n8n · Workflow platform with Agent Builder and agent nodes
Product and access
n8n combines fixed workflows, standalone published agents and agentic workflow nodes. The Message an Agent node connects published agents to workflows.
Provider
n8n GmbH develops the n8n automation platform with cloud and self-hosted options. Publicly available software uses the Sustainable Use License; additional enterprise features have separate license terms.
- Operator
- n8n GmbH
- Organization
- Company
- Website
- n8n.io
- Location
- Berlin, Germany
- Repository
- n8n-io/n8n
- GitHub stars
- 206,759 · Reviewed
- License
- Sustainable Use License; Enterprise License
Core features
7 features from provider sources · checked on 9 October 2026. Availability and limits are listed below.
Agent Builder in the project
Agents are created as their own project artifacts alongside workflows and published with versioning.
Source 3Tools, skills and knowledge base
Configurable tools, reusable Skills, and a searchable knowledge base give the agent capabilities and context.
Source 3Session and episodic memory
Sessions retain the current conversation context; episodic memory can retrieve earlier sessions.
Source 3Approve tools in workflows
In the AI Agent workflow node, selected tools can require human approval before execution.
Source 4Channels and schedules
Published agents are accessible through Slack, Telegram, or Linear and through recurring schedules.
Source 3Connect to workflows
Workflows can address agents; agents can delegate work to published subagents.
Source 3
Requirements and limits
Requirement
Cloud version or self-hosting
Agents are available on all n8n Cloud plans and all self-hosted plans from version 2.32.3. Instance owners can enable or disable them centrally.
Source 3Limitation
Preview phase
According to current documentation, Agents are in preview and can make mistakes; behavior may change during development.
Source 3Limitation
Queue mode
Queue mode is not yet supported for agents; n8n also notes possible errors with channel connections.
Source 3Requirement
Self-hosted knowledge base
The knowledge base requires a configured sandbox; channel connections require a publicly reachable WEBHOOK_URL. AI-assisted building requires additional Assistant setup.
Source 3
Operation & oversight
Based on public provider documentation. Assessments are editorial inferences from the stated properties. Actual time requirements and reliability have not been measured.
Deployment covered: Workflow operation; cloud and self-hosted installations
Sources reviewed:
Documented with conditions
Files and work state
Saved execution data can be loaded again. Deleting a workflow also deletes its execution history.
EvidenceOpen in reviewed sources
Authentication
The operational sources reviewed here do not establish a cross-service lifetime for authentication.
EvidenceDocumented with conditions
Starting further runs
The Schedule Trigger starts published workflows on a schedule; the configured time zone applies.
EvidenceOpen in reviewed sources
Human intervention
The operational sources reviewed here do not establish universal approval before external actions.
EvidenceDocumented
Detecting errors
The execution view and configured error workflows support diagnostics and notifications.
EvidenceDocumented
Recovering from errors
Failed executions can be retried with the original or currently saved workflow.
Evidence
Editorial assessment
Error paths and notifications need deliberate configuration. Retries should account for external actions that already ran.
Practical tasks
Editorial examples based on documented features. No product tests performed.
Prepare an incoming request
- Your input
- Form event, classification rules, and approved storage
- Possible result
- The workflow classifies the request and saves a proposed response.
- What to check
- Work with test data and error paths; control storage access.
Reply draft for approval
- Your input
- Customer question, knowledge source, and email tool
- Possible result
- The agent creates a draft; sending waits for human approval.
- What to check
- Check recipients, facts, and message before sending.
Build a request process with classification, approval, and subsequent filing.
Your possible prompt
Design a process for new requests: capture information, sort it by topic, and create a proposed response. Plan an approval step before external actions.
Getting-started idea based on documented capabilities. Not an executed product test. Adapt the task, data, and permissions.
Setup and pricing
Setup
Configure workflow, model, and connections
Prices and included usage
Pricing checked
Cloud plans are billed by workflow executions with unlimited steps. The Community Edition is self-hosted under the Sustainable Use License.
- Community Edition
- EUR 0 software fee
Self-hosting; use within the Sustainable Use License.
Price source - Starter
- EUR 20/month; billed annually
2,500 executions/month, one shared project, five concurrent executions.
Price source - Pro
- EUR 50/month; billed annually
10,000 executions/month, three shared projects, up to 50 concurrent executions.
Price source - Enterprise
- Custom pricing
Cloud or self-hosting; custom execution allowance and enterprise features.
Price source
- Self-hosting adds infrastructure and, where applicable, model costs. OpenAI's price list is one example of separately billed model access: https://developers.openai.com/api/docs/pricing
- Agent turns share the execution allowance with workflows; model and tool usage may add costs.
Sources and evidence
Current documentation on standalone Agents and AI Agent workflow nodes reviewed. Agents are in Preview and available on all self-hosted plans from 2.32.3, including Enterprise. Queue mode remains restricted; sandbox and channels need their own configuration.
Editorial team: Michael Meierhoff · sources reviewed on . Provider information is not independent evidence of performance.
-
n8n.io /ai-agents/
-
docs.n8n.io Official website
-
docs.n8n.io /build/build-and-manage-agents.md
-
docs.n8n.io /build/integrate-ai/ai-examples/human-in-the-loop-for-tools.md
-
docs.n8n.io /choose-how-to-use-n8n/
-
n8n.io /pricing/
-
docs.n8n.io /sustainable-use-license/
-
api.github.com /repos/n8n-io/n8n
