| Availability |
Odoo Online
Odoo.sh
On Premise
|
| Odoo Apps Dependencies |
Discuss (mail)
|
| Community Apps Dependencies | Show |
| Lines of code | 9400 |
| Technical Name |
llm_letta |
| License | LGPL-3 |
| Website | https://github.com/apexive/odoo-llm |
| Availability |
Odoo Online
Odoo.sh
On Premise
|
| Odoo Apps Dependencies |
Discuss (mail)
|
| Community Apps Dependencies | Show |
| Lines of code | 9400 |
| Technical Name |
llm_letta |
| License | LGPL-3 |
| Website | https://github.com/apexive/odoo-llm |
Letta LLM Integration
Enterprise-ready integration bringing stateful AI agents with persistent memory to your Odoo workflows.
Transform your AI interactions with Letta's stateful agents that remember context, maintain conversation history, and execute Odoo tools through MCP.
Overview
The Letta LLM Integration brings advanced AI agent capabilities to Odoo, enabling stateful conversations with persistent memory. Unlike traditional stateless chatbots, Letta agents remember your interactions and maintain context across sessions.
What Makes Letta Different
- Persistent Memory - Agents remember past conversations and maintain context indefinitely
- Stateful Architecture - Each thread gets its own dedicated agent with isolated memory
- MCP Tool Integration - Full access to Odoo tools through Model Context Protocol
- Automatic Lifecycle - Agents are created, updated, and managed automatically with threads
- Flexible Deployment - Support for both Letta Cloud and self-hosted servers
Key Features
Agent-Based Conversations
Each thread gets its own Letta agent with dedicated memory and personality, creating truly personalized AI interactions.
Persistent Memory System
Agents maintain conversation history and context across sessions, building long-term relationships with users.
MCP Tool Access
Seamless integration with Odoo's MCP server gives agents access to all your configured tools and actions.
Automatic Agent Management
Agents are created, updated, and cleaned up automatically as you manage threads - no manual intervention needed.
Streaming Responses
Real-time message streaming with support for tool calls, reasoning steps, and assistant responses.
Cloud & Self-Hosted
Deploy on Letta Cloud for instant setup or self-host with Docker for complete control over your data.
Getting Started
Quick Setup with Docker
- Create Letta database in PostgreSQL
- Configure
.env.lettawith your settings - Run:
docker compose up letta_server -d - Server available at
http://localhost:8283
View Full Docker Setup Guide →
Cloud Setup
- Sign up at cloud.letta.com
- Get your API token from settings
- Configure Letta (Cloud) provider in Odoo
- Start creating threads with AI agents!
No infrastructure setup required - perfect for getting started quickly.
How It Works
1. Thread Creation
When you create a thread with Letta provider, an agent is automatically created with configured memory, tools, and personality.
2. Conversation
Messages are sent to the agent which maintains full conversation history and can execute Odoo tools through MCP.
3. Memory Persistence
All interactions are stored in the agent's memory, allowing it to recall past conversations and build on previous context.
Required & Recommended Modules
The Letta Integration works best with these complementary modules:
LLM MCP Server Required
Exposes Odoo tools to Letta agents through the Model Context Protocol. This module is essential for tool execution capabilities.
LLM Assistant
Define specialized AI assistants with custom prompts that become agent personalities in Letta, creating purpose-built AI helpers.
LLM Tool
Create custom tools that Letta agents can execute, extending their capabilities to interact with any part of your Odoo system.
Easy AI Chat
User-friendly chat interface that works seamlessly with Letta agents, providing a complete conversational AI experience.
Support & Resources
Documentation
Find detailed setup guides, API documentation, and integration examples in our GitHub repository.
View DocumentationLetta Resources
Learn more about Letta's architecture, capabilities, and deployment options.
Letta Docs Letta GitHub
Please log in to comment on this module