LIA-Assistant

<p align="center">
  <img src="docs/assets/logo.png" alt="LIA — Your life. Your AI. Your rules." width="600" />
</p>

<h1 align="center">LIA</h1>

<p align="center">
  <strong>Intelligent multi-agent conversational assistant with LangGraph orchestration, Human-in-the-Loop, enterprise-grade observability, and full i18n support (6 languages)</strong>
</p>

<p align="center">
  <a href="https://lia.jeyswork.com/"><img src="https://img.shields.io/badge/🚀_Try_LIA-lia.jeyswork.com-0EA5E9?style=for-the-badge" alt="Try LIA"></a>
  &nbsp;&nbsp;
  <a href="https://github.com/jgouviergmail/LIA-Assistant/stargazers"><img src="https://img.shields.io/github/stars/jgouviergmail/LIA-Assistant?style=for-the-badge&logo=github&label=Star&color=gold" alt="GitHub Stars"></a>
</p>

<p align="center">
  <a href="https://www.python.org/"><img src="https://img.shields.io/badge/Python-3.12%2B-3776AB?style=flat-square&logo=python&logoColor=white" alt="Python 3.12+"></a>
  <a href="https://nodejs.org/"><img src="https://img.shields.io/badge/Node.js-22%20LTS-5FA04E?style=flat-square&logo=nodedotjs&logoColor=white" alt="Node.js 22 LTS"></a>
  <a href="https://fastapi.tiangolo.com/"><img src="https://img.shields.io/badge/FastAPI-0.135.1-009688?style=flat-square&logo=fastapi&logoColor=white" alt="FastAPI"></a>
  <a href="https://nextjs.org/"><img src="https://img.shields.io/badge/Next.js-16-000000?style=flat-square&logo=nextdotjs&logoColor=white" alt="Next.js 16"></a>
  <a href="https://langchain-ai.github.io/langgraph/"><img src="https://img.shields.io/badge/LangGraph-1.1.2-FF6F00?style=flat-square" alt="LangGraph"></a>
  <a href="https://python.langchain.com/"><img src="https://img.shields.io/badge/LangChain-1.2.12-4B8BBE?style=flat-square" alt="LangChain"></a>
  <a href="#internationalization-i18n--6-languages"><img src="https://img.shields.io/badge/i18n-6%20languages-E040FB?style=flat-square" alt="6 languages"></a>
  <a href="#license"><img src="https://img.shields.io/badge/License-AGPL--3.0-blue?style=flat-square" alt="License"></a>
  <a href="https://deepwiki.com/jgouviergmail/LIA-Assistant"><img src="https://deepwiki.com/badge.svg" alt="Ask DeepWiki"></a>
</p>

<p align="center">
  <a href="#features">Features</a> •
  <a href="#administration--monitoring">Admin & Monitoring</a> •
  <a href="#quick-start">Quick Start</a> •
  <a href="#architecture">Architecture</a> •
  <a href="#documentation">Documentation</a> •
  <a href="#contributing">Contributing</a>
</p>

<p align="center">
  <strong>Version 1.13.10</strong> — Calendar-to-routes timezone fix, datetime.utcnow() eradication — April 2026
</p>

---

## Table of Contents

- [Why LIA?](#why-lia)
- [Try LIA Online](#try-lia-online)
- [Screenshots](#screenshots)
- [Features](#features)
- [Administration & Monitoring](#administration--monitoring)
- [Quick Start](#quick-start)
- [Architecture](#architecture)
- [Technologies](#technologies)
- [Documentation](#documentation)
- [Tests](#tests)
- [CI/CD](#cicd)
- [Performance](#performance)
- [Security](#security)
- [Contributing](#contributing)
- [Support](#support)
- [License](#license)
- [Acknowledgments](#acknowledgments)

---

## Why LIA?

**LIA** solves the fundamental problems of today's AI assistants:

| Problem | LIA Solution |
|---------|---------------------|
| **Unpredictable LLM costs** | Real-time token tracking, budget alerts, 93% optimization |
| **Uncontrolled hallucinations** | Human-in-the-Loop (HITL) with 6 approval levels |
| **Fragmented integrations** | Unified multi-domain orchestration (18 agents + MCP + sub-agents) |
| **Limited observability** | 500+ Prometheus metrics, 18 Grafana dashboards, GeoIP analytics |
| **Inconsistent performance** | OpenAI text-embedding-3-small embeddings, semantic routing with max-pooling |

