automation

Flyto2 Core: Automate AI Workflows

Streamline AI-agent workflows with Flyto2 Core.
479 stars83 forksPythonGuide quality 8/10Updated 8/14/2026100% free · open source
What it does

Flyto2 Core streamlines AI-agent workflows by providing a robust execution kernel for automation, supporting features like registry-backed modules, evidence capture, and versioning.

When to use it
  • You need to automate complex workflows involving AI agents and require a scalable, open-source solution.
  • Your startup relies heavily on workflow efficiency and automation, and you want to leverage Python for scripting.
  • You're looking for a tool that supports YAML recipes, triggers, and queue management for customized automation workflows.
Ready-to-paste prompt
Create a new YAML recipe named `my_workflow.yaml` with the following content: `modules: [module1, module2]` and `triggers: [trigger1]`, then execute it using the `flyto-core` CLI.
Heads up: Ensure you have Python and the necessary dependencies installed, as Flyto2 Core is built on Python and utilizes specific libraries for its functionality.
Saves to your device
Use with Claude
New

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

🛠️ Technical setup

Expect 20–40 minutes in a terminal — or let your AI agent drive it.

Try it instantly — no install
Claude Code
mkdir -p ~/.claude/skills/flyto-core && curl -fsSL https://workflowstacks.com/api/skills/flyto-core/claude-skill -o ~/.claude/skills/flyto-core/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.

How Flyto2 Core: Automate AI Workflows works
Codeflow
Free to inspect

Flyto2 Core: Automate AI Workflows is a very large Python project (~197k lines across 896 code files, plus 251 test files). It is a full software project: use it through its install path rather than reading it end to end. Last commit this month, Apache-2.0 license, has a test suite.

Size
Very large codebase
~197k lines · 896 code files · days to read — use, don't read
Setup
Developer setup
A real software project. Use it via its install path; don't expect to read it all.
Runs on
Python · Docker
Needs API keys (.env)
Python 99%Shell 1%
Where to start reading
  1. 1
    README.md
    Start here — what it does and how to install it
  2. 2
    AGENTS.md
    The instructions the AI actually follows
  3. 3
    run.py
    Where the program starts running
  4. 4
    package.json
    Dependencies and the commands it exposes
  5. 5
    .env.example
    The API keys and settings you must provide
What's in each folder
src/Core code — the actual logic930 files
workflows/Workflows / pipelines26 files
docs/Documentation46 files
examples/Examples you can copy29 files
demo/Examples you can copy4 files
audit_report/Folder50 files
scripts/Helper scripts42 files
handoffs/Folder37 files
READMEHas testsDocumentedCI checksDocker readyExamples includedApache-2.0 licenseUpdated this month
Quick Actions
Details
Creator
flytohub
Language
Python
Category
automation
Published
12/4/2025

Are you the creator of this tool? Claim your listing → and earn 85% of every sale.