Skip to content
Agents tracked: 492 Releases (7d): 545 Agent status: 1 with issuesSince last limit reset: Claude 9d · Codex 7d For AI agents: Markdown Updated Nov 20, 2026

n8n

A workflow automation platform with a visual editor, several hundred integrations and native AI agent nodes. It can be self-hosted or used as a cloud service.

Agent builders and workflow automation Workflow automation platformProprietaryFree to start

Use it in: Web app Self-hosted API / SDK Works with: MCP Local models

Price
Free
free tier available
Popularity
#1 in Automation
Gid Score 79 / 100 · #4 of 251 ranked AI agents
Trend
Steady
downloads up 4.9% over 30 days · down 28.5% last week
Development
Actively updated
latest 1.123.98, 2d ago
Community
211K GitHub stars
107K package downloads a week

Usage data: latest readings Nov 17 to Nov 19, 2026, last checked Nov 19, 06:31 UTC. Date of each number

What n8n does

n8n is a workflow automation platform from n8n. You use it through a web app, self-hosted and REST API. Its documentation covers MCP servers and local models. It has a free tier.

Teams use it for: Workflow automation, Document review, Internal tools, Reporting, Testing. See examples.

Key facts

Makern8n
TypeWorkflow automation platform
LicenseSustainable Use License (source-available)
InterfacesWeb app, Self-hosted, REST API
Main languageTypeScript
Open issues and PRs1,246
Docker Hub pulls287,906,967

Pricing

n8n offers a free self-hosted community edition. Cloud plans: Starter (€20/mo, 2.5K executions) and Pro (€50/mo, 10K executions). The Business plan (€667/mo, 40K executions) is self-hosted only. Enterprise plans are available on contact, hosted by n8n or self-hosted. Pricing shown is annual billing.

Source: official pricing page, checked Oct 28, 2026. Prices change often; confirm before you buy.

n8n pricing history since 2024 · Compare prices of all agents

Quick answers

  • Free to start?Yes
  • Open source?No
  • Where you use itWeb app, Self-hosted, REST API
  • Supports MCP?Yes
  • Feature comparisonAll agents
  • Closest alternativeDify · all alternatives

What's new in n8n: November 2026 so far

Full monthly summary

November brought stability improvements and expression handling fixes, along with enhancements to the AI Agent Node and migration reporting features. The month focused on resolving edge cases in workflow execution and improving the overall reliability of automation runs.

  • AI Agent Node now keeps tool-call history separate for each input item, improving multi-item processing accuracy.
  • Expression engine improvements allow reading Error objects and named array keys directly in workflows.
  • Migration report features now filter by recipient from notification emails and hide archived workflows by default.
  • Fixed resume attempts for waiting and queued executions to prevent unnecessary retries.

18 releases this month · summarised from the official release notes · all months

How teams use n8n

All n8n use cases · All use cases

Case studyField Aerospace

How Field Aerospace uses n8n to draft government proposals in minutes

Field Aerospace, an aircraft modification company, runs a self-hosted n8n deployment behind an internal web app to draft proposal responses, extract requirements and screen govern…

As reported by n8n, a proposal draft reaches about an 80% starting point in roughly 25 minutes, versus about two weeks of work from three or four peo…

n8nWorkflow automation · Document review
Case studyDropsolid

How Dropsolid syncs CRM and marketing data with n8n workflows

Dropsolid, a Belgian digital agency built on open-source tools, adopted n8n to connect its CRM, marketing automation and analytics. The workflows sync data between systems and fee…

As reported by n8n (vendor case study), the workflows connected the team's apps and synced their data, resolving the original integration challenges.

n8nWorkflow automation · Reporting
Recipe

Layer hallucination checks into AI agent workflows with n8n

An n8n blog guide explains how to combine several hallucination detection methods in AI agent workflows and route flagged outputs to retries, error workflows or human review. It s…

The article gives no quantitative results; it is a guidance piece, not a measured deployment. (as reported by n8n)

n8nAI Agent nodeDeepEvalTesting · Workflow automation
Recipe

Build a filtered morning AI news brief with You.com, Jev, and n8n

A guest post from You.com shows how to build an n8n workflow that searches the day's AI news, filters articles with a low-cost scoring model, and posts one cited brief per topic t…

As reported by the n8n blog (guest post by You.com), Jev scores each article for about $0.00004.

n8nYou.comJev (TypeSafe AI)Workflow automation · Research
Case studyDelivery Hero

How Delivery Hero automated account recovery with n8n Enterprise

Delivery Hero's IT service delivery team built one n8n workflow in which a manager approves an employee's account recovery and API calls then restore access. As reported by n8n, a…

As reported by n8n, time to deployment was 5 hours.

n8nn8n EnterpriseWorkflow automation · Internal tools
Case studyDeda.Tech

How Deda.Tech automates ITSM provisioning and server lifecycles with n8n

Italian IT service provider Deda.Tech uses n8n as middleware between its internal ITSM system and customers' tech stacks. It automates VM provisioning and server lifecycle tasks, …

Delivery time improved from 2 days to 30 minutes, as reported by n8n (vendor case study).

n8nn8n EnterpriseWorkflow automation · DevOps and CI

AgentGid articles about n8n

All guides

Get started with n8n

npmnpm install -g n8n
Dockerdocker pull n8nio/n8n

These commands use the packages tracked on this page. The vendor may recommend a different installer; see the official documentation.

