An AI Agent on your terminal, to preserve your brain juice.
Project description
🗲 Dasshh 🗲
An AI Agent on your terminal, to preserve your brain juice.
Dasshh is a tui built with textual that allows you to interact with your computer using natural language.
Note: This project is still in early development. Suggestions and contributions are welcome!
✨ Features
- Interactive & minimal chat UI
- Chat with your personal assistant on your terminal
- Perform actions on your computer with plain English
- Extensible with your own tools
📸 Screenshots
📦 Installation
Using uv (Recommended)
If you haven't tried uv yet, it's highly recommended for fast Python package management.
# Install uv on macOS
brew install uv
# Or using curl
curl -LsSf https://astral.sh/uv/install.sh | sh
# Install dasshh
uv tool install dasshh
Using pipx
# Install pipx if you haven't already
pip install --user pipx
pipx ensurepath
# Install dasshh
pipx install dasshh
Verify Installation
dasshh --version
🚀 Quick Start
1. Initialize Configuration
dasshh init-config
This creates a config file at ~/.dasshh/config.yaml.
2. Configure Your Model
Edit the config file to set your model and API key:
model:
name: gemini/gemini-2.0-flash
api_key: <your-google-AI-studio-api-key>
See litellm docs for all supported models and providers.
3. Launch Dasshh
dasshh
4. Start Chatting
Ask Dasshh to help with system tasks:
• What's the current CPU usage?
• Show me the top memory-intensive processes
• List files in my downloads folder
• Create a new directory called "projects"
Exit: Press Ctrl+C to terminate.
📖 Documentation
The documentation is available at https://vgnshiyer.github.io/dasshh/.
Running the docs locally
# Install dependencies
uv pip install mkdocs-material
# Serve the documentation
mkdocs serve
Then visit http://localhost:8000 in your browser.
🤝 Contributing
Contributions are welcome! Please open an issue with your suggestions or feature requests.
🛠️ Development
Clone the repository
git clone https://github.com/vgnshiyer/dasshh.git
cd dasshh
Install dependencies
uv sync
Run the app
python -m dasshh
📝 License
This project is licensed under the MIT License. See the LICENSE file for details.
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
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 dasshh-0.1.3.tar.gz.
File metadata
- Download URL: dasshh-0.1.3.tar.gz
- Upload date:
- Size: 27.9 kB
- Tags: Source
- Uploaded using Trusted Publishing? Yes
- Uploaded via: twine/6.1.0 CPython/3.12.9
File hashes
| Algorithm | Hash digest | |
|---|---|---|
| SHA256 |
df22b30a06a18cb302e4c6f2785f2b673553957b58f78ef91c7ff2e6b8b2d345
|
|
| MD5 |
6de75700d2c0ec2943fd4b218b12c7e1
|
|
| BLAKE2b-256 |
4e8ed0abc1e7e16bea89d6d7a15709c69194089732f6362cd41a007296658a36
|
Provenance
The following attestation bundles were made for dasshh-0.1.3.tar.gz:
Publisher:
publish.yml on vgnshiyer/dasshh
-
Statement:
-
Statement type:
https://in-toto.io/Statement/v1 -
Predicate type:
https://docs.pypi.org/attestations/publish/v1 -
Subject name:
dasshh-0.1.3.tar.gz -
Subject digest:
df22b30a06a18cb302e4c6f2785f2b673553957b58f78ef91c7ff2e6b8b2d345 - Sigstore transparency entry: 220093306
- Sigstore integration time:
-
Permalink:
vgnshiyer/dasshh@e7cd6bf3d9d5451ed6a331df4cff362f3a8003f9 -
Branch / Tag:
refs/tags/0.1.3 - Owner: https://github.com/vgnshiyer
-
Access:
public
-
Token Issuer:
https://token.actions.githubusercontent.com -
Runner Environment:
github-hosted -
Publication workflow:
publish.yml@e7cd6bf3d9d5451ed6a331df4cff362f3a8003f9 -
Trigger Event:
release
-
Statement type:
File details
Details for the file dasshh-0.1.3-py3-none-any.whl.
File metadata
- Download URL: dasshh-0.1.3-py3-none-any.whl
- Upload date:
- Size: 37.8 kB
- Tags: Python 3
- Uploaded using Trusted Publishing? Yes
- Uploaded via: twine/6.1.0 CPython/3.12.9
File hashes
| Algorithm | Hash digest | |
|---|---|---|
| SHA256 |
dbbdef5e43a1984aac3cb864bbd2a9184c5005cc0f4a6d5edd1c9d91c12892c7
|
|
| MD5 |
9f98ade9b4a74a09a1c85c58d8715e4d
|
|
| BLAKE2b-256 |
414d8140f75551ca73d346be8ee9650299f2ca4bdab2c00d50bcc629af0c5de4
|
Provenance
The following attestation bundles were made for dasshh-0.1.3-py3-none-any.whl:
Publisher:
publish.yml on vgnshiyer/dasshh
-
Statement:
-
Statement type:
https://in-toto.io/Statement/v1 -
Predicate type:
https://docs.pypi.org/attestations/publish/v1 -
Subject name:
dasshh-0.1.3-py3-none-any.whl -
Subject digest:
dbbdef5e43a1984aac3cb864bbd2a9184c5005cc0f4a6d5edd1c9d91c12892c7 - Sigstore transparency entry: 220093308
- Sigstore integration time:
-
Permalink:
vgnshiyer/dasshh@e7cd6bf3d9d5451ed6a331df4cff362f3a8003f9 -
Branch / Tag:
refs/tags/0.1.3 - Owner: https://github.com/vgnshiyer
-
Access:
public
-
Token Issuer:
https://token.actions.githubusercontent.com -
Runner Environment:
github-hosted -
Publication workflow:
publish.yml@e7cd6bf3d9d5451ed6a331df4cff362f3a8003f9 -
Trigger Event:
release
-
Statement type: