Skip to content

Project

n8n

n8n is an open-source workflow automation platform for building multi-step automations linking apps, APIs, and AI agents, self-hosted or via n8n Cloud.

Known aliases

  • n8n
  • n8n Cloud
  • n8n.io
  • n8n MCP Client node
  • n8n workflow JSON

Current stories

buildOne report1 publisher

A twelve-node n8n workflow that runs 2,000 times a month counts as 2,000 executions

n8n's pricing page counts one execution per workflow run, from EUR 20 a month for 2,500 executions up to EUR 667 for 40,000, a DEV Community review says. In the review's examples, the run schedule decides which tier a team lands on.

Publishers:dev.to

Reality

Evidence55
Adoption
Not scored
Hype gap
Not scored
Incentives50
Confidence60
buildOne report1 publisher

Check Point finds two LiteLLM flaws that expose every provider key the gateway stores

LiteLLM 1.83.9 fixes two Check Point-reported flaws, CVE-2026-35029 and CVE-2026-59823, that affect every older version of the gateway. A DEV Community patch guide pairs the upgrade with key rotation and an audit of what the gateway held.

Publishers:dev.to

Reality

Evidence45
Adoption55
Hype gap+20
Incentives
Not scored
Confidence50
buildOne report1 publisher

Ruflo's 100-agent swarm for Claude Code starts in read-only mode with approval switched on

Cognitum One released a new Ruflo on October 13 that turns one coding assistant into a swarm of 100+ agents. The parts worth copying are the controls around the model: approval modes, cost visibility and data gating.

Publishers:dev.to

Reality

Evidence25
Adoption55
Hype gap+30
Incentives70
Confidence55
buildOne report1 publisher

n8n workflow runs now export OpenTelemetry traces, with a span per node if enabled

n8n announced native OpenTelemetry tracing on June 8, 2026, emitting one trace per workflow run and, optionally, a child span for every node. Teams that already run an OTLP-compatible backend can read an n8n run beside their other services.

Publishers:dev.to

Reality

Evidence40
Adoption
Not scored
Hype gap+10
Incentives45
Confidence55
buildOne report1 publisher

ZoomInfo's n8n node puts contact and signal lookups inside the workflow run

ZoomInfo launched a ZoomInfo-maintained n8n node on October 12, 2026 that lets workflows and AI agents query contacts, companies and signals at runtime. That puts a ZoomInfo call inside the run itself, so failure handling and agent permissions become the design questions.

Publishers:dev.to

Reality

Evidence45
Adoption
Not scored
Hype gap+20
Incentives65
Confidence50
buildOne report1 publisher

Four September n8n advisories come back 'not found' on OSV.dev and GitHub's database

Two of n8n's three September advisory batches, at least 26 advisories in all, have no CVE IDs, a dev.to post reports. A green scanner report on a self-hosted instance says little until someone checks the version by hand.

Publishers:dev.to

Reality

Evidence42
Adoption
Not scored
Hype gap+20
Incentives45
Confidence40
buildOne report1 publisher

n8n 2.43.0 blocks publishing of workflows with unconnected required inputs

n8n 2.43.0, shipped October 6, refuses to publish any workflow whose required node inputs are unconnected, according to a dev.to review of the changelog. The check covers wiring only, so wrong credentials and bad prompts still need their own tests before an agent goes live.

Publishers:dev.to

Reality

Evidence55
Adoption
Not scored
Hype gap+5
Incentives
Not scored
Confidence55
buildOne report1 publisher

n8n opens workflow building to Claude Code, Cursor and other agent hosts over MCP

n8n has opened its MCP tools to agent hosts including Claude Code, Codex and Cursor, so their agents can build and edit workflows from inside the coding tool. The workflows still run in n8n, so each host a team connects is one more place that can change a live automation.

Publishers:dev.to

Reality

Evidence30
Adoption
Not scored
Hype gap+8
Incentives60
Confidence30
buildOne report1 publisher

n8n patches two server-takeover flaws rated CVSS 8.7 and 9.4 across three release lines

n8n disclosed two server-takeover flaws on October 5, rated CVSS 8.7 and 9.4, with fixes in versions 1.123.76, 2.37.7 and 2.38.2. On a shared instance, the 8.7-rated sandbox escape lets anyone who can edit a workflow run code on the server.

Publishers:dev.to

Reality

Evidence50
Adoption
Not scored
Hype gap+10
Incentives
Not scored
Confidence55
buildOne report1 publisher

n8n's Postgres node inlines $1 parameters as SQL literals

n8n 2.41.6's Postgres node writes $1 values into SQL text via pg-promise 11.9.1, so Postgres never gets a bind parameter. A psql PREPARE dry-run tests a path the node never uses, and Postgres types inlined literals before any CASE guard runs.

