# granawkins/rawdog

Generate and auto-execute Python scripts in the cli

Repository: https://github.com/granawkins/rawdog
Canonical: https://ross.abutalabs.com/products/rawdog
Language: Python
License: Apache-2.0
License Family: permissive
Last push: 2025-08-18T05:31:13+00:00

## Health v2 (maintenance only)
Score: 33/100 (v2, computed 2026-09-02T17:46:02.011165+00:00)
- activity 37, release rhythm 8, longevity 67
- inputs: {"age_days": 946, "days_push": 380, "days_rel": null, "gap_med": null, "n_releases_24m": 0}
- flags: none
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 1804, forks 139 (observed 2026-08-28T04:05:38.314939+00:00)

## What it is
Rawdog is a CLI assistant that responds to natural-language prompts by generating and auto-executing Python scripts. It uses a recursive self-augmentation approach (an alternative to RAG) where script outputs are fed back into the conversation to iteratively complete tasks.

## Use cases
- generate and run python scripts from natural language prompts
- analyze csv files in a directory with pandas
- inspect active ports and manage processes from the cli
- automate repo setup from a readme
- plot disk usage of files and folders
- cli ai assistant that executes code

## When to choose
- you want an LLM assistant that acts on your local machine via Python
- you need iterative tasks where script output informs the next step
- you want to use various LLM providers including local models via litellm

## When to avoid
- you cannot tolerate auto-executed arbitrary code without review
- you need a sandboxed or production-safe agent environment
- you don't want to expose an LLM API key or pay per request

## Facets
- artifact type: cli-tool
- maturity: active
- function: cli, agent-framework, llm-inference, developer-tools
- domain: artificial-intelligence, developer-tools
- platform: cli, python, cross-platform
- tags: ai-assistant, code-generation, auto-execution, rag-alternative, litellm, openai, ai-agents, command-line, automation

## Member repositories
- granawkins/rawdog (main) score 33

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:05:38.314939+00:00.
- Health v2: computed from the inputs above; adoption is never an input.
- Inferred fields (summary, facets, guidance): AI-extracted, prompt v1, taxonomy v1, on 2026-08-30T03:21:49.009405+00:00, confidence not recorded.
  - readme: https://github.com/granawkins/rawdog (fetched 2026-08-28T04:05:38.314939+00:00, sha 4284d9e483a0)
- Data as of 2026-08-30T08:39:29.467469+00:00.