repowisenftechie/stonkfly

nftechie / stonkfly

A full retained fly-connectome simulation with experimental memory and guarded Coinbase AgentKit trading actions.

Python★ 868
Use in your agentAsk this codebase

github.com/nftechie/stonkflyIndexed at 78ef3e0Up to date with upstream

What is stonkfly?

stonkfly is a Python simulation of a fly connectome that can operate a cryptocurrency trading account. It converts public Coinbase prices into visual inputs, processes them through a retained neural graph, and uses a fixed readout to propose buy, sell, or hold actions. The project is primarily written in Python and includes one C++ file.

Written by a model from the README and the source

41 files and 160 symbols in 2 modules, led by Python (27 files) and C++ (1).

Start reading

Code health

8.0out of 10Good
Full health report

Use nftechie/stonkfly in your agent

Point Claude Code, Cursor, Codex or VS Code at this repository. Your agent gets the index this page is built from: cited answers, callers, history and health for any file.

  1. 1.In Claude, open Customize → Connectors, click +, then Add custom connector. On a Team or Enterprise plan an owner adds it first under Organization settings → Connectors.
  2. 2.Paste the server URL below as the Remote MCP server URL, then click Add.
  3. 3.Click Connect. A Repowise sign-in window opens. Approve access.
  4. 4.Repowise's tools are now available in your Claude chats.

Connect with one click. Sign in with Repowise (OAuth), no API key to copy. Works in Claude on the web, desktop, and mobile.

Docs
bash
https://api.repowise.dev/mcp/nftechie/stonkfly
Editors need an API key: sign in to create one.Sign in to connect

This repo is public, so anyone with a Repowise account and an API key can connect.

Try asking

  • get_overview()
  • get_answer("how is stonkfly put together?")
  • get_why("why is stonkfly structured this way?")

Explore stonkfly

Key features of stonkfly

  • stonkfly simulates a retained fly connectome using public Coinbase prices as visual inputs.
  • stonkfly proposes buy, sell, or hold actions through a fixed neural readout.
  • stonkfly supports paper trading with public BTC-USDC data and a simulated balance.
  • stonkfly can place Coinbase Advanced spot orders through a custom Coinbase AgentKit ActionProvider.
  • stonkfly applies engineered reinforcement signals from positive and negative portfolio P&L to selected dopamine cells.
  • stonkfly includes a candidate memory rule that changes existing KC-to-MBON connections.

How nftechie/stonkfly works

Public Coinbase prices enter as an RGB chart and stimulate brightness and R8 color inputs in the retained MaleCNS v1.0 neural graph. The neural graph processes those inputs, while a fixed neural readout proposes buy, sell, or hold. Positive or negative portfolio P&L stimulates specified dopamine cells, and a candidate memory rule changes existing KC-to-MBON connections. Coinbase AgentKit checks trading limits and places spot orders through Coinbase Advanced. The stonkfly package provides the command-line entry points, while runs/paper/ stores local logs, sensory images, and resumable brain state. The tests directory contains the project tests.

The codebase has 41 files and 160 symbols in 2 modules, led by Python and C++. Code health is 8.0 out of 10, rated good.

Getting started with stonkfly

  1. Create and activate a Python virtual environment.
    python3.11 -m venv .venv
  2. Install stonkfly with its test dependencies.
    pip install -e '.[test]'
  3. Prepare the dataset.
    python -m stonkfly prepare
  4. Run the default paper-trading mode.
    python -m stonkfly run

Commands copied from the README

nftechie/stonkfly FAQ

What is stonkfly?

stonkfly is a fly-connectome simulation that can operate a cryptocurrency trading account. It uses neural output to propose trading actions.

How does stonkfly work?

stonkfly turns public Coinbase prices into an RGB chart, stimulates a retained neural graph, and sends its fixed readout to guarded Coinbase trading actions.

How do I install stonkfly?

stonkfly installs in a Python 3.11 virtual environment with pip install -e '.[test]'. Prepare the dataset with python -m stonkfly prepare before running it.

What language is stonkfly written in?

stonkfly is written primarily in Python and also includes one C++ file.

How is the stonkfly code organized?

stonkfly's main package is in stonkfly, and its tests are in tests. The runs/paper/ directory stores paper-trading logs, sensory images, and resumable brain state.

When should I use stonkfly?

stonkfly is for simulating a fly connectome with cryptocurrency trading actions. Its default mode uses paper trades and public BTC-USDC data without requiring a key.

What license does stonkfly use?

stonkfly uses the MIT license.

The summary, features and answers on this page are written by a model from the README and the source, and refreshed with each index.

About this page

Get a page like this for your own codebase

Repowise built this map of nftechie/stonkfly from its source and git history. It parses every symbol, draws the dependency graph, scores each file's health from complexity, duplication, coverage and churn, finds hotspots and owners in the history, and writes documentation for every module. Your coding agent reads the same index over MCP, so its answers cite real files.

Index your repo freeSee how Repowise worksFree for 2 public repos, with a page like this one.

Prefer local? pip install repowise && repowise init indexes your own checkout, no account needed.