Theerasak Sukyanudid

Jane Street, Goldman Sachs, JP Morgan, BlackRock, Hudson River Trading, Two Sigma, D.E. Shaw. The most expensive engineering teams in the world released their financial tools on GitHub. Here are 7 repos, one from each. 1. Jane Street, janestreet/magic-trace github.com/janestreet/mag… 5.3k stars. Process tracer powered by Intel PT. When your profiler is blind, magic-trace sees every CPU instruction. 2. Goldman Sachs, goldmansachs/gs-quant github.com/goldmansachs/g… Derivative pricing the GS traders use at their desks. MIT licensed. 3. JP Morgan, finos/perspective github.com/finos/perspect… What JPM traders use to watch markets in real time. A $24k/year terminal, for free. 4. BlackRock, blackrock/lcso github.com/blackrock/lcso Rust optimizer for portfolio problems. Where scipy gives up, this works. 5. Hudson River Trading, hudson-trading/corral github.com/hudson-trading… Structured concurrency for C++20. The foundation of HFT infrastructure at one of the largest U.S. trading firms. 6. Two Sigma, twosigma/flint github.com/twosigma/flint Time-series joins on Apache Spark with temporal tolerance. Built for billions of ticks. 7. D.E. Shaw, deshaw/pyflyby github.com/deshaw/pyflyby Auto-import for IPython and Jupyter. D.E. Shaw also funded the development of IPython itself. Bookmarked it

GEMINI 3.5 FLASH CAN DESIGN ANIMATED WEBSITES THAT LOOK LIKE THEY COST $50,000. Someone just recorded a 25 minute tutorial showing you how to build one from scratch using Google AI Studio and Gemini 3.5 for free.

10 GitHub repos so good they shouldn't be free. 1. AutoHedge An autonomous hedge fund built in Python with four AI agents: a director generates investment theses, a quant validates them, a risk manager decides position size, and an execution agent places orders. Operates live on Solana. With 'pip install -U autohedge', you can start trading immediately. repo → github.com/The-Swarm-Corp… 2. Vibe-Trading A trading system using a Directed Acyclic Graph (DAG) model, featuring 64 finance skills and 29 preset specialist agent swarms. Includes analysis methods like Ichimoku, Elliott Wave, SMC, Black-Scholes, full Greeks, and risk parity. Its crypto desk provides liquidation heatmaps and token unlock tracking. You can observe agents debating strategies in real time. repo → github.com/HKUDS/Vibe-Tra… 3. Fincept Terminal A Bloomberg Terminal replacement that runs on your laptop. CFA levels 1, 2, and 3 analytics. 20+ investor AI agents (Buffett, Dalio, Soros). 100+ data connectors, including Polygon, World Bank, and IMF. Bloomberg charges $24,000 a year. This is free. repo → github.com/Fincept-Corpor… 4. LibreChat Every model ChatGPT runs, plus Claude, Gemini, DeepSeek, and 20 more. Self-hosted. Native MCP support. You own the data, the history, the infrastructure. OpenAI charges $20/month to use their wrapper. This costs nothing to use your own. repo → librechat.ai 5. Open Higgsfield AI A self-hosted cinema studio with 200+ AI models. Flux, Midjourney, Sora, Kling, Veo, GPT-4o, SDXL all in one interface. Text to image. Image to video. Cinema mode with pro camera controls. No subscription. Your data stays local. repo → github.com/Anil-matcha/Op… 6. Open-LLM-VTuber A Live2D AI companion that runs offline, sees your screen, hears your voice, and never forgets. Inner thoughts are shown as a separate text layer, so you watch the reasoning happen before words come out. Pet mode floats it on your desktop. Swap the LLM in one config line. repo → github.com/Open-LLM-VTube… 7. Claude Ads A free Claude Code skill that runs 190 audit checks across Google, Meta, YouTube, LinkedIn, TikTok, and Microsoft Ads. 6 parallel subagents firing at once. Consolidates into a single Ads Health Score ranked by revenue impact. Agencies charge $4,000 a month for this. repo → github.com/AgriciDaniel/c… 8. Agentic Inbox Cloudflare just open-sourced an email client where an AI agent reads your inbox and drafts your replies. Runs entirely on Cloudflare Workers. Each mailbox lives in its own Durable Object. Your email never leaves your Cloudflare account. One click deploys it. repo → github.com/cloudflare/age… 9. Camofox Browser An open source headless browser that makes AI agents invisible to bot detection. Spoofs navigator properties, WebGL, AudioContext, and WebRTC at the C++ level. The browser does not look modified because it genuinely is not. Accessibility tree output drops token cost by 90%. repo → github.com/jo-inc/camofox… 10. Hyperframes HeyGen open-sourced a video framework that does everything Remotion does without React, without JSX, without teaching your AI agent a new format. The agent writes HTML. The framework renders MP4. GSAP, Lottie, and Three.js all work. Same HTML always produces the same file. repo → github.com/heygen-com/hyp… These are not toys. Each one replaces a paid product you're still being charged for. Pick one. Install it. Plug it into your workflow. 100% free. 100% open source.

