LIALIA
Únete a la BETA

Política de privacidad

Cómo LIA protege sus datos y respeta su privacidad.

1. Introduction

This privacy policy describes how LIA, an open-source personal AI assistant, collects, uses, and protects your personal data. LIA is developed and operated by an independent developer as an open-source project under the AGPL-3.0 license.

LIA is currently in beta phase and is offered free of charge during this period. The application is accessible at https://lia.jeyswork.com. The complete source code is publicly available, allowing you to audit how your data is processed at any time.

This policy applies to the hosted instance of LIA. If you deploy your own instance (self-hosting), you become the data controller for that instance and this policy does not directly apply. We nevertheless encourage you to use it as a basis for your own compliance.

By using LIA, you acknowledge that you have read and understood this policy. If you do not accept the terms described herein, please do not use the service.

2. Data collected

LIA collects and processes the following categories of data, strictly necessary for the operation of the service:

User account data:

  • Email address (unique identifier)
  • First and last name
  • Password (hashed via bcrypt, never stored in plain text)
  • Language preferences and timezone
  • User role (standard or administrator)

Conversation data:

  • Messages exchanged between you and the assistant
  • Execution plans generated by the planning system
  • Results of actions performed by agents (email search, event creation, etc.)
  • Conversation history, saved as checkpoints in PostgreSQL

Third-party service connection data:

  • OAuth access tokens (Google Workspace, Apple iCloud, Microsoft 365)
  • Refresh tokens for automatic renewal
  • These tokens are encrypted via Fernet (AES-128-CBC symmetric encryption) before storage

Usage data:

  • Anonymized usage metrics (request count, response times)
  • LLM token counters consumed per session
  • Technical error logs (without personally identifiable data)

Data that LIA does NOT collect:

  • Geolocation data
  • Biometric data
  • Browsing data outside of the application
  • Advertising profiles or targeting data

In compliance with the General Data Protection Regulation (GDPR), each data processing activity is based on a specific legal basis:

Processing activityLegal basisJustification
Account creation and managementPerformance of contract (Art. 6.1.b)Necessary to provide the service
Conversations with the assistantPerformance of contract (Art. 6.1.b)Core function of the service
Third-party service connections (Google, Apple, Microsoft)Explicit consent (Art. 6.1.a)You actively choose to connect each service
Sending data to LLM providersPerformance of contract (Art. 6.1.b)Necessary for the assistant to function
Technical logs and metricsLegitimate interest (Art. 6.1.f)Maintaining security and reliability of the service
Language preference cookieConsent (Art. 6.1.a)Storing your language choice

You may withdraw your consent at any time for processing based on consent, without affecting the lawfulness of processing carried out prior to withdrawal.

4. Hosting and data location

Hosted instance infrastructure:

The official LIA instance is self-hosted on a physical server administered by the developer. Data is stored in France.

  • Database: PostgreSQL for persistent storage (accounts, conversations, checkpoints)
  • Cache: Redis for sessions and temporary caching
  • Reverse proxy: Cloudflare Tunnel for secure HTTPS access
  • TLS certificates: Managed automatically by Cloudflare

International data transfers:

When you interact with LIA, certain data is transmitted to LLM providers for natural language processing. These providers may have servers located outside of the European Union (notably in the United States and China). See the "LLM Providers" section for details.

Connections to Google Workspace, Apple iCloud, and Microsoft 365 also involve exchanges with these providers' servers, subject to their own privacy policies.

5. Data security

LIA implements a multi-layered security architecture designed to protect your data at every stage:

BFF (Backend-for-Frontend) architecture: The BFF architecture ensures that authentication tokens and third-party service credentials never transit through the browser. All sensitive operations are performed server-side.

Encryption of sensitive data:

  • OAuth tokens (Google, Apple, Microsoft) are encrypted with Fernet (AES-128-CBC + HMAC SHA256) before database storage
  • Passwords are hashed with bcrypt (adaptive cost factor)
  • All communications are encrypted in transit via TLS 1.2+

PII (Personally Identifiable Information) filtering: Before sending data to LLM providers, LIA applies PII filtering that reduces personally identifiable information transmitted. This mechanism minimizes the exposure of your sensitive data to third-party services.