Publishers:dev.to

Reality

Evidence70
Adoption
Not scored
Hype gap0
Incentives
Not scored
Confidence65
buildOne report1 publisher

NVIDIA's RTX Spark PCs fit a 4-bit 70B model in 128GB with about 90GB to spare

NVIDIA's RTX Spark PCs from Lenovo and Acer ship in October with up to 128GB of shared CPU/GPU memory, enough for a 4-bit 70B model. Long-context agents now fit on owned hardware, though a cost comparison with cloud inference waits on system prices.

Publishers:dev.to

Reality

Evidence30
Adoption
Not scored
Hype gap+35
Incentives
Not scored
Confidence30
buildOne report1 publisher

Three workflow bugs made one team's GPT-5.4 agent look lazy in production

One team running a GPT-5.4 agent in n8n traced its production 'laziness' to three workflow bugs, the first a retry cap cut from 6 to 2. Fixing the loop restored quality on the same model, so traces and stop reasons should be checked before any model swap.

Publishers:dev.to

Reality

Evidence30
Adoption
Not scored
Hype gap+10
Incentives
Not scored
Confidence30
buildOne report1 publisher

n8n's preview Agents call existing workflows as tools for open-ended jobs like triage

n8n has put Agents into preview on n8n Cloud, letting a model choose its own steps from four kinds of tools, existing workflows among them. Teams can hand triage and inbox review to an agent and keep repeatable actions in the workflows it calls.

Publishers:dev.to

Reality

Evidence35
Adoption10
Hype gap+15
Incentives70
Confidence40
buildOne report1 publisher

Hand-built Shopify webhooks lose their subscription without notice when the receiver fails

Shopify removes the subscription from a webhook whose destination is failing, and it emails the owner only when an App Store or custom app created the webhook. A merchant who builds one by hand in the admin has to watch the receiver themselves.

Publishers:dev.to

Reality

Evidence55
Adoption
Not scored
Hype gap0
Incentives
Not scored
Confidence55
investOne report1 publisher

European agentic-AI startups pass last year's funding total with 7.9bn euros raised

European agentic-AI startups have raised 7.9bn euros this year, already more than last year's 7bn, according to Sifted data. The founders who explain how customers deploy agents each sell one layer of the stack and disagree about which one has to come first.

Publishers:sifted.eu

Reality

Evidence35
Adoption
Not scored
Hype gap+30
Incentives75
Confidence40
buildOne report1 publisher

A workflow's step count decides whether Make or n8n costs less to run

Make bills a credit for every module a scenario executes and n8n bills once per run, so a 20-step pipeline costs 20 units on Make and one on n8n. For short flows the two prices converge, and the choice turns on who maintains the flows and where the data may live.

Publishers:dev.to

Reality

Evidence55
Adoption
Not scored
Hype gap+5
Incentives35
Confidence55
buildOne report1 publisher

AWS puts the agent runtime behind an n8n node, and leaves the permissions with you

An open-source AgentCore node moves memory, sandboxed execution and tool access into a managed harness. The install is the easy part; the access decisions do not move.

Publishers:dev.to

Reality

Evidence45
Adoption
Not scored
Hype gap+10
Incentives70
Confidence50
buildOne report1 publisher

The money behind low-code agents is better documented than their failure rate

n8n went from $2.5bn to $5.2bn in seven months and SAP is embedding its canvas in Joule Studio, while the single number offered for agent failure, an 88% security incident rate, arrives without a population or a definition.

Publishers:dev.to

Reality

Evidence42
Adoption58
Hype gap+30
Incentives52
Confidence45
buildOne report1 publisher

Three flipped defaults in n8n 2.0 can change a workflow nobody edited

A dev.to walkthrough of the n8n 1.x to 2.0 upgrade treats it as a host-configuration review, because the defaults that changed decide what Code nodes may read and which nodes exist at all.

Publishers:dev.to

Reality

Evidence35
Adoption
Not scored
Hype gap+18
Incentives30
Confidence42

Earlier coverage

  1. n8n's Assistant asks for a credential at the node that needs it

    Build · September 10, 2026 · One report1 publisher

  2. Velatir's 5M euro seed prices AI oversight at about $12,500 a customer

    Invest · August 20, 2026 · Confirmed2 publishers

  3. A coding agent deleted the rule its own rename had broken

    Build · August 14, 2026 · One report1 publisher