alex_varga

Yeah, check out the GitHub and skills for ai agents

If you use MCP servers to connect to multiple tools, you’re probably wasting most of your context window.

Each tool loads its input/output schemas into context. Just 5 tools – like Notion, Gmail, WhatsApp, Jira, and Confluence – can easily fill the entire 100k token window

And your AI agent gets dumber, slower, just because they can't hold large context at once.

Moreover, if you use OpenRouter or any API you will have to pay for storing all of this data in the context, meaning by default any user generates 100k+ context per message How I fixed that: - get-tools loads only the tools you need, using vector search - Smaller context → up to 10x faster request Meaning I can now connect 100+ different tools, and use them dynamically, without bloating the context window

Hey folks. I was exploring different WhatsApp MCPs, but they all required to host it locally. I scaled it to cloud, and now it works.

→ it can text your wife → reply to your mom → book Airbnbs → send investor updates

You can trigger WhatsApp via API, or inside Claude, Cursor, ChatGPT etc. → Full WhatsApp API is exposed: send, receive, get contacts, chats, etc. → VeyraX helps AI with tool calling

WhatsApp MCP is also available inside VeyraX Flows.

→ Connect Whatsapp to Notion, Gmail, Jira, Slack — whatever you want → Flows have public API → Create your own + share it with friends

Since it is free, I found it useful to share it into our mcp community. Can you please support?

I implement it on Go Server with whatsmeow and websockets connection, and proxied it via python Fast API to make it available in the VeyraX marketplace

Hey HN,

We built VeyraX to make it easy for anyone to automate complex workflows using just natural language.

Think Zapier + LLM + instant testing

The core idea: you describe a workflow ("When a new GitHub issue is created, summarize it with AI, then send to Slack"), and our agent connects the tools, builds the flow logic, and lets you test it before publishing.

-> VeyraX supports 70+ tools: GitHub, Linear, Notion, Gmail, Sentry, Typeform, Airtable, etc. -> You can test flows in real time with AI (similar to vibe coding) -> You can also ask the AI to generate and optimize flows for you -> We have API for each flow available as REST, or MCP

Why we built it:

We were tired of spending hours wiring APIs or learning new automation platforms just to save 5 minutes a day

We wanted something that felt like an AI teammate — not just a bunch of triggers and actions.

Would love your feedback – especially on the interface and flow testing logic. Happy to answer anything!

thanks!

AMA!

The only issue, that they are probably trained on most common data. This includes the fact that FDA and some other major organisations avoid some sort of diseases (parasites, 3.5B people infected, lyme disease and some more)

looking forward on updates

If you are looking for a cost-effective provable computation programming language for dApps, consider Cairo. It’s native to Provable Computation and includes low-level access to memory, underlying primitives, and functional-style programming. In this article you will find code examples and a list of resources how to learn Cairo in 2022