LEO919

My Karpathy-style git wiki knowledge base for OpenClaw got to 2.3GB and I know git limit is 5GB so my GStack autoplan skill one line prompted this spec for my upgraded GBrain with SqlLite. This will be MIT license open source soon. gist.github.com/garrytan/49c88…

分享 5 个开箱即用的 Polymarket 开源交易脚本。 如果你打算在 Polymarket 上构建自动化交易系统，这里有你需要的基础组件。从底层的数据抓取、钱包追踪，到自动化执行和机器学习模型，基本涵盖了量化交易的全套流程。 1. 交易终端 (Trading terminal) 支持快捷键操作、极速下单、盈亏监控以及 Telegram 实时报警。彻底告别每 5 秒就需要手动确认一次钱包签名的繁琐操作。 GitHub: github.com/txbabaxyz/poly… 2. 数据记录器 (Data recorder) 同步抓取 Polymarket 和币安的盘面数据。包括订单薄深度、历史成交和各项技术指标，全部落盘保存并提供实时可视化看板。 GitHub: github.com/txbabaxyz/poly… 3. 自动化交易机器人 (Trading bot) 基于置信度公式动态计算仓位，并设定硬性止损。核心策略是在市场结算前约 4 分钟，系统自动买入当前的高胜率标的。 GitHub: github.com/txbabaxyz/4coi… 4. 钱包分析工具 (Wallet analyzer) 专门用于追踪聪明钱地址。输入任意钱包，自动提取其完整的交易历史，按具体预测市场进行分类，并生成可视化的建仓轨迹图表。 GitHub: github.com/txbabaxyz/coll… 5. 机器学习模型 (ML model) 通过 TAAPI 接口拉取 208 种技术指标，用于预测市场走向并测算盘面的公允价值。 GitHub: github.com/txbabaxyz/mlmo… 以上工具均为免费开源。你可以独立运行这些脚本模块，也可以将它们作为代码库直接喂给 Claude，用来辅助迭代和定制你自己的全自动化交易闭环。

《OKX 对话交易员第 11 期》对话 @lanaaielsa ：一个链上胜率不到 10% 的人，是怎么赢得漂亮的？ 70 U，是棍哥这一轮链上的起点。 巅峰时，他靠 TRUMP 一战数 10m 但他说，他的胜率其实不到 10%。 十次里，九次他是错的。 你可能会问：一个十次里九次判断失误的人，怎么可能赢得这么漂亮？ 他的答案是，交易从来不是热血搏杀，更多时候是忍受低胜率的枯燥，和对人性的管理。怕亏、怕错、怕踏空，这些情绪才是最大的敌人。 他也说，他不擅长交易。他擅长的，是找到真正会交易的人，和那些藏在链上数据里别人看不见的信号。 他存了几十 TB 的链上历史数据，正在持续喂给 AI，训练它学会识别市场节奏，未来用来辅助，甚至替代他自己的交易判断。 刚毕业那年，他在养猪场数猪，为上市公司做 IPO 尽调。今天，他还在数——只不过数的是链上地址、资金流向、和那不到 10% 的胜率里，藏着的那一次机会。 本期 OKX 的朋友们，Mia 对话棍哥 @lanaaielsa ：聊 AI、聊那个胜率 10% 也能赢得漂亮的故事。

x.com/i/article/2033…

Mind blown: A Chinese quant college student builds an AI swarm engine in 10 days flat, explodes GitHub with 13,000+ stars, and scores $4,000,000 in funding! Introducing MiroFish is the multi-agent simulator that's revolutionizing predictions for trading, PR, and more. What is MiroFish? It's a digital sandbox where thousands of AI agents with individual memories and behaviors interact like a real society. Feed it any scenario (news leak, policy change, or even a classic novel's missing ending), and it simulates crowd reactions, debates, and outcomes to forecast real-world events. The Creator's Story: > In late 2025, fourth-year student Guo Hanjiang coded the core using AI assistants. > It went viral overnight, landing him 30m Yuan (~$4m) from Shanda Group. > He ditched the dorm, started a company, and now leads the charge. Key Applications: .Trading: Input financial news or reports, watch simulated market panics and price swings for predictive insights. .PR Testing: Companies/Politics run draft statements to spot backlash and refine messaging. .Creative Experiments: Loaded a lost-ending Chinese novel, agents role-played characters and generated a logical finale. .Easy setup: Deploy via Docker in minutes with any LLM API key. Pro tip: Simulate something wild like Elon Musk tweeting about Dogecoin 2.0 and spawn agent traders, influencers, and investors, generate real-time video clips of the frenzy to test moonshots or crashes risk-free. Traders are already winning big: Check this one on Polymarket - $120,000+ net profits from spot on SPX 500 bets, powered by MiroFish sims on historical data. His profile: polymarket.com/profile/%40moi… For effortless gains, try Kreo copy trading: Auto-mirror pros like him and ride their edges. Try here: @join" target="_blank" rel="nofollow noopener">kreo.app/@join Add his wallet: [0x17559efac103ac7f361be37ec0b93888d4c55aac] to [t.me/KreoPolyBot?st…] and start track/copy him. Repo: github.com/666ghj/MiroFish

x.com/i/article/2031…

Excited to announce our partnership with @PalantirTech and TWG AI to build the next generation sports integrity platform. Some color on why this is significant: Today, in the state-by-state regulatory framework, leagues have limited visibility into what's happening in their markets, fragmented tooling, and have to choreograph their compliance desires across dozens of state regulators with no unified standard. Additionally, the technology being used is rudimentary compared to what's actually possible. The shift to a federal regulatory framework is the chance to innovate around the entrenched, fragmented, and antiquated infrastructure and build this the way it should have been built. Palantir's anomaly detection and data integration is second to none. TWG AI brings deep financial infrastructure and sports expertise, and is owned by TWG, which has ownership stakes in the Lakers, Dodgers, Chelsea, and more. These are the right partners to build something that actually holds up and gets adoption - utilizing our collective domain expertise to build a solution specifically suited for the risk profile of sports markets. If we do this right, our hope is its use will extend beyond sports prediction markets and be valuable to all stakeholders in the sports ecosystem. For the love of the game.