Skip to main content

No project description provided

Project description

Elroy

Discord Documentation PyPI

Elroy is a scriptable, memory augmented AI personal assistant, accessible from the command line. It features:

  • Long-term Memory: Automatic memory recall of past conversations
  • Reminders Track context based and timing based reminders
  • Simple scripting interface: Script Elroy with minimal configuration overhead
  • CLI Tool interface: Quickly review memories Elroy creates for you, or jot quick notes for Elroy to remember.

Reminder demo

Quickstart

The fastest way to get started is using the install script:

curl -LsSf https://raw.githubusercontent.com/elroy-bot/elroy/main/scripts/install.sh | sh

Or install manually with UV:

# Install UV first
curl -LsSf https://astral.sh/uv/install.sh | sh

# Then install Elroy
uv pip install elroy

For detailed installation instructions including Docker and source installation options, see the Installation Guide.

Basic Usage

Once installed locally you can:

# Start the chat interface
elroy chat

# Or just 'elroy' which defaults to chat mode
elroy

# Process a single message and exit
elroy message "Say hello world"

# Force use of a specific tool
elroy message "Create a reminder" --tool create_reminder

# Elroy also accepts stdin
echo "Say hello world" | elroy

Memory and Reminder Tools

Slash commands

Elroy's tools allow it to create and manager memories and reminders. In the background, redundant memories are consolidated.

As reminders or memories become relevant to the conversation, they are recalled into context. A Relevant Context panel makes all information being surfaced to the assistant available to the user.

All commands available to the assisstant are available to the user via / commands.

For a guide of what tools are available and what they do, see: tools guide.

For a full reference of tools and their schemas, see: tools schema reference

Configuration

Elroy is designed to be highly customizable, including CLI appearance and memory consolidation parameters.

For full configuration options, see configuration documentation.

Supported Models

Elroy supports OpenAI, Anthropic, Google (Gemini), and any OpenAI-compatible API's.

Model aliases are available for quick selection:

  • --sonnet: Anthropic's Sonnet model
  • --opus: Anthropic's Opus model
  • --4o: OpenAI's GPT-4o model
  • --4o-mini: OpenAI's GPT-4o-mini model
  • --o1: OpenAI's o1 model
  • --o1-mini: OpenAI's o1-mini model

Scripting Elroy

Remember command

You can script with elroy, using both the CLI package and the Python interface.

Python scripts

Elroy's API interface accepts the same parameters as the CLI. Scripting can be as simple as:

ai = Elroy()

# some other task
ai.remember("This is how the task went")


# Elroy will automatically reference memory against incoming messages
ai.message("Here are memory augmented instructions")

To see a working example using, see release_patch.py

Shell scripting

The chat interface accepts input from stdin, so you can pipe text to Elroy:

# Process a single question
echo "What is 2+2?" | elroy chat

# Create a memory from file content
cat meeting_notes.txt | elroy remember

# Use a specific tool with piped input
echo "Buy groceries" | elroy message --tool create_reminder

Claude Code Integration

Elroy provides skills for Claude Code that expose memory management as slash commands:

  • /remember - Create a long-term memory
  • /recall - Search through memories
  • /list-memories - List all memories
  • /remind - Create a reminder
  • /list-reminders - List active reminders
  • /ingest - Ingest documents into memory

Installation

Install the Claude Code skills using the Elroy CLI:

elroy install-skills

Or use the just command from the repository:

just install-claude-skills

This installs skills to ~/.claude/skills/ making them available in all Claude Code sessions.

Important: Restart your Claude Code session after installation to load the new skills.

To uninstall:

elroy install-skills --uninstall

For detailed usage and examples, see claude-skills/README.md.

Branches

main comes with backwards compatibility and automatic database migrations.

stable is sync'd with the latest release branch.

experimental is a test branch with upcoming changes. These may contain breaking changes and/or changes that do not come with automatic database migrations.

License

Distributed under the Apache 2.0 license. See LICENSE for more information.

Contact

Bug reports and feature requests are welcome via GitHub

Get in touch on Discord or via email

Project details


Download files

Download the file for your platform. If you're not sure which to choose, learn more about installing packages.

Source Distribution

elroy-0.3.0.tar.gz (58.9 MB view details)

Uploaded Source

Built Distribution

If you're not sure about the file name format, learn more about wheel file names.

elroy-0.3.0-py3-none-any.whl (199.1 kB view details)

Uploaded Python 3

File details

Details for the file elroy-0.3.0.tar.gz.

File metadata

  • Download URL: elroy-0.3.0.tar.gz
  • Upload date:
  • Size: 58.9 MB
  • Tags: Source
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/6.2.0 CPython/3.11.14

File hashes

Hashes for elroy-0.3.0.tar.gz
Algorithm Hash digest
SHA256 27862dd28ee3a84f95ed5332900f6bdea17dc5d123fafeb57f091652f880675a
MD5 24c5a4d374eb554e96653050de069a0c
BLAKE2b-256 9c04e203c4a525ad69f78ebc96d72a9c70cd21a5a519460fcbacfc183427bd21

See more details on using hashes here.

File details

Details for the file elroy-0.3.0-py3-none-any.whl.

File metadata

  • Download URL: elroy-0.3.0-py3-none-any.whl
  • Upload date:
  • Size: 199.1 kB
  • Tags: Python 3
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/6.2.0 CPython/3.11.14

File hashes

Hashes for elroy-0.3.0-py3-none-any.whl
Algorithm Hash digest
SHA256 464cc5d7afdd6942504d34ce777a31dcae94a4db9c43f178065abba618f428c7
MD5 a89959d616b1af26d3f72dc01f38363d
BLAKE2b-256 efb77ba276726729f71e49a0838df90174547073f43400536d5eb8690f9429f5

See more details on using hashes here.

Supported by

AWS Cloud computing and Security Sponsor Datadog Monitoring Depot Continuous Integration Fastly CDN Google Download Analytics Pingdom Monitoring Sentry Error logging StatusPage Status page