explore the practical guide ↓

Independent OpenViST project profile, based on linked sources.

Darwinia — OpenViST project profile in Trading & Crypto Agents.
OpenViST project illustration. See the linked sources for product details.
Understand the project

Practical overview

When it fits

Use Darwinia when the task is researching or testing adaptive Bitcoin trading strategies and their behaviour under adversarial scenarios, rather than executing trades on an exchange.

Who it is for

  • Quantitative-finance researchers exploring evolutionary strategy discovery
  • Developers building or testing Bitcoin trading agents
  • OpenClaw and Claude Code users who want an agent-oriented strategy-evolution workflow

Documented uses

  • Generate trading-strategy candidates through population-based evolution
  • Evaluate strategies against included BTC data
  • Stress-test an evolved champion against simulated market attacks
  • Inspect discovered patterns through a local dashboard or agent workflow
Before you choose

Requirements & limits

The repository is public and MIT-licensed. Its quick-start documentation describes self-hosted local use with Python and NumPy, included BTC data and no API keys. OpenClaw and Claude Code skills are also documented.

  • The core approach uses genetic selection, crossover and mutation rather than only manually authored rules.
  • Evaluation includes named simulated attacks such as rug pulls, fake breakouts, slow bleeds, whipsaws and volume mirages.
  • The repository documents a 17-gene strategy representation covering signals, thresholds, personality and adaptation.
  • The system is positioned for backtesting and research; live trading and exchange execution are not established by the supplied material.
  • OpenClaw and Claude Code are supported as distinct agent-oriented integration paths.

Check current requirements in the official documentation. Source-based guidance does not mean OpenViST has run or independently tested this project.

Source-based practical guide

Set up Darwinia for local strategy evolution

Install the repository and prepare its documented local workflow for evolving BTC trading strategies.

Before you start

  • Python 3.9 or newer
  • A local copy of the public Darwinia repository
  • Python and NumPy; the repository quick start states that no API keys are required

Steps

  1. Clone the Darwinia repository and change into its project directory.

  2. Install the project with its development dependencies using the repository’s documented installation command.

  3. Run the documented evolution command to generate strategy candidates.

  4. Run the documented adversarial arena command to evaluate a champion against simulated attacks.

Expected outcome

A local Darwinia workflow is prepared to evolve strategies and evaluate a champion in the adversarial arena.

Guide limitations

  • The supplied documentation describes backtesting and simulated attack scenarios, not live trading or exchange execution.
  • The result depends on the configured evolution and evaluation workflow; the documentation does not establish future trading performance.
Documentation 1 ↗
Evidence and transparency

Sources & review

Official repository ↗
Source record details
Source availability
Active
Sources checked
4 October 2026
Original website title
0xSanei/darwinia · Official homepage title · retained in its source language
How we review sourcesSuggest a correction