Solutions

Layered from the runtime out.

A local inference server, then the work that sits on it — documents, edge, agents, ops, enterprise. Same thesis on every row: intelligence with a body.

01 · Runtime v0.1.7

LMForge

Run AI Models on Your Own Machine

Download a model and within minutes you have a fast, OpenAI-compatible AI endpoint running entirely on your machine. LMForge detects your GPU, VRAM, and drivers, installs the best inference engine automatically, and keeps your models served by an always-on daemon — closing the app never stops them.

  • Private — nothing leaves your device
  • One-command install, auto engine selection
  • OpenAI + Ollama compatible API
  • Multi-model orchestration
  • Rust
  • Tokio
  • axum
  • SvelteKit
  • Tauri
Open solution →
Runtime

02 · Intelligence In progress

DocIntel

Enterprise Document Intelligence

A 10-component distributed document intelligence system built with Kotlin API gateway, Python Haystack RAG pipeline, and full Docker orchestration. Demonstrates production-grade patterns: hybrid search with RRF fusion, multi-tenant isolation, semantic caching, and LiteLLM provider abstraction.

  • Hybrid Search with RRF Fusion
  • Multi-Tenant Document Isolation
  • Semantic Caching
  • LiteLLM Provider Abstraction
  • Haystack
  • Kotlin
  • Qdrant
  • LiteLLM
  • Docker
Open solution →
Intelligence

03 · Edge In progress

EduMate Lite

On-Device AI Learning Companion

A privacy-first mobile learning companion that runs entirely on-device. Upload documents, ask questions, and get AI-powered answers — all without internet. Demonstrates edge AI architecture with on-device RAG pipeline using Gemma small language model and ObjectBox vector storage.

  • Fully On-Device RAG
  • Gemma Small Language Model
  • ObjectBox Vector Storage
  • Zero Network Dependency
  • Flutter
  • Gemma
  • ObjectBox
  • Dart
Open solution →
Edge

04 · Agents In progress

CodeForge Lite

AI-Powered Local Code Review

An Android-native code review tool that runs entirely on-device. Uses local LLM inference for code quality analysis, security scanning, and documentation suggestions — all without sending your code to external APIs. Built with Kotlin and designed for developers who care about code privacy.

  • On-Device Code Analysis
  • Multi-Language Support
  • Quality & Security
  • Documentation Generation
  • Kotlin
  • Android
  • LLM
  • On-Device AI
Open solution →
Agents
💓

05 · Ops Inception

Pulse

Lightweight Service Health Dashboard

A dead-simple health monitoring tool born from frustration with heavyweight observability stacks. Define your services in a YAML file, deploy the single binary, and get a real-time dashboard with uptime history and Slack/webhook alerts. No agents, no sidecars, no cloud account required. Built in Go for minimal resource footprint — runs happily on a $5 VPS monitoring 50+ services.

  • One YAML Config
  • Single Binary
  • Real-Time Dashboard
  • Uptime History
  • Go
  • HTMX
  • SQLite
  • Docker
Open solution →
Ops

06 · Enterprise In progress

BizSync:Impex

Multi-Tenant Import/Export ERP Platform

A full-stack ERP platform built for import/export merchants. Handles multi-currency invoicing, inventory across warehouses, shipment lifecycle tracking, customs documentation, and multi-geo tax compliance. Multi-tenant architecture with tenant isolation at the database level via MongoDB Atlas. Cross-platform mobile + web via Flutter, with a Spring Boot microservices backend.

  • Multi-Tenant Isolation
  • Multi-Currency Invoicing
  • Shipment Lifecycle
  • Cross-Platform
  • Flutter
  • Spring Boot
  • MongoDB Atlas
  • Kotlin
Open solution →
Enterprise
🧠

Phoenix

Ready when you are

Hey! I'm Phoenix — I know Titas's work, projects, and experience. Ask me anything — from distributed systems to production RAG, or what it's like building at Tesco and VMware.