- Intelligent Conversations - Engage in natural multi-turn dialogues
- Command Generation - Get optimized shell commands
- Pipeline Integration - Process data from other commands (e.g.,
git diff | viby "write a commit message") - MCP Tools - Extended capabilities through Model Context Protocol integration
# Install from PyPI
pip install viby# Install from source with uv
uv pip install -e .yb "Write a quicksort in python"
# -> Sure! Here is a quicksort algorithm implemented in **Python**:yb -c
|> Tell me about quantum computing
# -> [AI responds about quantum computing]
|> What are the practical applications?
# -> [AI responds with follow-up information]git diff | yb "Generate a commit message"
# -> Added information to the READMEyb "What is this project about?" < README.md
# -> This project is about...yb -s "How many lines of python code did I write?"
# -> find . -type f -name "*.py" | xargs wc -l
# -> [r]run, [e]edit, [y]copy, [c]chat, [q]quit (default: run): yb "What time is it now?"
# -> [AI uses time tool to get current time]
# -> "datetime": "2025-05-03T00:49:57+08:00"Viby reads configuration from ~/.config/viby/config.yaml. You can set the model, parameters, and MCP options here.
Use the configuration wizard to set up your preferences:
yb --configThis allows you to configure:
- API endpoint and key
- Model
- Temperature and token settings
- MCP tools enablement
- Interface language
Viby supports Model Context Protocol (MCP) servers for extended capabilities. MCP configurations are stored in ~/.config/viby/mcp_servers.json.