Backend engineer with a long PHP/Symfony background and active open-source work in the PHP community — now building self-hosted, privacy-first software in Go.
I ship and operate Svoi, an open-source personal AI assistant, and maintain SD Studio, a local Stable Diffusion + LLM client. Everything I build leans local-first: no cloud lock-in, no subscriptions, full control over your data.
| Layer | Technologies |
|---|---|
| Backend | Go 1.25, PHP 8.x (Symfony), PostgreSQL + pgvector, MySQL, Redis |
| Frontend | Vue 3, TypeScript, JavaScript |
| AI / ML | Local LLMs (Ollama & OpenAI-compatible), RAG & embeddings, Stable Diffusion (Forge / A1111), vision models |
| Additional | Python, Wails v2 (Go desktop), SQLite |
| Infra | Docker, nginx, GitHub Actions, Linux server administration |
A self-hosted, open-source personal AI assistant. Streaming chat with agentic tools, long-term memory, a RAG knowledge base, custom assistants and templates, tasks and reminders, and a proactive scheduler. AGPL-3.0; the operator configures a single LLM provider (local Ollama or any OpenAI-compatible cloud) that serves every user.
- Stack: Go + Vue 3 + PostgreSQL/pgvector, multi-provider LLM chain with failover, SearXNG web search, admin panel, PWA
- Design notes: ARCHITECTURE.md
Desktop companion for Svoi's external knowledge base ("My PC"). It indexes local folders and uploads them as ciphertext over an end-to-end-encrypted blind relay — the server holds no decryption keys.
A privacy-first desktop client for local Stable Diffusion + LLM workflows. All processing happens on-device; nothing leaves the machine.
- LLM prompt engineering — plain-text ideas to ready-to-use SD prompts
- Vision-guided multi-scene generation and smart inpainting
- Design notes: ARCHITECTURE.md
- Building and operating Svoi (svoi-ai.ru) as a production, self-hostable product
- Documenting engineering decisions over raw code output
- Open to Senior PHP / Fullstack roles, with strong interest in Go and AI-infrastructure work
- Prefer remote-friendly, product-focused teams
- Architecture over syntax — document why, not just how.
- AI as a multiplier — LLMs handle boilerplate and research; design, error handling, and UX stay in human hands.
- Local-first and private — build software people can actually run and own.
- Ship, measure, iterate — working software over perfect abstractions.
Open to feedback, bug reports, and architectural discussion.