# llm-workflow-engine/llm-workflow-engine

Power CLI and Workflow manager for LLMs (core package)

Repository: https://github.com/llm-workflow-engine/llm-workflow-engine
Canonical: https://ross.abutalabs.com/products/llm-workflow-engine
Language: Python
License: MIT
License Family: permissive
Topics: chatgpt, chatbot, gpt3, llm, openai, gpt-3, gpt4, python
Last push: 2026-08-14T17:15:46+00:00

## Health v2 (maintenance only)
Score: 84/100 (v2, computed 2026-09-03T02:20:16.233290+00:00)
- activity 97, release rhythm 60, longevity 97
- inputs: {"age_days": 1369, "days_push": 19, "days_rel": 49, "gap_med": 24.5, "n_releases_24m": 25}
- flags: prerelease_only
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 3717, forks 469 (observed 2026-08-28T04:08:15.403303+00:00)

## What it is
LLM Workflow Engine (LWE) is a power CLI and workflow manager for interacting with LLMs like ChatGPT/GPT-4 from the terminal. It supports multiple LLM providers via a plugin architecture and lets you integrate LLM calls into larger workflows, e.g. via Ansible playbooks.

## Use cases
- chat with gpt from the command line
- manage llm conversations in a terminal
- build workflows that call llms
- use multiple llm providers from one cli
- extend a chat cli with custom plugins
- script llm calls in ansible playbooks

## When to choose
- you want a terminal-first interface to ChatGPT/GPT-4 or other LLMs
- you need to chain LLM calls into scripted workflows
- you want a plugin system to add custom LLM commands or providers

## When to avoid
- you need a graphical chat interface
- you want to self-host open-weight models locally rather than call provider APIs
- you need a full agent framework with autonomous multi-step reasoning

## Facets
- artifact type: cli-tool
- maturity: active
- function: cli, chatbot, llm-inference, agent-framework, workflow-automation, plugin-system
- domain: large-language-models, developer-tools, chatbots
- platform: cli, python, cross-platform
- tags: llm, openai, gpt, chatgpt, shell, provider-plugins, ansible-workflows, command-line, automation

## Member repositories
- llm-workflow-engine/llm-workflow-engine (main) score 84

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:08:15.403303+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 2026-08-29T18:29:22.208965+00:00, confidence not recorded.
  - readme: https://github.com/llm-workflow-engine/llm-workflow-engine (fetched 2026-08-28T04:08:15.403303+00:00, sha c509ad79439f)
  - registry_pypi: https://pypi.org/pypi/llm-workflow-engine/json (fetched 2026-08-29T09:24:07.795947+00:00, sha 481af88db42d)
- Data as of 2026-08-30T08:39:29.467469+00:00.