# shobrook/wut

A terminal assistant for the hopelessly confused

Repository: https://github.com/shobrook/wut
Canonical: https://ross.abutalabs.com/products/wut
Language: Python
License: MIT
License Family: permissive
Last push: 2024-12-20T22:03:43+00:00

## Health v2 (maintenance only)
Score: 22/100 (v2, computed 2026-09-03T02:20:16.233290+00:00)
- activity 0, release rhythm 8, longevity 97
- inputs: {"age_days": 1364, "days_push": 621, "days_rel": 626, "gap_med": null, "n_releases_24m": 1}
- flags: none
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 1424, forks 85 (observed 2026-08-28T04:04:41.373933+00:00)

## What it is
wut is a Python CLI tool that sends the output of your last terminal command to an LLM (OpenAI, Claude, or a local Ollama model) and returns a plain-English explanation. It requires running inside a tmux or screen session so it can capture the previous command's output.

## Use cases
- explain a stack trace from my last command
- decipher an unfamiliar error code in the terminal
- figure out why my command failed
- summarize long log output
- ask follow-up questions about terminal output
- get help fixing incorrect shell commands

## When to choose
- you frequently hit confusing errors or stack traces in the terminal
- you want an LLM assistant that works with OpenAI, Anthropic, or local Ollama models
- you already live inside tmux or screen sessions

## When to avoid
- you don't use tmux or screen, since output capture requires them
- you don't want terminal content sent to a third-party LLM API
- you need fully offline tooling without any LLM access

## Facets
- artifact type: cli-tool
- maturity: active
- function: cli, llm-inference, developer-tools
- domain: developer-tools, large-language-models
- platform: cli, python
- tags: terminal-assistant, llm, error-explanation, tmux, ollama, command-line, macos, linux

## Member repositories
- shobrook/wut (main) score 22

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:04:41.373933+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 2026-08-30T04:37:36.916373+00:00, confidence not recorded.
  - readme: https://github.com/shobrook/wut (fetched 2026-08-28T04:04:41.373933+00:00, sha 748fe09b056b)
- Data as of 2026-08-30T08:39:29.467469+00:00.