Skip to main content

PW Agent 🧠

CLI coding assistant powered by your Ollama GPUs via PastaWater.

Install

The recommended way to install pw-agent is using pipx to keep it isolated from your other Python packages:

pipx install pw-agent

Alternatively, you can use standard pip: pip install pw-agent

Usage

pw-agent

First run guides you through setup — paste your API token, pick a GPU, start chatting.

Features

  • Interactive REPL with real-time streaming and a premium dashboard status bar.
  • Plan vs Build Modes: Use /plan for read-only analysis and /build for execution.
  • Context Discovery: Automatically finds PW_AGENT.md for project-specific rules.
  • Tab Autocomplete for commands, file paths, and GPU slots.
  • Session Control: Fresh sessions by default; use -c to resume where you left off.
  • File Injection: /add file.py or @file.py — inject files into the LLM's context.
  • Batch Processing: Model can run multiple tool calls in a single turn.
  • GPU Fleet Control: /models to view GPUs and /use N to switch connections or slots.
  • AI Commits: /commit to generate and apply git commit messages based on your diff.
  • Safety First: -y flag for auto-approve; otherwise, every file edit requires confirmation.

Connect

  • Cloud mode: Use your PastaWater API token to access your remote fleet.
  • Direct mode: Point at a local Ollama instance (--brain http://localhost:11434).

Get your token at pastawater.io/settings

Model compatibility (tool calling)

Agentic tool use needs both a capable model AND an Ollama whose tool-call parser tolerates that model's output drift.

Model Ollama Tool calling Notes
qwen3-coder:30b >= 0.31.2 verified ~20 GB resident on a single 24 GB card
qwen3-coder:30b 0.21.x broken intermittent qwen tool call parsing failed: EOF — session degrades to plain chat
llama3.1:8b any recent works weaker coder; fine for pipeline text tasks

Failure signals (v1.51.0+): a session that ends without executing any tool due to parse failure/stall emits {"type":"result","subtype":"degraded", "degraded_reason":...,"is_error":true} and exits with code 3; a missing model or dead endpoint fails preflight with the installed-model list and exits with code 2. Only one large model fits a 24 GB card at a time — requesting a second large tag while one is resident forces CPU offload.

Download files

Download the file for your platform. If you're not sure which to choose, learn more about installing packages.

Source Distribution

pw_agent-1.51.0.tar.gz (123.3 kB view details)

Uploaded Source

Built Distribution

If you're not sure about the file name format, learn more about wheel file names.

pw_agent-1.51.0-py3-none-any.whl (129.7 kB view details)

Uploaded Python 3

File details

Details for the file pw_agent-1.51.0.tar.gz.

File metadata

  • Download URL: pw_agent-1.51.0.tar.gz
  • Upload date:
  • Size: 123.3 kB
  • Tags: Source
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/7.0.0 CPython/3.12.13

File hashes

Hashes for pw_agent-1.51.0.tar.gz
Algorithm Hash digest
SHA256 f4676337a8411dd56a70a03728895d91c2b7432c6d9d8535a8f00c5c0a246c3e
MD5 2d5775a78f3682a5cd17be331694c319
BLAKE2b-256 05231a2c17638f285bda6963076cc5eb2a9b8d5a309b273107d0f688127cdae8

See more details on using hashes here.

File details

Details for the file pw_agent-1.51.0-py3-none-any.whl.

File metadata

  • Download URL: pw_agent-1.51.0-py3-none-any.whl
  • Upload date:
  • Size: 129.7 kB
  • Tags: Python 3
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/7.0.0 CPython/3.12.13

File hashes

Hashes for pw_agent-1.51.0-py3-none-any.whl
Algorithm Hash digest
SHA256 25f138410919bcc8485cfc5f012f546dd90b090c837d1de580a96fd1c376ed40
MD5 132ef6df883832dba8b56442f838efed
BLAKE2b-256 0f64e55094448765520f7864e5255ee5afa874c8633341296c036ccd1679d2c0

See more details on using hashes here.

Release history Release notifications | RSS feed

Supported by

AWS Cloud computing and Security Sponsor Datadog Monitoring Depot Continuous Integration Fastly CDN Google Download Analytics Sentry Error logging StatusPage Status page