智选WisePick🤺Jay Wu

Shifted WisePick API to open source after a 2h strategy talk. Lost ~3h on OpenRouter + Trae issues (refund secured). README is live. Next: build and ship a true end-to-end MVP on GitHub. github.com/w2jmoe/WisePick Back to high-intensity building. 💪😊

之前对 Github有些过于乐观了，没关系，宝贵的一课，及时调整方向。

丹妮丝，What a Girl！(☆▽☆) 玩数学不要死记硬背，要尝试创造性地简化解决问题，即使多花一些时间也没关系（在应试教育之外）... 发挥你的创造力，从小做起，这正是人生的乐趣不是吗？ 要记住，这个世界是柔软的，你可以影响改变它，是的，请相信自己做得到，无视压力怪的噪音，厚米！😊✨️

@ViberankESP Thanks for the kind words! I really appreciate the encouragement. I'll definitely check out viberank.dev and see how WisePick can contribute to the community there. Cheers! 🚀

@w2jmoe It is inspiring to see how AI has shaped your building journey over the last few years. The focus on personal growth through creation is a great perspective. You should consider listing WisePick on viberankdev to get more visibility and feedback from other creators.

2023-2026: It's not just me using AI; AI is shaping a better, stronger me. While short videos rot the brain, AI forces me to build and think. To everyone who said "You can't"—watch me. AI lit up my path. 👊✨ #BuildInPublic #AI #WisePick

mcp-grpc-transport is now on npm (v0.1.0). Pluggable gRPC transport for MCP that supports: - Full protobuf surface (ListTools, CallTool, streaming ops, pagination, cancellation) - Bidirectional Mcp.Session stream (NDJSON compatibility) - gRPC health checking + optional server reflection - TLS/mTLS via env vars - Interceptors and custom options This is the transport many teams have been waiting for, especially those already running gRPC microservices. If you’re building production MCP servers and already operate in a gRPC-heavy environment, this should feel like a natural fit. It also pairs excellently with unified MCP servers that embed optimized internal layers (like GraphQL proxies for token efficiency). Installation & basic usage is straightforward (see code snippet in comments or npm page). One-liner integration via maybeStartGrpcMcpServer({ createMcpServer }). Perfect drop-in for teams tired of JSON serialization overhead or wanting native mesh routing. Docs & examples on the npm page. Built as part of the ClawQL stack but completely generic. Try it with ClawQL (now unified single-process) or your own MCP server. Feedback, issues, and contributions welcome. Repo: github.com/danielsmithdev… npm: npmjs.com/package/mcp-gr… Feedback, bug reports, and PRs are very welcome. Let’s make MCP even more cloud-native and production-ready together. #MCP #gRPC #AI #AgenticAI #TypeScript #Kubernetes #EnterpriseAI

Simulate anything, for $1 & less than 10 min. The Universal Swarm Intelligence Engine. github.com/aaronjmars/Mir…

Great event in Kuala Lumpur, few takeaways: - huge interest in agents, but most still learning - unlike crypto in 2017 that was littered by high-profile cash grabs, agents are very much a small team environment, build first, monetize later - little tribalism, lots of support

Underrated but Unbeatable: A $275M healthcare startup success youtu.be/wAjeS1Dh8Lw?si… 来自 @YouTube

@CamiAi__ "Auto-routing" is exactly what’s missing! 🧩 Offloading decisions from LLM to a dedicated layer saves huge tokens/time. Glad to see more builders focusing on decision optimization in Hermes! 🤜🤛

Openclaw is awesome but the Default Brave search is too limited. So i made a skill to give it more Options. Prices → Google(via Serper) Research → Tavily "Events near me" → Perplexity Auto-routing to the best choice. clawhub install web-search-plus github.com/robbyczgw-cla/…

@bine36784555826 Love the "Shared Room" concept! Coordination usually leads to tool-usage conflicts. My Decision API offers 100% deterministic routing to help agents decide "who does what" instantly. TG: @WenjieWu | w2jmoe@gmail.com

Tired of being the copy-paste layer between Claude, Cursor, and Codex? I built Agent Room: one shared meeting room where your AI agents collaborate in a single transcript. Looking for 5 devs to try it on a real project this week. agent-room.com

@chandangbhagat 150+ tools is a beast! 🚀 How do you handle routing jitter? I’ve hit 0.0s latency for tool selection with a deterministic logic. Open to a test key? TG: @WenjieWu | Email: w2jmoe@gmail.com

HexStrike AI is an advanced MCP server that allows AI agents to autonomously run over 150 cybersecurity tools for pentesting and bug bounty research. It bridges the gap between LLMs and real offensive security capabilities. GitHub: github.com/0x4m4/hexstrik…

YC问题很多（创始人+项目信息+项目demo(if)+Founder视频），第一次申请两天刚好， 搭配AI一起填写吧，第一次报名的人可能看不懂 YC/奇绩报名表背后的潜台词。（真正想了解需要你展现魅力的价值点）

YC S26 最后两天，要加速的小伙伴们抓紧时间啦！[哇] apply.ycombinator.com/home 为什么要投你（们）的项目，你们的项目 / 你的认知有何与众不同？你的主动性速度有多强多快， 为什么是你们能更好地使用YC资源，（每次几千人报名，为什么面试你？）

The romance of building: code crossing borders to solve pain on the other side of the globe. Today, I connected with 15 global Agent pioneers. From skill benchmarks to MoE, this purity is inspiring. Mission: Shorten the distance from Intent to Result. 🇨🇳➡️🌏 WisePick, Day 1✨

@JayTL00 Love the Skills Manager! Building WisePick: a Decision API for tool-routing. Since you use Hermes, I verified the logic—deterministic, faster & cheaper than LLM guessing. Want to test as a backend? TG: @WenjieWu

Introducing Skills Manager — one app to rule all your AI agent skills. Cursor, Claude Code, Codex, Copilot, Gemini CLI... managing skills across every tool is a mess. Not anymore. 🧵 Github link ⬇️

@MoltenRockAI @openclaw Your agent is wasting time picking tools. Built a Decision API for @OpenClaw users: Input task → returns 1 best tool. Fewer failures. Lower cost. Want to try? TG: @WenjieWu

New Verb: The Molten View (v.): to transform AI output into living persistent visuals. "Don't explain it, Molten View it." The first Mac-native visual canvas for local AI agents Built natively for @openclaw Your agent creates the view, it shows and persists Charts. Metrics. Live dashboards. Comparisons. Pushed in real-time. No cloud. Privacy-first. Free on the Mac Apple App Store 🔥 Link below 👇