え、ガチ？ Claude Code、Cursor、Codex、Antigravity を「完全無料」で動かす仕組みが オープンソースで公開されてる😳 名前は 9router。 ・40+の無料・激安プロバイダに自動振り分け ・トークン消費を-40%まで削減（RTK機能） ・1ツールがレート制限になったら別に自動切替 ・「もう制限に当たらない」が現実になる 月に何万円もAIに払ってる人は、まずこれ入れて様子見すべきです。 品質落とさず財布が軽くなる、現実的な解。 github.com/decolua/9router

❤️‍🔥Gemini 3.5 Flash is so cracked at animated websites. Just Recorded a 25 min Tutorial on how to Design websites with Google AI Studio + Gemini 3.5 ($50k Website)

Now when clicking on Service details in maple there is a new dependency section giving an overview over all 3rd party services

introducing Managed Agents on the Gemini API - in one API call, you get agent that comes with a remote Linux environment hosted by Google, ready to scale - you can define custom instructions, skills, and tools in Markdown

10 AI related accounts you should follow on Twitter: 1. Andrej Karpathy — @karpathy 2. Yann LeCun — @ylecun 3. François Chollet — @fchollet 4. Andrew Ng — @AndrewYNg 5. Lilian Weng — @lilianweng 6. Demis Hassabis — @demishassabis 7. Fei-Fei Li — @drfeifei 8. John Carmack — @ID_AA_Carmack 9. Jeremy Howard — @jeremyphoward 10. Gwern Branwen — @gwern follow these 10 before everyone else does. Let me know who I missed?

4 levels of Hermes Agent setup: LEVEL 1: main agent You → Hermes Agent this is your main agent and your prototype area, where you test new workflows and refine them. it doubles as your orchestrator until you have something worth breaking out ---- LEVEL 2: specialized agents You → SEO Agent You → CMO Agent You → Ops Agent once a workflow is solid, break it out into its own agent with its own credentials, memory and scope. --- LEVEL 3: orchestrated team You → Orchestrator ↓ Specialist Agents bring the orchestrator back in. it now steers the company of agents you have built. ---- LEVEL 4: automated team Cron / Events → Orchestrator ↓ Agent Team add task lists so the team works async. cron and events fire jobs, the orchestrator routes them through the task bus, the team handles the work without you ---- take small steps, you DO NOT want to automate slop. if your output at level 1 is mediocre, you are about to scale mediocrity. 20 agents shipping low quality work at speed is worse than 3 shipping great work slowly. I would rather run fewer agents with better output than MAXXING the agent count and spitting out more of the same.

