[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"project-96189":3},{"id":4,"name":5,"fullName":6,"owner":7,"repo":5,"description":8,"homepage":9,"htmlUrl":9,"language":10,"languages":9,"totalLinesOfCode":9,"stars":11,"forks":12,"watchers":13,"openIssues":14,"contributorsCount":14,"subscribersCount":14,"size":14,"stars1d":14,"stars7d":14,"stars30d":14,"stars90d":14,"forks30d":14,"starsTrendScore":14,"compositeScore":15,"rankGlobal":9,"rankLanguage":9,"license":16,"archived":17,"fork":17,"defaultBranch":18,"hasWiki":19,"hasPages":17,"topics":20,"createdAt":9,"pushedAt":9,"updatedAt":21,"readmeContent":22,"aiSummary":23,"trendingCount":14,"starSnapshotCount":14,"syncStatus":24,"lastSyncTime":25,"discoverSource":26},96189,"stonkfly","nftechie\u002Fstonkfly","nftechie","A full retained fly-connectome simulation with experimental memory and guarded Coinbase AgentKit trading actions.",null,"Python",292,41,1,0,44.87,"MIT License",false,"main",true,[],"2026-09-20 04:01:32","![Stonkfly: a pixel fly beside a candlestick chart](assets\u002Fstonkfly.png)\n\n# Stonkfly\n\nA fly-connectome simulation that can operate a crypto trading account. Actual neural output, actual Coinbase integration. Profitable learning has not been demonstrated.\n\n**How it works:** Public Coinbase prices become an RGB chart. It stimulates 3,335 brightness inputs and 811 R8 color inputs in the retained **MaleCNS v1.0 graph: 166,700 neurons, 25.6 million connections**. A fixed neural readout proposes buy, sell or hold. A custom **Coinbase AgentKit ActionProvider** checks limits and places spot orders through Coinbase Advanced.\n\nPositive portfolio P&L stimulates 15 identified PAM11 dopamine cells; negative P&L stimulates two PPL101 aversive dopamine cells. A candidate memory rule changes existing KC-to-MBON connections. These are engineered reinforcement signals, **not modeled pain receptors**. Synaptic changes do not establish that it learns to trade profitably. [Model and evidence](docs\u002Fmodel.md).\n\n## Run it\n\nPython 3.11, a C++17 compiler, macOS\u002FLinux. Allow several GB for the dataset and dependencies; 16 GB RAM recommended.\n\n```sh\npython3.11 -m venv .venv\nsource .venv\u002Fbin\u002Factivate\npip install -e '.[test]'\npython -m stonkfly prepare\npython -m stonkfly run\n```\n\nDefault: **paper trades, real public BTC-USDC data, $100 simulated balance**. No key needed. Local logs, sensory images and resumable brain state go in `runs\u002Fpaper\u002F`. Ctrl-C stops it; the same command resumes.\n\nFor real orders, first create a dedicated Coinbase Advanced portfolio with **at most 100 USDC** and a portfolio-scoped **ECDSA API key with View + Trade, no Transfer**. Copy `.env.example` to `.env`, fill it in locally, then run these commands yourself:\n\n```sh\npython -m stonkfly run --live --preflight-only\npython -m stonkfly run --live\n```\n\nDefaults: $10 maximum order including reserved fees, 24 attempts\u002Fday, no shorts or leverage. A $20 drawdown stops new orders; **it does not liquidate holdings or cap further losses**. [Operation and recovery](docs\u002Foperations.md).\n\n```sh\npython -m stonkfly status\npython -m pytest -q\n```\n\nThe repo does not come funded or connected to anyone’s account. Live execution needs your local credentials and explicit opt-in.\n","Stonkfly 是一个将果蝇神经连接组（MaleCNS v1.0）与加密货币交易系统耦合的仿真项目，通过视觉编码的K线图刺激神经网络，并基于多巴胺信号驱动突触可塑性以尝试实现行为反馈学习。核心功能包括：真实 Coinbase 市场数据接入、基于神经输出的买卖决策、受控的现货订单执行（支持纸面与实盘）、以及工程化设计的奖励\u002F惩罚型多巴胺回路（PAM11\u002FPPL101）。技术上采用全保留神经图谱（16.7万神经元、2560万连接），依赖 C++17 编译加速，本地运行且状态可恢复。适用于神经计算、生物启发式交易算法研究及具身AI在金融信号处理中的概念验证场景。",2,"2026-09-12 02:30:03","CREATED_QUERY"]