A CLI coding assistant powered by your Ollama GPUs. Uses local LLMs for code generation, chat, and agentic workflows. Current version: 1.50.40. Released frequently via PyPI.
pip install pw-agentNo compatibility data collected yet for this library.
Verified import paths — ran on the pinned version, not inferred.
Initialize the agent with an Ollama host and model, then send a chat message.
Use PastaWaterAgent(model='codellama').
Set a reasonable timeout or check connectivity before calling agent methods.
Use agent.chat() instead of agent.generate().