AI Chat
ChatGPT-style interface backed by your local Ollama models or Gemini. Full conversation history, smart prompts, and file attachments.
Open Chat →
Chat with local LLMs, manage project memory, track live transit,
and automate your devices — all from one self-hosted platform.
Platform capabilities
What's inside
Six core modules, all running on your hardware. No subscriptions, no data leaks.
ChatGPT-style interface backed by your local Ollama models or Gemini. Full conversation history, smart prompts, and file attachments.
Open Chat →Portable project memory that persists across devices. Save structured context, launch briefed chats, and reuse template packs instantly.
Open Memory Core →Real-time Malaysia GTFS transit data. Live vehicle positions on an interactive map, route planning, and nearby stop detection.
Open Transit Live →Deploy lightweight daemon agents on your desktop machines. Get status reports, trigger automation, and monitor running processes remotely.
Open Chat →Browser-based panel for remote device management. Send commands, capture screenshots, and manage files on connected machines.
Open Control Panel →Full Telegram bot integration. Receive messages, trigger commands, get AI responses and system reports directly in your Telegram app.
Open Chat →Quick access
Three core apps — each fully responsive and installable on your phone.
Chat with local AI, send prompts, view reports and agent results in one thread.
/appManage, save and launch portable project memories. Export MEMORYCORE.md bundles.
/memorycoreReal-time vehicle positions, nearby routes, and GTFS route planning for Malaysia.
/transit-liveUnder the hood
A fully self-hosted stack with zero mandatory cloud dependency. Your data stays on your hardware — LLM inference, database, background workers and all.
High-performance Python API server with SQLAlchemy + SQLite persistence and Celery task queue.
Local LLM inference via Ollama (any model) with Gemini as a cloud fallback option.
Distributed background job queue for reports, screenshots, and long-running tasks.
Service worker with app shell caching. Installs on iOS Safari, Android Chrome, and desktop browsers.
Vanilla HTML/CSS/JS · Service Worker · Offline Shell
REST endpoints · SQLAlchemy · SQLite · Celery Workers
Local inference · Vision models · Multi-model switching
Redis · n8n Workflows · Self-hosted on VPS or local
Agent downloads
When the latest build files are present on the VPS, these buttons download the actual installer packages immediately.
One-click Windows installer for screenshots, shell tasks, VS Code actions, and continuous heartbeats back to FitClaw.
Download Windows `.exe`Install the Android agent companion directly from your VPS so phones and tablets can register, heartbeat, and stay connected.
Download Android `.apk`Install as app
Works as a native-feeling app on iOS Safari, Android Chrome, and desktop browsers. One tap — it appears in your launcher like any other app.
Open /app in your browser
Tap Share → Add to Home Screen on iOS, or the install icon on Chrome
FitClaw appears in your launcher and works offline