ai-agent

go-flow-levee: Streamline Go Workflows with AI‑Driven Automation

Name: go-flow-levee: Streamline Go Workflows with AI‑Driven Automation
Author: google

go-flow-levee lets founders automate Go process orchestration with an AI agent, reducing dev setup time and keeping services scalable.

195 stars17 forksGoGuide quality 8/10 · reviewed Oct 10Updated 8/9/2022100% free · open source

What it does

Go-flow-levee automates AI workflows for founders, providing efficient solutions built with Go, enabling streamlined execution of machine learning tasks

When to use it

•When you need to automate data processing and model training in a Go-based environment
•When you have to integrate AI workflows with existing Go applications
•When you require a scalable and efficient solution for deploying AI models

Ready-to-paste prompt

levee run -f levee.yaml -t myworkflow

Heads up: Ensure you have Go 1.17 or later installed, as go-flow-levee requires this version or higher to function correctly

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/go-flow-levee && curl -fsSL https://workflowstacks.com/api/skills/go-flow-levee/claude-skill -o ~/.claude/skills/go-flow-levee/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 go-flow-levee: Streamline Go Workflows with AI‑Driven Automation works

Codeflow

Free to inspect

Go-flow-levee: Streamline Go Workflows with AI‑Driven Automation is a medium Go project (~7.8k lines across 80 code files, plus 54 test files). Expect some technical setup — comfortable with a terminal, or ask a developer. Last commit 51 months ago, Apache-2.0 license, has a test suite.

Size

Medium codebase

~7.8k lines · 80 code files · ~1 h to skim

Setup

Some technical setup

Comfortable with a terminal? 20–40 min. Otherwise ask a dev.

Runs on

No API keys detected

Go 99%Shell 1%

Where to start reading

1
README.md
Start here — what it does and how to install it
2
cmd/levee/main.go
Where the program starts running
3
go.mod
Dependencies and the commands it exposes
4
internal/pkg/config/config_test.go
Inside internal/ — the main logic begins here

What's in each folder

internal/Core code — the actual logic157 files

pkg/Core code — the actual logic1 files

cmd/Command-line entry points1 files

guides/Documentation3 files

configuration/Folder3 files

design/Proposals & design notes3 files

hack/Helper scripts1 files

.github/CI / automation (GitHub Actions)6 files

READMEHas testsDocumentedCI checksApache-2.0 licenseLast update 51 mo ago

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/go-flow-levee && curl -fsSL https://workflowstacks.com/api/skills/go-flow-levee/claude-skill -o ~/.claude/skills/go-flow-levee/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

google

Language