S.I.R.I.U.S. (Smart Intelligent Responsive Interface for Universal Support)

Privacy & local, AI assistant that automates tasks, email, and workflows across tools. Stable Node.js + Ollama today; Next‑Gen TypeScript + Mistral + n8n (EU‑compliant) in progress.
Tech Stack: Node.js TypeScript Express WebSocket React Native Chrome Extension Ollama Mistral n8n Pinecone Notion API Asana API Google Workspace Jira Trello
Source Code

Summary

S.I.R.I.U.S. Exists in two states, as its original version, which is essentially an orchestrator that connects productivity apps. this is done by calling apis through a Restful design. In it’s second state which you find when you review the project is it’s newer version. This second version can be more akin to that of a research project, in both the capabilties of AI - agents/assisted coding. Therefore when you look at the source code AI is heavily used, the main goal was to test the limits of training my own model on a “small scope” using supervised learning.

Challenges Addressed

  • Privacy: Keeping AI inference and user data strictly local by default for privacy and sovereignty
  • Tool fragmentation: Unifying fragmented productivity tools like Notion, Asana, Google Workspace, Jira, and Trello / is to be resolved with n8n to reduce overhead.
  • Resilience: Ensuring resilience and offline functionality to avoid reliance on centralized cloud services

Core Capabilities

  • Automation & integrations: End-to-end automation and integrations across popular productivity platforms and n8n workflow engine.
  • Local-first AI Local inference with optional vector memory using Pinecone
  • Learning: Advanced learning features including circadian rhythm analysis and pattern recognition
  • Multi-interface: Multi-platform support via web, React Native app, and browser extension interfaces

Architecture (high level)

  • Current (stable)
    • Runtime: Node.js services, WebSocket real‑time events, workers for heavy tasks
    • AI: Ollama local inference; Matryoshka quantization optimization
    • Data: Local JSON memory; optional Pinecone for vector recall
    • Clients: Web UI, React Native app, browser extension (does not currently work as a browser extension)
    • Integrations: Modular services (Notion/Asana/Google/Jira/Trello/n8n)
  • Next (TypeScript rewrite)
    • TypeScript + stricter types, maintainable modules
    • AI: Mistral (EU‑centric) for chat/embeddings
    • Automations: n8n workflows + webhook processing (200+ integrations)
    • Focus: EU compliance, observability, testability,
    • Goal: The rewrite consitutes that i will be training it semi supervised without AI, the typescript version will be smaller in scope and more focused on actually solving what i set out to do with this project.

Role & Contributions

  • Sole proprietor
  • Led system architecture and integration strategy
  • Built service adapters, real‑time messaging, memory layer, and workers
  • Implemented (Ollama) and EU‑aligned model path (Mistral) in Next
  • Authored developer docs, onboarding scripts, and comprehensive tests

Outcomes

  • Private: No external data sharing; offline operation
  • Reduced context switching via unified command and integration layer
  • Extensible: Clear adapter contracts; easy to add services/workflows
  • Next‑gen: Type-safe TS codebase + n8n expands integrations to 200+ with minimal glue(if the n8n integration is possible)

Accessibility & UX

  • Accessibility-first (ARIA), responsive/adaptive design, minimalistic UI, classic modular structure, cross‑browser support

Status

  • Shipping: Local-first Node.js + Ollama, core integrations, tests
  • In progress: sirius-next TypeScript rewrite with Mistral + n8n, circadian/productivity analytics APIs