Infographics of a modern Metro made using GPT Image 2 on ChatGPT Prompt; Create a premium square “reference-style urban transportation infographic” centered around a futuristic modern metro system called the {METRO_NAME}, designed as a beautifully curated transit-engineering handbook page rather than a public transport advertisement. The composition should feel like a modern visual encyclopedia mixed with an elite railway infrastructure field guide and high-end editorial infographic system. Visual Direction: • 1:1 square composition • Dark premium urban-tech background with subtle railway schematics, metro maps, and futuristic blueprint overlays • Elegant palette using deep navy, matte black, steel gray, electric blue accents, and soft white lighting • Refined editorial typography hierarchy with modern transportation aesthetics • Rounded modular information cards with clean spacing • Gentle realistic reflections and premium HUD-style dividers • Minimal transit-system iconography • Extremely detailed central metro train render viewed in dramatic three-quarter perspective inside a futuristic underground station • Thin precision annotation lines pointing toward transportation systems and smart engineering features • Clean, organized “knowledge-first” layout with high information density but breathable spacing Main Subject Presentation: A stunning ultra-detailed realistic render of the {METRO_NAME} modern metro train placed at the center, featuring sleek aerodynamic train design, glowing destination displays, realistic stainless-steel textures, illuminated station lighting, smart glass windows, premium urban-environment realism, and futuristic rail infrastructure. Surround the metro with scientific and engineering callouts explaining: • regenerative braking system • smart signalling & CBTC control • electric propulsion system • passenger information systems • safety and surveillance technology • platform screen doors • energy-efficient design • smart ventilation systems • accessibility features • track and infrastructure engineering Include modular infographic sections such as: • Metro System Overview • Technical Specifications • Train Dimensions & Layout • Passenger Capacity & Flow • Smart Control Systems • Sustainability Features • Track & Infrastructure Engineering • Signalling & Automation • Station Design & Facilities • Safety & Emergency Systems • Passenger Experience Features • Urban Connectivity & Network Map • Energy Efficiency Comparison • Construction & Expansion Timeline • “Top 5 Smart Innovations” section • Built for Future Smart Cities Add small premium visualization modules like: • metro network maps • train blueprint diagrams • station layout graphics • passenger flow visualizations • signalling workflow diagrams • energy-efficiency comparison charts • train configuration illustrations • smart-city connectivity graphics • platform safety diagrams • infrastructure cross-section visuals Style Keywords: “premium urban mobility encyclopedia” “editorial metro engineering handbook” “high-end transportation infographic” “scientific railway infrastructure poster” “museum-quality transit reference page” “modular smart-city knowledge system” “clean transportation editorial design” “ultra-detailed metro visualization” Avoid: • cluttered public advertisement aesthetics • cartoon transportation styling • unrealistic sci-fi levitating trains • excessive cyberpunk neon overload • chaotic city scenes • generic subway poster layouts The final result should resemble a professionally published railway infrastructure reference-book page created for transit enthusiasts, architects, engineers, urban planners, transportation designers, and educational infrastructure archives.

Chinese engineers built a Claude-powered bot called PHANTOM that turned $1.18 into $3.3 MILLION. Not signals. Not manual trading. Fully autonomous execution. Stats: • 37,063 trades • 71% win rate • Biggest trade: $180K Copy it here:t.me/KreoPolyBot?st… How it works: Scans thousands of markets across Polymarket + Kalshi Detects mispricing before repricing happens Enters and exits automatically in seconds The system runs 3 different engines: Pairs Arbitrage YES 0.62 + NO 0.41 = instant edge Sentiment AI Scans X + breaking news before markets react Volatility Timing Enters before spikes and exits into movement Why sports and prediction markets are perfect for this: • Slow repricing • Wide spreads • Constant inefficiencies That’s where the millions came from. Humans can’t compete anymore. You can’t monitor 50+ markets at once. You hesitate. You sleep. The bot doesn’t. 24/7 execution. No emotions. No delays. By the time you click, the opportunity is already gone. Manual trading is dying. Automation already won. Want the full setup? Comment “GUIDE” Like + RT Follow @0x_Discover

GPT image V2 prompt share Explored multiple futuristic workshop campaign directions through brand-specific advertising systems for HDFC Bank, SpaceX, OpenAI, and Google. Prompt : ⏬

🚨 ANTHROPIC JUST KILLED THE DEMO AGENT ERA. Their Agents team showed exactly what production grade looks like. Not theory. Not a tutorial. A four layer framework for multi agent systems built to actually work in the real world. 30 minutes. This is the video I wish existed 6 months ago.

there's no catch; SAM3 is open source and really good one of the things it does really well is object tracking, even in crazy complex scenes like basketball probably my favorite computer vision model ever

Instead of watching Netflix tonight, watch this 2-hour Stanford lecture. It will teach you more about how LLMs like ChatGPT and Claude are actually built than most people learn in years working in AI. Stanford released it for free. Save this.