What n8n users report right now

All 2 reports, questions and fixes →

Fixed in 2.39.0 Users report that after n8n 2.36.x every call through the Mistral Cloud Chat Model node failed with 'Failed to parse URL from [object Request]' before any request reached Mistral, while 2.35.4 worked.

Reported on GitHub · 8 👍

Closed Users report the Qdrant Vector Store node failing with 'fetch failed' when used as an AI Agent tool, although the credential test passes and the same Qdrant endpoint works outside n8n. The thread points to more than one cause; the 2.39.0 release notes list an updated Qdrant client, but the reporter still saw errors on 2.39.6 before closing the issue.

Reported on GitHub · 1 👍

The most discussed problems in its GitHub repository, checked Nov 12, 2026. Written by AgentGid in its own words; statuses and fix versions come from the project's own pages. Reports are users' accounts, not AgentGid tests.

Compare n8n with another agent

vs
# Agent Gid Score Downloads 7d 7d 30d Stars Latest release Price
14
DifyLangGenius
63 — — — 161K+80/day 1.20.02d ago Free + $59/mo
44
AnythingLLMMintplex Labs
50 — — — 68.4K+35/day 1.20.03d ago Free + $50/mo
50
LangflowLangflow (DataStax, an IBM company)
47 13.2K down 19.0% up 13.8% 157K+36/day 1.13.33d ago Free (OSS)
79
Jobs Applier AI Agent NewFederico Elia
412/4 — — — 32.6K+19/day usage-counter11d ago Free (OSS)
100
Coze StudioByteDance
382/4 — — — 21.8K+2/day 0.5.19mo ago Free (OSS)
109
ActivepiecesActivepieces
36 — — — 25.6K+20/day 0.93.012d ago Free + $20/mo

Head to head: n8n vs LangGraph · n8n vs CrewAI · n8n vs Dify · n8n vs Zapier Agents · n8n vs AnythingLLM · n8n vs Langflow · n8n vs Jobs Applier AI Agent · n8n vs Activepieces

Ratings from people who use n8n

No ratings yet. Used n8n? Rate it and say what it is good and bad at.

  1. Release GitHub Releases

    n8n 1.123.98 released

    <source media="(prefers-color-scheme: dark)"… (+1 more release that day)

  2. Official n8n

    AI made integrations the vendor’s problem

    Report discusses how MCP adoption across vendors has shifted integration responsibilities from users to vendors in AI agent development tools.

  3. Release GitHub Releases

    n8n 1.123.97 released

    <source media="(prefers-color-scheme: dark)"…

  4. Official n8n

    New in n8n: Public API rate limits that keep every team on your instance running

    n8n added public API rate limits per API key with 429 response headers and idempotency key support for safe retries.

  5. Data AgentGid data

    n8n downloads down 30% in a week

    105K npm downloads in the 7 days to Nov 13, against 150K the week before.

    n8n
  6. Official n8n

    Build Safer n8n Agents and Workflows with Google Gemini 4 Carbon

    Google Gemini 4 Carbon model is now available in n8n, with improved performance on coding and agentic automation tasks scoring 53.9% on AutomationBench.

  7. Official n8n

    Meet Nod: a standalone personal agent from n8n Labs that runs on your computer

    n8n Labs released Nod, a standalone personal agent that runs locally on computers, works across apps and websites, and uses configurable AI providers.

