diff --git a/index.html b/index.html index 99294f3..015b751 100644 --- a/index.html +++ b/index.html @@ -21,72 +21,72 @@

CipherDolls — AI companion platform

-

An AI companion platform spanning cloud, web, and physical IoT devices.

- github.com/cipherdolls ↗ +

What if an AI companion wasn't just an app, but something physical in your room? CipherDolls is my biggest project: an AI companion platform where characters can talk, listen — and live inside real devices.

+ github.com/cipherdolls ↗

core

-

Backend API for the CipherDolls platform: wallet-signature auth, AI chat completions, TTS/STT, embeddings (pgvector), USDC payments on Base, and IoT device management over MQTT.

+

The brain of the platform: one backend that handles chat, voice, memory, payments and the connection to the physical dolls.

  • Bun
  • Elysia
  • Prisma
  • PostgreSQL
  • Redis
  • MQTT
- View on GitHub ↗ + View on GitHub ↗

server

-

Minimal chat backend derived from core, stripped to the essentials: chat with a Character, optional TTS/STT — same architecture, no payments or IoT.

+

A slimmed-down core for anyone who just wants to chat with a character — the same architecture, none of the complexity.

  • Bun
  • Elysia
  • Prisma
  • PostgreSQL
- View on GitHub ↗ + View on GitHub ↗

stream-player

-

TTS audio streaming proxy — subscribes to Redis Pub/Sub and forwards audio chunks to WebSocket clients with a compact binary protocol.

+

Voices need to arrive instantly. This streams the AI's speech to your browser the moment it is generated.

  • TypeScript
  • Redis
  • WebSocket
- View on GitHub ↗ + View on GitHub ↗

stream-recorder

-

WebSocket audio ingestion microservice — accepts raw WAV streams, converts to MP3 in-memory via ffmpeg, forwards to the backend.

+

The listening half: your voice streams in, gets converted on the fly, and lands with the AI.

  • TypeScript
  • WebSocket
  • ffmpeg
- View on GitHub ↗ + View on GitHub ↗

firmware-watcher

-

ESP-IDF firmware for the SenseCAP Watcher companion device: BLE WiFi provisioning, MQTT events, MP3 playback through the onboard codec, LVGL UI on a 412×412 display, deep sleep.

+

The magic moment: a real device on your desk wakes up, connects, and speaks with the character's voice.

  • C
  • ESP-IDF
  • ESP32-S3
  • LVGL
- View on GitHub ↗ + View on GitHub ↗

firmware-m5sticks3

-

ESP-IDF firmware for the M5StickS3 (ESP32-S3) pocket companion device with display, audio codec, and IMU.

+

The pocket version: the same companion on a tiny stick with a display and a microphone.

  • C
  • ESP-IDF
  • ESP32-S3
- View on GitHub ↗ + View on GitHub ↗
@@ -96,62 +96,62 @@

Decentralized apps — Gnosis Chain + Ethereum Swarm

-

dApps with on-chain logic and censorship-resistant Swarm storage/hosting.

+

Can the web run without servers? These apps are my experiments in building things that nobody can switch off.

SwarmChat

-

Decentralized 1:1 messenger and WebRTC video calling: wallet identity, on-chain contact registry, encrypted messages over Swarm PSS with feeds as offline outbox. Live at swarmchat.eth.

+

I was thinking about how cool it would be to have a web3-based chat system. Is it possible to communicate without any servers? With Swarm, a decentralised technology, this is now possible — messages travel encrypted through the network itself, and your wallet is your identity.

  • Solidity
  • React
  • Swarm PSS
  • WebRTC
- View on GitHub ↗ + View on GitHub ↗

Pink Chainsaw

-

Decentralized imageboard: post images, comment, and vote with xBZZ; fees auto-top-up the poster's Swarm postage stamp so good content stays alive. A social-score system prices posting by reputation.

+

I wanted an imageboard where content can't just disappear. Images live on Swarm, and every post pays a little to keep them alive — good content earns you cheaper posting, bad content gets expensive.

  • Solidity
  • Foundry
  • React
  • Swarm
- View on GitHub ↗ + View on GitHub ↗

FreeeMarket

-

Multi-vendor marketplace where anyone runs their own shop and gets paid in stablecoins through on-chain escrow — deliberately fee-free and VAT-free.

+

Can you run a marketplace with no company behind it? Anyone opens a shop, buyers pay in stablecoins, and on-chain escrow replaces the middleman. Deliberately fee-free — a farmers' market for the internet.

  • Solidity
  • Gnosis Chain
  • Swarm
- View on GitHub ↗ + View on GitHub ↗

WalletMatrix

-

Pivot-table view of a crypto wallet across every EVM chain — tokens as rows, chains as columns; drag one cell onto another to bridge or cross-chain swap. Static SPA deployable to Swarm.

+

My tokens were scattered across a dozen chains and I could never see the whole picture. So I built a pivot table for your wallet: tokens as rows, chains as columns — drag a cell from one chain to another to bridge.

  • React
  • TypeScript
  • Vite
- View on GitHub ↗ + View on GitHub ↗

swarm-connect

-

React connect-button + wizard for Swarm on Gnosis: wallet → network → balances → Bee node → postage stamp, in one modal. Published on npm; demo hosted on Swarm itself.

+

Every Swarm dApp I built needed the same onboarding dance: wallet, network, Bee node, postage stamp. So I packaged it once — a single React button that walks users through all of it.

  • React
  • wagmi
  • npm package
- View on GitHub ↗ + View on GitHub ↗
@@ -161,35 +161,35 @@

AI on GPU — self-hosted speech services

-

Dockerized speech AI for NVIDIA GPUs, tuned for the RTX 5090 / Blackwell generation.

+

I wanted my projects to hear and speak without sending a single word to the cloud — so these run on my own GPU.

whisper-cuda

-

OpenAI-Whisper-compatible ASR web service built for RTX 5090 (sm_120) — faster-whisper on CTranslate2/CUDA 12.8, no PyTorch.

+

Speech-to-text on my own GPU: no cloud, no per-minute pricing. Whisper packaged for the RTX 5090 so anything in my homelab can transcribe audio locally.

  • Python
  • FastAPI
  • CUDA
- View on GitHub ↗ + View on GitHub ↗

kokoro-cuda

-

Minimal Kokoro TTS API with CUDA: 49 voices in 9 languages, streaming WAV/PCM plus MP3/Opus/FLAC, web UI included.

+

Giving my projects a voice: a small self-hosted TTS service with 49 voices in 9 languages, fast enough to stream. Type text, hear it instantly.

  • Python
  • FastAPI
  • CUDA
- View on GitHub ↗ + View on GitHub ↗

voxtral-cuda

-

Text-to-speech service running Mistral's Voxtral-4B-TTS with CUDA acceleration via vLLM-Omni.

+

The newest open speech models are amazing but heavy. This runs Mistral's Voxtral on a local GPU, so state-of-the-art speech stays in my own house.

  • Python
  • vLLM
  • CUDA
- View on GitHub ↗ + View on GitHub ↗
@@ -204,11 +204,11 @@

stakingtracker

-

Self-hosted ETH staking rewards tracker and tax-report generator — reads from your own beacon node, persists daily history to SQLite, no external APIs or keys.

+

Tax season with an ETH validator used to mean paid APIs and spreadsheets. Now my own beacon node does the work: a small self-hosted app that records rewards daily and prints the tax report.

  • TypeScript
  • Fastify
  • SQLite
- View on GitHub ↗ + View on GitHub ↗
@@ -219,8 +219,8 @@