Top 200 ReposEXPLORER
Browse agents, categories and pages
Back to results
Reported by sourceThe source says this happened. Top 200 Repos has not reproduced it.

Build a self-hosted AI agent workflow with human approval

Use n8n's visual canvas to wire an LLM agent to your apps, add tools and memory, and pause for human approval before it acts.

Try the promptRead the original (opens in a new tab)

The problem

How it works

The README describes n8n as a fair-code platform that mixes a visual canvas with custom JavaScript or Python. You self-host it with Docker on port 5678, connect a model provider such as OpenAI, Anthropic or Google, and build multi-step agent workflows with tool use, human approvals and observability. The AI docs add agents with tools and memory, multi-model workflows and MCP server connections.

Results and limitations

The maintainers claim a large integration catalog and thousands of workflow templates, and say you can switch model providers without redesigning the workflow.

Before you try it

Integration counts differ between the README and the repo description, so treat them as approximate. The Sustainable Use License limits some commercial uses, and model calls bill through your provider. Results depend on your setup and were not independently reproduced by Top 200 Repos.

Tools and repositories

Tools
n8n · Docker
Prerequisites
A self-hosted n8n instance or n8n Cloud account, plus an API key for your chosen model provider and credentials for each connected app.

Try it yourself: Design an n8n agent workflow

Fill the fields to adapt the prompt. Empty fields stay as visible [placeholders].

Preview
Design an n8n workflow that [What the workflow should do]. It starts from [Trigger] and may use these apps: [Connected apps]. Lay out the nodes in order, which ones the AI agent can call as tools, what memory it needs, and which credentials I must create. Insert a human approval step before any node that sends a message, writes to a database, deletes data or spends money. Give me the plan first and wait for my approval; then produce importable workflow JSON with placeholder credential names instead of real secrets. Finish with a short test plan using sample input.

Keep a human approval node in front of every outbound or destructive step until the workflow has been tested.

Related videos

About n8n-io/n8n

About n8n-io/n8n

Independent creators. Listing a video implies no endorsement, sponsorship or partnership.

Sources

  1. n8n-io/n8n README (opens in a new tab)

    Project documentation · github.com · Undated · Source checked 9 Nov 2026, 22:21 UTC

    What this source supports
    • Visual canvas combined with custom code
    • Multi-step AI workflows with tool use, human approvals and observability
    • Self-host with Docker; editor on localhost:5678
    • Fair-code under the Sustainable Use License
  2. Integrate AI (opens in a new tab)

    Project documentation · docs.n8n.io · Undated · Source checked 9 Nov 2026, 22:25 UTC

    What this source supports
    • Connect LLM providers such as OpenAI, Anthropic and Google
    • Add tools and memory to agents
    • Connect MCP servers to an AI agent
Report a problem

Reported by source

Build an on-call investigation agent from your own alert history

Goutham Veeramachaneni connected Claude Code to Grafana's gcx CLI, his code and runbooks, then trained its skill on two weeks of past pages for his services.

gouthamve.dev · 21 Apr 2026anthropics/claude-code
Planned, not done

Hand CRM updates and follow-up drafts to Grok Bot agents with approval steps

Grok Bot launched in beta in August 2026: always-on agents with their own cloud computer that sign in to your apps, learn routines by watching you, and come back when something needs your approval.

x.ai · 11 Aug 2026
Planned, not done

Try a desktop-operating agent safely in Anthropic's computer use demo container

Anthropic's computer-use-demo runs Claude inside a Docker desktop that you watch in the browser, with a chat panel, so you can test screen, mouse and keyboard automation away from your own machine.

github.com
Reported by source

Keep a resident desktop agent for research notes and blog work

Raj Chettri runs Nous Research's Hermes Agent on his desktop for scheduled research summaries, note filing, quick scripts and his blog's writing pipeline.

rajchettri-com.pages.dev · 25 May 2026NousResearch/hermes-agent
Reported by source

Run a self-hosted personal assistant on a spare Mac

Federico Viticci ran OpenClaw (then called Clawdbot) on an M4 Mac mini with Claude Opus 4.5 over Telegram for briefings, smart-home control and small automations.

macstories.netopenclaw/openclaw
Planned, not done

Run coding agents from one self-hosted control centre with OpenHands

OpenHands Agent Canvas runs the OpenHands agent, or Claude Code, Codex, Gemini CLI and other ACP agents, on your machine or in Docker sandboxes, and can trigger them from schedules or webhooks.

github.comOpenHands/OpenHands