This guy built a trading bot with Claude and made $193,000 on Polymarket His bot trades the microstructure of short BTC Up / Down markets through limit orders and combines a hybrid of arbitrage, market making, and hedging His strategy is simple: > Enters a position when it sees mispricing > Then buys the opposite outcome, turning part of the trade into a paired arb > The base position is hedged with the pair, while the rest remains as a directional trade This guy’s Polymarket account: @0x04b6d7e930cf9e493c5e6ef24b496294f95594c8-1774448369789?via=670" target="_blank" rel="nofollow noopener">polymarket.com/@0x04b6d7e930c… Using this strategy, he captures an average edge of 2-3% and repeats it hundreds of times Consistent micro edge + clean execution = lifechange

the engineer who built Claude Code just dropped a 28-minute video on how to write prompts that actually work I've seen $300 courses that don't cover what he shows in the first 10 minutes CLAUDE.md files, memory shortcuts, parallel sessions, prompting patterns all in one video and completely free works whether you're a developer, a beginner, or someone who's been using Claude for months based on this, I put together 18 things you can copy and use in Claude today full guide in the article below

🤯太强了！ 用 ChatGPT-Image2 生成企业级商用画册，效果超出预期！🔥 我做了一本《曙川智造》智能自动化解决方案画册： 深色科技美学 + 精致机器人视觉，排版专业又有设计感，真实商业物料完成度很高！ 三张图展示案例： 1、封面与封底：完整品牌门面 2、核心内页跨页：企业介绍 + 产品技术 3、全册系统预览：风格统一，整册感很强 一整套可以直接用于企业展示的画册Demo！ GPT生成画册的方法和结构拆解，在评论区👇

🚀 Acabo de probar Antigravity CLI, el nuevo agente de IA de Google y esta muy bueno: ⚡ Está escrito en Go, así que se siente muy ligero 🧠 El modelo Gemini 3.5 Flash responde muy rápido y hace un trabajo bastante bueno, además que justo ahora lo pueden usar gratis. 🛠️ Tiene comandos que no hacen extrañar nada de otros agentes; ahora cuenta con subagentes, puedes programar tareas e incluso tiene la posibilidad de editar el planning con un editor integrado. ✅ Y soporta skills, MCP y similar a Antigravity con la misma configuración 🔥 Mucho mejor que lo que era Gemini CLI de lejos

别让 AI Agent 第二次踩同一个坑。 最近看到一个挺有意思的开源项目：RoBrain github.com/adelinamart/ro… RoBrain 是 AI 编程团队的“决策记忆层”，专门记录一次次 coding session 里做过的技术选择、选择理由、被排除的方案、影响文件和会话元数据，让 Claude Code、Cursor、Copilot 这类工具在新会话里少一点失忆。 比如一个人在 Cursor 里决定购物车状态管理用 Zustand，因为 Redux 引起重渲染问题；另一个人第二天在 Claude Code 里开新任务，agent 又准备建议 Redux。 RoBrain 的价值就在这里：它把当时的决策、理由、被否掉的选项、关联文件都沉淀下来，下一次直接塞回上下文。 我觉得最值得讲的亮点有三个。 第一是 rejected[]，它把“当初为什么没选 Redux / GraphQL / 某个方案”变成结构化字段，这比普通记忆库只记结论更有价值，因为工程里真正反复浪费时间的，往往是大家忘了某个方案当初为什么被否掉。 第二是跨工具团队记忆，README 里的例子是 Alice 在 Cursor 里做了决策，Bob 第二天在 Claude Code 里能把这段上下文拿回来继续干。 第三是 Synthesis，它会对长期积累的决策做批处理扫描，找漂移、冲突和反复出现的实体，相当于给团队的 agent 工作流加了一个“事后复盘 + 冲突雷达”。