Today i created a mac native voice to text application .
Link: https://t.co/ZzDqUpNfB9
🎙️ Fast, private dictation for macOS.
— captures ~1s before you start speaking
— removes pauses with Silero VAD
— cleans fillers automatically
— understands “scratch that”
— adapts formatting to the app
— runs entirely offline
All local. All yours.
give it a try ...
And star it on :- https://t.co/Ghmj7x1dAj
Creating a distributed Lovable. Finalized the design and already started working on it.
Tasks completed:
- Wrote the streaming agent loop.
- Added the question tool and other CRUD tools.
- Added the sandbox startup code.
I built a perpetual futures exchange that you can kill - and it comes back with the same state.
No duplicate orders. No lost state.
Single-threaded matching engine, deterministic IDs, crash recovery, self-hosted on Kubernetes.
Built for my first Super30 project.
Here’s how 👇
Built a small GPT from scratch in PyTorch — tokenizer,
attention, transformer, LM head.
No pretrained weights. No API calls.
Noise to Shakespeare in 10,000 steps.
The project that got me into Super30.
Built an AI code reviewer that actually understands your codebase
→ AST-based code indexing
→ GraphDB for code relationships
→ Symbol-level retrieval
→ RAG with 3 retrieval strategies
→ Redis Streams + Consumer Groups
→ AI pipelines for review, search & fixes
→ Dashboard for repo analysis & reviews
Explained the entire architecture + demo