CandlePulse – Natural language trading alerts powered by AI
Natural language to trading logic beats manual indicator configuration.

Persistent memory across sessions, but Lovable and v0 already dominate app generation.
Developers and power users wanting custom tools without coding
Lovable · v0 · Cursor
you get your own cloud instance at matrix-os.com. you describe what you want ("build me an expense tracker with categories") and it appears on your desktop as a real app saved as a file.
tech stack: node.js, typescript, claude agent sdk as the kernel, next.js frontend, hono gateway, sqlite/drizzle. everything is a file, apps, data, settings, ai memory. git-versioned.
what makes it different from chatgpt/claude artifacts: - persistent memory that learns your preferences across sessions - apps are real files you own, not ephemeral chat outputs - runs 24/7 in the cloud, not just when you have a tab open - accessible from web, telegram, whatsapp, discord, slack - open source, self-hostable
came out of placing top 20 at anthropic's claude code hackathon. been building it full-time since.
2,800+ tests, 100k+ lines of typescript
live: matrix-os.com github: github.com/HamedMP/matrix-os
would love feedback on the approach. the core bet is that ai should be an os, not a chat window.
Natural language to trading logic beats manual indicator configuration.
Claude-powered OS kernel with multi-agent architecture, but execution is early and architectural novelty is limited.
Yet another CLI note tool with Ollama wrapped around embeddings and reminders.
Natural language test generation via Claude; OpenAPI scanner auto-detects specs from source.
Parametric BREP output beats mesh generators like Meshy for actual engineering.
Pseudocode IR layer validates before execution, but orchestrates existing APIs like Midjourney and Runway.