automation

lionagi: Automate Complex Workflows with AI‑Powered Agents

Name: lionagi: Automate Complex Workflows with AI‑Powered Agents
Author: ohdearquant

lionagi lets founders orchestrate AI agents to handle data, LLM tasks, and automation pipelines, all in Python. Ideal for rapid prototyping and scaling smart workflows.

From the repo · “An intelligence orchestra”

412 stars85 forksPythonGuide quality 9/10 · reviewed Oct 13Updated 10/22/2026100% free · open source

What it does

Lionagi streamlines workflows by automating tasks using Python and machine learning, allowing founders to orchestrate their workflows efficiently

When to use it

•When you have repetitive tasks that can be automated using machine learning
•When you need to integrate multiple services and tools into a single workflow
•When you want to optimize your workflow using data-driven decision making

Ready-to-paste prompt

lionagi run my_workflow --task my_task --input my_input.csv --output my_output.csv

Heads up: Make sure you have Python 3.8 or higher installed, as lionagi is not compatible with earlier versions of Python

Saves to your device

Use with Claude

New

Skip the builder — one click puts this in Claude, Cursor, Antigravity and more.

✅ Light setup

Installs with a command or two; your AI agent can do it for you.

Try it instantly — no install

Claude Code

mkdir -p ~/.claude/skills/lionagi && curl -fsSL https://workflowstacks.com/api/skills/lionagi/claude-skill -o ~/.claude/skills/lionagi/SKILL.md

Open in another AI app

Opens the app with this repo with the prompt ready to go — no copy-paste needed.

Connect the whole catalog (MCP)

claude mcp add --transport http workflowstacks https://workflowstacks.com/api/mcp

Adds a WorkflowStacks connector to Claude Code: search and load any skill here by chatting.

What's inside — free to inspect

No purchase needed

Read the entire source before you build — unlike paid marketplaces that hide it behind a buy button.

top-level files

folders

111.9M

source size

Apache-2.0

license

Key files

.pre-commit-config.yaml

AGENT.md

README.md

File tree

.claude-plugin/

.github/

apps/

assets/

benchmarks/

cookbooks/

docs/

examples/

lion1/

lionagi/

lionrs/

marketplace/

notebooks/

scripts/

tests/

.coveragerc

.env.example

.gitignore

.markdownlint.jsonc

.pre-commit-config.yaml

.python-version

AGENT.md

CHANGELOG.md

CLAUDE.md

Use with Claude

New

Skip the builder — one click puts this in Claude, Cursor, Antigravity and more.

✅ Light setup

Installs with a command or two; your AI agent can do it for you.

Try it instantly — no install

Claude Code

mkdir -p ~/.claude/skills/lionagi && curl -fsSL https://workflowstacks.com/api/skills/lionagi/claude-skill -o ~/.claude/skills/lionagi/SKILL.md

Open in another AI app

Opens the app with this repo with the prompt ready to go — no copy-paste needed.

Connect the whole catalog (MCP)

claude mcp add --transport http workflowstacks https://workflowstacks.com/api/mcp

Adds a WorkflowStacks connector to Claude Code: search and load any skill here by chatting.

Quick Actions

Details

Creator

ohdearquant

Language

Python

Do this with a working workflow

Pages we wrote and tested that put a skill like this to work — importable n8n templates, outcome guides and Claude Desktop configs.

Outcome guide

Score your leads by ideal-customer fit

You describe your ideal customer once and keep leads in a Google Sheet. The workflow scores each 1–5 for fit with a one-line reason, so you sort and work the best first.