### Primary Use Cases

```
📅 "Find my meetings for tomorrow and send a reminder to all participants"
📧 "Summarize my unread emails from this week that have attachments"
👥 "Update the companies of my contacts who work at startups"
🔔 "Remind me tomorrow at 9am to call Marie for her birthday"
```

---

## Try LIA Online

<p align="center">
  <a href="https://lia.jeyswork.com/"><img src="https://img.shields.io/badge/🚀_Try_LIA-lia.jeyswork.com-0EA5E9?style=for-the-badge" alt="Try LIA"></a>
</p>

LIA is available as a hosted service at **https://lia.jeyswork.com/** — no installation required.

> **Closed beta**: Access is currently limited to a restricted number of users, at the administrator's discretion. To request an invitation, contact **liamyassistant@gmail.com**.

---

## Screenshots

<p align="center">
  <img src="docs/assets/screenshot-homepage.png" alt="Dashboard — Homepage with usage statistics" width="800" />
  <br /><em>Dashboard — Homepage with quick access, usage statistics, and personalized greeting</em>
</p>

<p align="center">
  <img src="docs/assets/screenshot-chat.png" alt="Chat — Multi-agent conversation with debug panel" width="800" />
  <br /><em>Chat — Multi-agent conversation with real-time debug panel (right sidebar)</em>
</p>

<details>
<summary><strong>More screenshots</strong></summary>

<p align="center">
  <img src="docs/assets/screenshot-settings-preferences.png" alt="Settings — Preferences (connectors, MCP, themes)" width="800" />
  <br /><em>Settings — Preferences: connectors, MCP servers, language, timezone, and themes</em>
</p>

<p align="center">
  <img src="docs/assets/screenshot-settings-features.png" alt="Settings — Features (memory, interests, notifications)" width="800" />
  <br /><em>Settings — Features: LIA Style, long-term memory, interests, proactive notifications, scheduled actions, sub-agents, channels</em>
</p>

<p align="center">
  <img src="docs/assets/screenshot-settings-administration.png" alt="Settings — Administration panel" width="800" />
  <br /><em>Settings — Administration: LLM config, RAG Spaces, users, connectors, pricing, skills, voice, broadcast, debug</em>
</p>

<p align="center">
  <img src="docs/assets/screenshot-settings-administration-oneclick.png" alt="Settings — One-click administration" width="800" />
  <br /><em>Administration — One-click simplicity: every admin action is accessible in a single click, no technical skills required</em>
</p>

<p align="center">
  <img src="docs/assets/screenshot-settings-administration-llm.png" alt="Settings — LLM Configuration with multi-provider support" width="800" />
  <br /><em>Administration — LLM Configuration: 7 providers (OpenAI, Anthropic, DeepSeek, Qwen, Perplexity, Ollama, Gemini), per-node model selection</em>
</p>

<p align="center">
  <img src="docs/assets/screenshot-faq.png" alt="FAQ — Searchable help center" width="800" />
  <br /><em>FAQ — Searchable help center with categorized Q&A sections</em>
</p>

</details>

---

## Features

### Multi-Agent Intelligence (LangGraph 1.x)

- **19+ Specialized Agents**: Contacts, Emails, Calendar, Drive, Tasks, Reminders, Places, Routes, Weather, Wikipedia, Perplexity, Brave, Web Search, Web Fetch, Browser Control (with progressive screenshot streaming), Smart Home (Philips Hue), Context, Query + dynamic MCP agents
- **MCP (Model Context Protocol)**: Per-user external tool servers with OAuth 2.1, SSRF protection, structured items parsing, MCP Apps (interactive iframe widgets), **Iterative Mode (ReAct)** for complex servers — a dedicated agent reads docs then calls tools correctly
- **Agent Initiative Phase**: Post-execution cross-domain enrichment — the assistant proactively verifies related information (e.g., weather shows rain → checks calendar for outdoor events). Prompt-driven, read-only, fully configurable
- **Skills (agentskills.io)**: Open standard for expert instructions (SKILL.md), model-driven activation, progressive disclosure (L1/L2/L3), sandboxed scripts, marketplace import, auto-translated multi-language descriptions, ZIP download, admin management. **Planner skill guard**: multi-domain deterministic skills are protected from false-positive early clarification requests v

[truncated…]