// automation · Forward-Future/loopy

loopy

loopy est un projet de automatisation open source, créé par Forward-Future (Forward-Future/loopy sur GitHub). Il compte 3 164 étoiles sur GitHub et 281 forks, il est publié sous la licence MIT et a été mis à jour pour la dernière fois sur GitHub le 11 septembre 2026.

A library of practical AI-agent loops and an installable skill for finding, adapting, and designing repeatable agent workflows.

★ 3,2 k étoiles⑂ 281 forksMITmis à jour sept. 2026
▦ visuel — le README de ce projet ne contient aucune capture intégrable,
voici donc un emplacement réservé. Le guide ci-dessous est complet malgré tout.
// détails du projet

Détails du projet

Étoiles GitHub
3 164
Forks
281
Licence
MIT
Dernière mise à jour sur GitHub
11 septembre 2026
Catégorie
Automatisation
Type de fiche
Guide d'installation complet
Site officiel
Official site
// fonctionnement

Comment ça marche

  1. Connect your apps

    Link the services you already use through built-in integrations or generic webhooks and API calls.

  2. Build the flow visually

    Drag triggers and actions onto a canvas: when this happens, do that.

  3. Add logic and AI

    Branch on conditions, loop over items, or pipe steps through language models.

  4. Deploy and monitor

    Turn the workflow on and watch executions in the run history.

// fonctionnalités

Pourquoi on l'adore

Automation-ready

Designed to run unattended: triggers, schedules, and webhooks.

Versioned flows

Export, diff, and back up workflows like code.

No per-run pricing

The automation is free; you only pay for your own server.

Scheduling & triggers

Cron, webhooks, and events keep flows running 24/7.

AI-native steps

Call LLMs mid-workflow for decisions and extraction.

Self-hosted & private

Credentials and execution data stay on your infrastructure.

Advertisement
// lancez-le

Lancez-le vous-même

  1. Step 1 — Clone the repo

    Download the source and move into the project folder.

    git clone https://github.com/Forward-Future/loopy.git
    cd loopy
  2. Step 2 — Check the README

    Every project documents its own setup; start with install requirements.

    cat README.md | head -60
  3. Step 3 — Run it

    Follow the project's launch command — Docker, pip, npm, or a binary release.

    # see README for the exact launch command
// cas d'usage

Ce que vous pouvez créer

  • Sync data between apps without manual copy-paste.
  • Turn form submissions into tickets and notifications.
  • Build AI triage for inboxes and queues.
  • Schedule reports, backups, and posts.
Advertisement
// faq

Questions fréquentes

Who maintains loopy?

It is an open-source project at Forward-Future/loopy with 281 forks. Check the repo's contributors and recent commits to see how active maintenance is.

Is loopy free for commercial use?

MIT licensed — use it commercially, no strings attached.

What do I need to run it?

Docker and a small VPS or home server cover most of these.

How does it compare to Zapier?

Same idea, but self-hosted with no per-task pricing.

Do I need to code?

Most flows are visual; light expressions help for advanced logic.

// continuez l'exploration

Outils similaires

Automatisation

agent-toolkit

A curated collection of skills for AI coding agents. Skills are packaged instructions and scripts that extend agent capabilities across development, document…

★ 2,5 k étoilesMIT
Voir le guide →
Automatisation

prefect

Prefect is a workflow orchestration framework for building resilient data pipelines in Python.

★ 24,0 k étoilesApache-2.0
Voir le guide →
Automatisation

nanobrowser

Open-Source Chrome extension for AI-powered web automation. Run multi-agent workflows using your own LLM API key. Alternative to OpenAI Operator.

★ 13,9 k étoilesApache-2.0
Voir le guide →
Automatisation

harmony-next.skills

Offline skill library for building HarmonyOS NEXT apps with AI assistants.

★ 359 étoilesCustom
Voir le guide →
Automatisation

browser-search

Agent skill for web search and browsing that fights AI hallucinations.

★ 528 étoilesMIT
Voir le guide →
Automatisation

n8n-skills

Skill pack that teaches AI assistants to build and fix n8n workflows.

★ 404 étoilesCustom
Voir le guide →
// alternatives

Alternatives en Automatisation

Les autres projets de la catégorie Automatisation avec le plus d'étoiles du catalogue LibreAI — la sélection réaliste d'alternatives si loopy ne vous convient pas.

  • n8n★ 206,6 k

    Fair-code workflow automation platform with native AI capabilities. Combine visual building with custom code, self-host or cloud, 400+…

  • Langflow★ 155,8 k

    Langflow — the visual builder for AI agents and workflows: drag-and-drop flows over LangChain components, deployed as APIs or MCP tools, MIT-licensed

  • awesome-claude-skills★ 76,4 k

    A curated list of awesome Claude Skills, resources, and tools for customizing Claude AI workflows

  • Flowise★ 55,5 k

    Flowise — build AI agents visually: an open-source drag-and-drop UI over LangChain and LlamaIndex, with chatflows, agentflows and a marketplace of templates

  • Huginn★ 50,0 k

    Create agents that monitor and act on your behalf. Your agents are standing by!

// plus en automation

Plus en Automatisation

Projets de la catégorie Automatisation proches dans le catalogue, les plus proches en étoiles de loopy — continuez à explorer de part et d'autre.

  • Easel★ 3,3 k

    An open-source AI agent for social media — find trends, create, publish and learn what works.

  • openrpa★ 3,1 k

    Free Open Source Enterprise Grade RPA

  • WorkBuddyGuide★ 3,3 k

    A practical, open-source guide to mastering WorkBuddy through real-world workflows.开源的 WorkBuddy 实战蓝皮书:教程、真实工作流、Skills、MCP、自动化与多智能体实践。

  • create-pull-request★ 2,9 k

    A GitHub action to create a pull request for changes to your repository in the actions workspace

  • Vibe-Skills★ 3,5 k

    Intelligent Skill routing and workflow orchestration for AI agents — +21.12 pp reward, −29.6% tokens on SkillsBench with DeepSeekV4Flash-VE.

  • zotero-actions-tags★ 2,8 k

    Customize your Zotero workflow.

Obtenir loopy

Gratuit et ouvert : récupérez le code source, mettez une étoile au dépôt et commencez à créer.