Open Assistant is an evolving open source artificial intelligence agent able to interact in basic conversation and automate an increasing number of tasks.
Maintained by the Open Assistant working group lead by Andrew Vavrek, this software is an extension of Blather by Jezra, Kaylee by Clayton G. Hobbs, and includes work done by Jonathan Kulp.
Linux (tested ubuntu16.04):
- sudo apt-get install libpulse-dev swig
- pip install pocketsphinx
OR * pip install -r requirements.txt
Windows (tested anaconda, python3.5): * pip install pocketsphinx OR * pip install -r requirements.txt
- aplay - console audio player (on Windows use ffplay from ffmpeg with switch -nodisp -autoexit for console player - https://ffmpeg.org/ffplay.html)
- plaympeg - console mp3 player
- projectm - visualizations responsive to sound
- wmctrl - window manager control. opening, closing, resize, switch windows.
- xdotool - command line x automation tool
- xvkbd - virtual keyboard for x
- Install dependencies and tools.
- Download and unpack the latest
openassistant-master.zip
package. - Edit
run.sh
to configure desired variables, then save. - Make
run.sh
executable with:$chmod +x ./run.sh
- Run
./run.sh -c -H20 -m0 -M mind/boot
. Global variables will be set andrun.py
will launch. - If
$MINDDIR/conf/commands.json
has changed and your machine is online, a new dictionary and language model will be created via the Sphinx Knowledge Base Tool. - Say Launch Open Assistant to enable operating system control commands such as Maximize Window and Fullscreen. Say Launch Stella to initiate a dialogue with her mind. To have Stella quit say Goodbye Stella. Say Close Open Assistant to quit operating system command recognition.
- To change assistant commands and language, edit
conf/commands.json
. Exit and relaunchrun.sh
. - For usage instructions, check out the Open Assistant Wiki.
- For help, you can receive support in the Open Assistant Forum.
- Port Open Assistant to multiple Linux distributions, beginning with Ubuntu
- Enable dynamic voice and instant name changes via spoken commands
- Configure syntax and actions via spoken commands
- Install internal language model translation
- Improve speech recognition and synthesis
- Long-term memory & machine learning
- Web scraping & information analysis
- Establish multiple default 'personalities' and plug-in functions
- Port Open Assistant to all operating systems and devices
- Galactic Exploration!
Join our development working group at: http://www.openassistant.org
Open Assistant fork for Crux System: https://github.com/s1lvino/c9-ports/tree/master/openassistant