Skip to content

lsegal/aviary

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

704 Commits
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 

Aviary: the AI Agent Nest

Aviary logo

Release Tests License

Aviary is a full AI assistant platform. Connect your AI models to Slack, Signal, Discord, and more. Have conversations, set up scheduled tasks, and let your agents work for you, all managed from a CLI or a web-based control panel.

Website | Docs: Getting Started · Configuration · CLI Reference · MCP Tools


Install

macOS / Linux

Homebrew

brew tap lsegal/aviary https://github.com/lsegal/aviary
brew install aviary

This tap works with Homebrew on macOS and Linux.

Manual (cURL)

curl -fsSL https://aviary.bot/install.sh | sh

The install script downloads the latest release binary to ~/.local/bin/ and adds it to your PATH.

Windows

Scoop

scoop bucket add aviary https://github.com/lsegal/aviary
scoop install aviary/aviary

Scoop installs Aviary into Scoop's managed package directory and shims aviary.exe onto your PATH.

Manual (PowerShell)

iwr https://aviary.bot/install.ps1 | iex

The install script downloads the latest release binary to ~/.local/bin/ and adds it to your PATH.

Docker

mkdir -p ~/.config/aviary
docker run --rm -it \
  -p 16677:16677 \
  -p 1455:1455 \
  -p 45289:45289 \
  -v ~/.config/aviary:/home/bot/.config/aviary \
  ghcr.io/lsegal/aviary:latest

The image runs aviary serve by default. With the bind mount above, Aviary stores its config, TLS certs, and login token in your host ~/.config/aviary/ directory.

The Docker image also includes a working Chrome/Chromium browser, so browser tasks run in headless mode out of the box without extra setup.

Tip: -p 1455:1455 is only needed for OpenAI Codex OAuth, and -p 45289:45289 is only needed for Gemini OAuth. If you are using API keys or other providers, you can omit those extra port mappings.

Binary Release

Download the latest release for your platform from the Releases page, place the binary in your $PATH, and make it executable.

Go Install

go install github.com/lsegal/aviary/cmd/aviary@latest

Quick Start

# Start the server
aviary serve

# Set up a provider credential and create your first agent
aviary configure

# Chat with an agent
aviary agent run assistant "Hello!"

Open the web control panel at https://localhost:16677 and log in with the token from ~/.config/aviary/token.

Using Docker, run one-off CLI commands against the same mounted config directory by overriding the container command:

docker run --rm -it \
  -v ~/.config/aviary:/home/bot/.config/aviary \
  ghcr.io/lsegal/aviary:latest \
  aviary configure

For a full walkthrough see the Getting Started guide.


Documentation

Getting Started Install, first agent, first chat
Configuration aviary.yaml walkthrough — providers, agents, channels, tasks
Scheduled Tasks Cron and file-watch tasks
Control Panel Web UI overview
CLI Reference All commands and flags
Config Reference Full aviary.yaml schema
MCP Tools All available MCP tools

Contributing

See CONTRIBUTING.md.

About

Aviary is a full AI assistant platform. Connect your AI models to Slack, Signal, Discord, etc., have conversations, set up scheduled tasks, and let your agents work for you.

Topics

Resources

License

Code of conduct

Contributing

Stars

Watchers

Forks

Sponsor this project

  •  

Packages

 
 
 

Contributors