Sessions and authentication:

  • User sessions are stored in Redis with automatic expiration
  • Authentication relies on secure cookies (HttpOnly, Secure, SameSite)
  • No authentication tokens are exposed to client-side JavaScript

Secure logging: Technical logs use structured JSON format (via structlog) and are configured to exclude personally identifiable data.

6. LLM providers

LIA uses multiple Large Language Model (LLM) providers to process your requests. The choice of provider depends on your instance configuration and the type of task:

ProviderHeadquartersUsage in LIA
OpenAIUnited StatesGPT models for conversation and planning
AnthropicUnited StatesClaude models for conversation and analysis
Google (Gemini)United StatesGemini models for multimodal processing
DeepSeekChinaAdvanced reasoning models
Qwen (Alibaba)ChinaLanguage processing models
PerplexityUnited StatesAugmented web search
OllamaLocalModels executed locally (no external transfer)

What is transmitted to LLM providers:

  • The content of your messages (after PII filtering)
  • Conversational context necessary for response coherence
  • Tool results (email summaries, event details, etc.)

What is NOT transmitted:

  • Your OAuth tokens or passwords
  • Your account identifiers
  • Unfiltered raw data from your connected services

Provider commitments: Major providers (OpenAI, Anthropic, Google) contractually commit to not using API data to train their models. We encourage you to review their respective policies for further details.

When Ollama is configured, requests are processed locally and no data leaves your infrastructure.

7. Data retention

Retention periods are defined based on the nature of the data:

Data typeRetention periodJustification
User accountUntil account deletionPerformance of contract
Conversation historyUntil deletion by user or account deletionService continuity
Encrypted OAuth tokensUntil service disconnection or account deletionAccess to connected services
Redis sessionsAutomatic expiration (24h of inactivity)Security
Technical logsRolling 30 daysDiagnostics and security
Usage metricsRolling 90 days (anonymized)Service improvement

Account deletion: When you request account deletion, all your personal data is irreversibly deleted, including: user profile, conversations, checkpoints, encrypted OAuth tokens, and preferences. This deletion is effective within a maximum of 30 days.

8. Your rights

Under the GDPR, you have the following rights:

  • Right of access (Art. 15): Obtain a copy of all personal data we hold about you.
  • Right to rectification (Art. 16): Correct inaccurate or incomplete personal data.
  • Right to erasure (Art. 17): Request the deletion of your personal data ("right to be forgotten").
  • Right to restriction (Art. 18): Request restriction of processing of your data in certain circumstances.
  • Right to data portability (Art. 20): Receive your data in a structured, commonly used, and machine-readable format.
  • Right to object (Art. 21): Object to the processing of your data based on legitimate interest.
  • Right to withdraw consent: At any time, without affecting the lawfulness of processing carried out prior to withdrawal.

To exercise these rights, contact us at the address indicated in the Contact section. We will respond within 30 days in accordance with the GDPR.

If you believe your rights are not being respected, you have the right to lodge a complaint with the CNIL (Commission Nationale de l'Informatique et des Libertes) or any other competent supervisory authority.

9. Cookies

LIA uses a minimal number of cookies, exclusively functional:

CookiePurposeDurationType
NEXT_LOCALEStores your language preference (fr, en, de, es, it, zh)1 yearFunctional
Session cookieMaintains your authentication sessionSession durationStrictly necessary

What LIA does NOT use:

  • No tracking cookies
  • No advertising cookies
  • No third-party analytics cookies (Google Analytics, etc.)
  • No tracking pixels
  • No browser fingerprinting

The cookies used by LIA are either strictly necessary for the operation of the service or relate to your explicit choice (language preference). In accordance with the ePrivacy Directive, strictly necessary cookies do not require prior consent.

10. Contact

For any questions regarding the protection of your personal data, the exercise of your rights, or this policy, you may contact us:

Data controller: LIA is operated by an independent developer acting as data controller within the meaning of the GDPR.

Changes to this policy: This policy may be updated to reflect changes in the service or applicable regulations. In the event of a substantial modification, you will be notified through the application. The update date at the top of this document prevails. We encourage you to review this policy regularly.

Open-source transparency: As an open-source project, LIA allows you to audit the source code at any time to verify exactly what data is collected, how it is processed, and where it is sent. This radical transparency is a fundamental commitment of the project.