# Our products

> Open-source projects we built ourselves: a local AI assistant, a receiver of live Solana transactions and an event relay to Telegram. The code is public on GitHub, so you can see how we work before you write to us.

Page: https://nopeoplelabs.com/products/ · Russian version: https://nopeoplelabs.com/ru/products/

## GhostSwitch: Local AI assistant

One open Qwen3.5 model plus a library of LoRA experts for code, finance, law, CAD and two dozen other fields. For every message it picks the expert that fits, writes the answer and checks it in code. Runs on a laptop with 16 GB of memory.

### What it does

- A router picks the expert for each message, or answers with the base model when none fits
- The expert attaches to the model already in memory in 0.1–0.3 s, with no reload
- Answers are checked by code: completeness, arithmetic, citations, JSON fields; a failed check means a retry
- OpenAI-compatible API: works with the OpenAI SDKs and the OpenCode coding agent
- Chats stay on your computer; it works offline once the models are downloaded

### In numbers

- **88.3%** HumanEval+ with the coding expert, against 76.7% for the base model
- **16 GB** of memory runs the whole expert library
- **27** experts for Qwen3.5-9B

- Stack: Python, Qwen3.5, LoRA, MLX, llama.cpp, OpenAI API
- Code on GitHub: https://github.com/hiddenway/GhostSwitch
- License: Apache-2.0

## Solana Shred Receiver: Live Solana transactions

Joins Solana mainnet Gossip as an unstaked node, receives the shreds Turbine sends it and rebuilds transactions from them; missing shreds are recovered with Reed-Solomon. Live transactions with no validator, no stake and no paid shred feed.

### What it does

- Decoded transactions without Jito ShredStream, DoubleZero or a paid RPC
- Two decode paths: complete data shreds go out at once, missing ones are rebuilt from coding shreds
- Duplicate shreds from different retransmitters are dropped before recovery
- WebSocket streams of shreds and transactions, Prometheus metrics, JSON logs

### In numbers

- **~40 ms** on average from a received shred to a decoded transaction
- **$0** for the shred feed: no paid provider behind it
- **4 GB** of RAM and 4 vCPU run one instance

- Stack: Rust, Solana, Agave, Gossip, Turbine, Reed-Solomon, Prometheus
- Code on GitHub: https://github.com/hiddenway/solana-shred-turbine-receiver
- License: MIT

## RelayCore: App events to Telegram

A serverless relay on Vercel: your apps send events to one HTTP endpoint, RelayCore delivers them to Telegram bots and chats. Bots, routes and chats are set up in a web dashboard, with no server to run.

### What it does

- Server errors, deploys, payments and cron jobs arrive as Telegram messages
- One event goes to many chats at once, including topics in forum groups
- A live event log with the delivery status of every message
- Bot tokens and API keys encrypted with AES-256-GCM; a setup wizard on first run

### In numbers

- **1** HTTP endpoint for events from all your apps
- **0** servers to manage: it deploys to Vercel
- **AES-256** encryption of bot tokens and API keys

- Stack: Next.js 16, TypeScript, Upstash Redis, Telegram Bot API, Vercel, Tailwind CSS
- Code on GitHub: https://github.com/hiddenway/RelayCore

All numbers are from each project’s README on GitHub.

## Need something like this for your business?

Client projects are built by the same people. Write in Telegram or WhatsApp what you need, and we come back with the scope and a fixed price.

- Telegram: https://t.me/danil_khol
- WhatsApp: https://wa.me/995597512189
- Contact page: https://nopeoplelabs.com/contact/