Great talk by @gnumanth on building and operating remote #MCP server for context-aware model execution in a large payment platform. #architecture#scalability#payments
https://t.co/a1GV8KiF5v
I baked Samvada a fully Indic-stack AI Counselor that uses @SarvamAI 's models for almost realtime inference 🤓
Audio → VAD -> STT (saarika:v2.5) → Text → LLM (sarvam-m) → Text → TTS (bulbul:v2) → Audio
P.S: Will try to host, but need to get the compliance right.
@ChromiumDev /me built a webmcp-bridge 🤓
It connects to remote MCP servers and registers discovered tools with WebMCP (navigator.modelContext.provideContext), so browser AI surfaces can invoke them.
TLDR: MCP tools, now usable through WebMCP in the browser. https://t.co/Fr6SRu6rB7
Hands down, @AnthropicAI's Opus 4.5 is the best coding model I’ve ever used!
I gave Opus a very tough MCP UI challenge and even said, “I bet 1000 BTC you can’t fix it.”
Not only did it fix the bug, it didn’t even keep the 1000 BTC! 🤓
#AI
Happy to see that Google’s codewiki already had one my GitHub repos indexed 🤓
https://t.co/oaZQOUeerM
Reminded me a lot about git-tips https://t.co/pVihBacT6y and deepwiki.
pip install agentu
Features:
- Auto-detects Ollama models (also works with OpenAI, vLLM, LM Studio)
- Memory with importance weights, SQLite backend
- MCP integration with auth support
- One-line REST API with Swagger docs
- #python functions are tools, no decorators needed
#ai
I went swimming in the ocean of @OpenAI's Apps SDK… and came back with a handbook!
P.S: Indeed OAIs official docs is the source of truth, this is just a rough notebook 🤓
Maybe, I can create a CLI tool to scaffold app? 🤷
https://t.co/sCgm25Dl0Z
Built an #AI hair styler by forking an AI Studio app 🤓
Uses @GoogleDeepMind Nano Banana (Gemini 2.5 Flash Image) to suggest + generate hairstyles from your face. 🍌💇♂️
Back in October 2024 I had baked -> https://t.co/8zjB8PhXPD but with 🍌 it is much better!