Skip to main content

Documentation Index

Fetch the complete documentation index at: https://docs.loom.teamecho.ai/llms.txt

Use this file to discover all available pages before exploring further.

​
1. Install from PyPI

pip install loom-memory
This installs Loom and registers the loom CLI command.

​
2. Install from Source (optional)

If you prefer to install from source: 
git clone https://github.com/TeamEcho-AI/Loom.git
cd Loom

# Create and activate a Python 3.10 conda environment
conda create -n loom python=3.10 -y
conda activate loom

# Install dependencies
pip install -r requirements.txt

# Install Loom as a package
pip install -e .
For development mode with testing and linting tools, run pip install -e ".[dev]" instead.

​
3. Initialize & Configure

# Initialize the project (generates config + template files)
loom init
This creates the files Loom needs to run:
FilePurpose
configs/loom.yamlYour config — edit this to set LLM provider, model, etc.
templates/general.jsonBuilt-in general template (editable)
templates/roleplay.jsonBuilt-in roleplay template (editable)
Then configure your LLM provider (pick one):
Open configs/loom.yaml and set api_key, model, base_url:
llm:
  api_key: "your-api-key"
  model: "gpt-4o"
  base_url: "https://api.openai.com/v1"

​
4. Verify installation

These examples run without an API key: 
# Schema operations
python examples/01_basic_schema.py

# Input converters
python examples/03_converters.py

​
5. Run with LLM

Requires a configured API key: 
# Full chat with memory
python examples/02_chat_with_memory.py

# Or start the web server
loom serve
# Open http://localhost:8666

# Or run as a background daemon
loom serve start
loom serve status

​
Next Steps

Python API

Learn how to use Loom programmatically.

CLI Reference

Explore the full command-line interface.

Service Management

Run Loom as a daemon with auto-start on boot.

Schema Templates

Use preset templates or create your own.

Configuration

Customize LLM provider, persistence, and more.