  8. Official n8n

    Send contracts for e-signature from n8n, with TurboDocx, Slack approval and SharePoint filing

    Tutorial on using n8n with TurboDocx to automate contract e-signature workflows including Slack approval and SharePoint filing.

    n8n

What changed: recent n8n releases

Monthly summary · Full changelog

1.123.98
  • <!-- This is an auto-generated description by cubic. --> <a href=" target="_blank" rel="noopener noreferrer" data-no-image-dialog="true"><picture><source media="(prefers-color-scheme: dark)"…
2.48.5
  • AI Agent Node: Keep tool-call history separate for each input item (4f16701)
  • AI Agent Node: Stop adding newlines between streamed text chunks (19d9fa4)
  • core: Give fresh installs a random instance ID (1f15447)
  • core: Hand dollar property reads to the expression engine (6fb7219)
  • core: Keep small objects inside an Error in sandboxed expressions (fd845a7)
  • core: Treat instance owners and admins as team project members in credential checks (d17bbc5)
Earlier releases
1.123.97
  • <!-- This is an auto-generated description by cubic. --> <a href=" target="_blank" rel="noopener noreferrer" data-no-image-dialog="true"><picture><source media="(prefers-color-scheme: dark)"…
2.47.7
  • core: Stop redacting executions that use global credentials (c067170)
2.48.4
  • core: Stop redacting executions that use global credentials (4f6927f)
1.123.96
  • editor: Make JSON highlight color visible on light theme (bffbcd8)
  • Update @modelcontextprotocol/sdk (f719280)

n8n prices over time

Full pricing history →

n8n plan pricesfrom archived copies of the official pricing page
Cheapest paid planMost expensive self-serve plan

n8n popularity and usage data

n8n was downloaded 107K times from npm in the week ending Nov 17, 2026, down 28.5% on the week before and up 4.9% over the last 30 days compared with the 30 before. The GitHub repository has 211K stars, 3,784 of them added in the last 30 days. The latest stable release is 1.123.98, published Nov 18, 2026; there were 31 stable releases in the past 30 days. It was mentioned in 45 Hacker News posts and comments over the last 30 days.

Downloads per daynpm, 7-day average 15.3K/day
GitHub starsrunning total 211K
Hacker News mentionsposts and comments, rolling 7-day total 7 this week
Wikipedia page viewsEnglish Wikipedia, 7-day average 331/day
Website rankTranco list; a lower rank means more traffic #5,536

Download the raw daily series: n8n.csv

Gid Score breakdown

Adoption94
Community97
Attention46
Momentum52

Gid Score shows public popularity and activity (usage, GitHub stars, mentions, growth), not the quality of the product. Each component is scored 0 to 100 from public signals; a dash means no data for it. How the Gid Score works.

How fresh these numbers are

NumberLatest readingLast checked
Package downloadsNov 17, 2026Nov 19, 06:21 UTC
GitHub starsNov 19, 2026Nov 19, 06:26 UTC
Docker pullsNov 19, 2026Nov 19, 06:26 UTC
Website rank (Tranco)Nov 18, 2026Nov 19, 06:31 UTC
Wikipedia viewsNov 18, 2026Nov 19, 06:26 UTC
Hacker News mentionsNov 18, 2026Nov 19, 06:26 UTC

We fetch every source once a day. Registries publish downloads and page views a day or two late, so their latest reading trails the check. A reading more than 4 days old is marked out of date; the Gid Score still uses it until a newer one arrives.

n8n FAQ

How much does n8n cost?

n8n offers a free self-hosted community edition. Cloud plans: Starter (€20/mo, 2.5K executions) and Pro (€50/mo, 10K executions). The Business plan (€667/mo, 40K executions) is self-hosted only. Enterprise plans are available on contact, hosted by n8n or self-hosted. Pricing shown is annual billing.

Is n8n open source?

No. n8n is a proprietary product from n8n.

How popular is n8n?

n8n was downloaded 107K times from npm in the week ending Nov 17, 2026, down 28.5% on the week before and up 4.9% over the last 30 days compared with the 30 before. The GitHub repository has 211K stars, 3,784 of them added in the last 30 days. The latest stable release is 1.123.98, published Nov 18, 2026; there were 31 stable releases in the past 30 days.

What is the latest version of n8n?

The latest stable release we track is 1.123.98, published on Nov 18, 2026.

What are the alternatives to n8n?

The closest alternatives in the same category by Gid Score are Dify, AnythingLLM, Langflow, Jobs Applier AI Agent.

For the makers of n8n badges, corrections

Add a live badge to your README or site:

AgentGid: #1 in Automation Gid Score: 79/100 downloads: 107K/week ▲5% 30d

[![AgentGid: #1 in Automation](https://agentgid.com/badges/n8n-rank.svg)](https://agentgid.com/agents/n8n/)
[![Gid Score: 79/100](https://agentgid.com/badges/n8n-score.svg)](https://agentgid.com/agents/n8n/)
[![downloads: 107K/week ▲5% 30d](https://agentgid.com/badges/n8n-downloads.svg)](https://agentgid.com/agents/n8n/)

Something wrong or outdated on this page? Send a correction with a link to the official source. More for makers.

Where these numbers come from

npm: n8n. GitHub: n8n-io/n8n. Wikipedia: N8n. Site rank: n8n.io on the Tranco list. See data sources for how each one is collected.