Fully local voice assistant inspired by J.A.R.V.I.S.
Project description
my-own-jarvis
Fully local voice assistant inspired by J.A.R.V.I.S.
- GitHub: https://github.com/lusparkl/local_ai_assistant_jarvis
- Full release guide: https://github.com/lusparkl/local_ai_assistant_jarvis/blob/main/README_RELEASE.md
- Issues: https://github.com/lusparkl/local_ai_assistant_jarvis/issues
Requirements
- Windows 10/11
- Python
>=3.11and<3.14(Python3.12recommended) pipxinPATH- Microphone + speakers/headphones
- Ollama runtime/CLI in
PATH(https://ollama.com/download)
Install
CPU/default:
pipx install my-own-jarvis --python 3.12
CUDA 12.6:
pipx install my-own-jarvis --python 3.12 --pip-args "--extra-index-url https://download.pytorch.org/whl/cu126"
First run
ollama pull qwen3:8b
jarvis setup
jarvis doctor
jarvis run
jarvis start is available as an alias for jarvis run.
Update
pipx upgrade my-own-jarvis
jarvis doctor
Uninstall
pipx uninstall my-own-jarvis
Download files
Download the file for your platform. If you're not sure which to choose, learn more about installing packages.
Source Distribution
my_own_jarvis-0.1.3.tar.gz
(9.3 MB
view details)
Built Distribution
Filter files by name, interpreter, ABI, and platform.
If you're not sure about the file name format, learn more about wheel file names.
Copy a direct link to the current filters
File details
Details for the file my_own_jarvis-0.1.3.tar.gz.
File metadata
- Download URL: my_own_jarvis-0.1.3.tar.gz
- Upload date:
- Size: 9.3 MB
- Tags: Source
- Uploaded using Trusted Publishing? No
- Uploaded via: twine/6.2.0 CPython/3.11.4
File hashes
| Algorithm | Hash digest | |
|---|---|---|
| SHA256 |
20fd4ce49eb07ac838f46e57d99b06b8db91fbc6ecff4d31d8cc056de63d8ee1
|
|
| MD5 |
1f9cd37a6cdae285453febf31786a4ad
|
|
| BLAKE2b-256 |
ac42160ac37a795a8485ef8052b4b83022f870696380484b06d769652dd0fdd5
|
File details
Details for the file my_own_jarvis-0.1.3-py3-none-any.whl.
File metadata
- Download URL: my_own_jarvis-0.1.3-py3-none-any.whl
- Upload date:
- Size: 9.3 MB
- Tags: Python 3
- Uploaded using Trusted Publishing? No
- Uploaded via: twine/6.2.0 CPython/3.11.4
File hashes
| Algorithm | Hash digest | |
|---|---|---|
| SHA256 |
964fcf99db1f2a99f4aae4f383b69f74d6047792f3d13a3d81c0432597c1b29b
|
|
| MD5 |
7573776c771c6b6d8fcf1bf34477467b
|
|
| BLAKE2b-256 |
dac618d23890e86cd02879f838265b6a4f5f965e40ac236572bec51fcf3e20b9
|
