coolwulf

the airline flight number attached to the icon is in dark color and should be visible, also could switch to satelite view when zoom in, which is dark color

This is fixed now.

I registered on OpenSky and using their API

also fixed the parallelex problem of route trail vs. the plane icon

I just modified zooming algo a lit, now it should improve your user experience.

For people having problems navigating, you can search flifht number on the left search bar. When click on the flight number, the view will jump over.

I will take a look to fix these bugs.

opensky database is limited. I need to find some data source for China and south America

I am on Mac. Will try to get on a Windows box to test this

I changed a higher resolution image and that is why now it is a little bigger...

try change to satellite view it will be more visible

If you switch to satelite view, the planes will be very visible.

:P just optimize to the extreme

I can take a look. The current zoom is zooming to screen center. Maybe I should change it to cursor location.

Need to check my calculations. Thanks for noticing it.

The current data is from OpenSky, mainly north america and EU.

Currently I developed this for desktop browser, so it might not work well on mobile. But I will improve and update it.

It's mainly eGui + WebGPU

coolwulf ai

Hey HN,

I've been building CoolWulf AI (https://coolwulfai.com), a self-hosted personal AI assistant. After seeing OpenClaw blow up, I wanted to share what I've been working on — a different approach to the same problem.

*Why I built this:*

I tried OpenClaw and found the Node.js/TypeScript stack heavy for what's essentially a local agent. pnpm, Node 22+, React — lots of moving parts. I wanted something that's a single binary, zero runtime dependencies, and feels native on macOS. So I built it in Go.

*How it's different from OpenClaw:*

- *Single binary, no runtime needed.* Download, set your API key, run. No Node.js, no pnpm, no build step. One ~100 MB binary. - *Built in Go.* Fast startup, low memory footprint, compiles to a native executable. No garbage collector pauses from a JS runtime sitting in the background. - *macOS-native integrations.* Deep AppleScript-based control of Apple Notes, Reminders, Calendar, Terminal.app, and WeChat desktop. These aren't browser hacks — they use the native accessibility and scripting APIs. - *WeChat support.* This was a big one for me. WeChat desktop on macOS is a native Cocoa/Qt app with a readable accessibility tree. CoolWulf can read messages, send messages, search contacts, and navigate chats — all via AX APIs and CGEvent. I haven't seen another AI agent do this. - *Simpler setup.* Web-based first-time wizard. Configure your LLM provider, connect Gmail/Calendar via OAuth, enable messaging connectors — all from the browser. No terminal wizards, no YAML files.

*What it does:*

- 20+ LLM providers (OpenAI, Claude, Gemini, DeepSeek, Groq, Ollama, local models via vLLM/LM Studio) - Messaging: WhatsApp, Teams, Telegram, Slack, WeChat - Email: Gmail and Yahoo Mail with full OAuth - Calendar: Google Calendar + Apple Calendar - Browser automation: Chrome CDP + Playwright via MCP - Task management: org-mode style with scheduled tasks, cron jobs, automatic execution - Persistent memory: SQLite + vector embeddings for semantic search across conversations - Background heartbeat: runs 24/7, monitors your systems, executes due tasks, sends alerts - Web dashboard for chat, tasks, scheduled jobs, and settings

*Architecture choices:*

Go was the right call. The binary compiles in seconds, cross-compiles trivially, and the concurrency model (goroutines for heartbeat, browser sessions, connector polling) maps perfectly to an always-on agent. SQLite with vector extensions (sqlite-vec) gives us semantic memory without running a separate vector DB.

Try it: https://coolwulfai.com

Happy to answer questions about the Go implementation, WeChat automation, or the macOS accessibility approach.

maybe it's a dns issue with name server. Try https://www.chess-notation.com/

Also I'm able to show all the express deals hotels with their details on a single map, now you can book the hotel like using google map.

You can run the server locally by downloading the local server (both Windows and Mac OS x version)

I am able to reverse engineered Priceline's algorithm on their express deals opaque booking. Using this website you can find the exact hotel the opaque booking is hiding you from.

Invitation code list: 0d59790f c247b410 f59fb470 161fa7d9 b1f63598 370d652e c773561c 769a7306 d1186edc

A side project. Curated >500 high quality college essays and >300 college enrollment information. Then build a QDrant vectodb with embedding. The user updates their portfolio -> AI will use VectorDB with RAG to generate college and major recommendation and help drafting the college essay.

Also current I allow each registered user to send up to 3 invitation codes to friends. If you want to share them here, feel free to post your invitation codes to others. Thank you.

Here are a list of invitation code you could use with your google account to login and play around: 3169eb56 8a246e4c b328dfb3 abac2825 08683ed7 ce34748c bb4bb911 753a3626 b5941da5 579426ff

Please leave a comment to let others know which code you used.

It is the updated version with a newly trained model with more data and added VLLM stage.

I have not heard about them.