n8n-agents

Name: n8n-agents
Author: czlonkowski

5.8kstars983forks

How to install n8n-agents?

czlonkowski/n8n-skills/n8n-agents

$npx -y skills add czlonkowski/n8n-skills --skill n8n-agents

Installs into the current project.

Summary

Design n8n AI agents the right way. Use when building or editing any @n8n/n8n-nodes-langchain.* AI node — an AI Agent, LLM chain, Text Classifier, or Information Extractor — and whenever the user mentions AI agents, LLM with tools, tool calling, $fromAI, system prompts, agent mem

Files · 1

View on GitHub

SKILL.md

1	# n8n Agents
2
3	The n8n AI Agent node (`@n8n/n8n-nodes-langchain.agent`) is a multi-turn LLM driver with sub-nodes for the model, memory, tools, and an optional output parser. This skill is the deep guide to designing agents and the LangChain family around them. For the high-level "where an agent fits in a workflow" picture, see n8n-workflow-patterns `ai_agent_workflow.md` — this skill goes one level down into how to build it well.
4
5	For node-type formats: in workflow JSON the LangChain nodes use the long `@n8n/n8n-nodes-langchain.` form (`.agent`, `.lmChatOpenAi`, `.memoryBufferWindow`, `.outputParserStructured`, `.toolWorkflow`, `.toolHttpRequest`, `.toolCode`). When you call `get_node` / `validate_node`, use the short* form (`nodes-langchain.agent`). See n8n-mcp-tools-expert for the format rules.
6
7	---
8
9	## Pick the right node first
10
11	Reaching for an Agent when the task is one-shot classification or extraction is the most common over-build. Decide before you wire anything:
12
13	\| You need to… \| Use \| Why \|
14	\|---\|---\|---\|
15	\| Call tools, reason over multiple turns, or hold memory \| AI Agent (`.agent`) \| The full loop: model + tools + memory + optional parser. Also a fine default when you'd rather standardize. \|
16	\| One-shot text in → text out, no tools \| Basic LLM Chain (`.chainLlm`) \| No agent loop, easier to debug. Still accepts an `outputParserStructured` sub-node. \|
17	\| Route a natural-language input to one of N branches \| Text Classifier (`.textClassifier`) \| ONE node, N output handles, downstream wires directly into each. Not Agent + Switch. \|
18	\| Pull structured fields out of free text \| Information Extractor (`.informationExtractor`) \| Purpose-built field extraction with a schema. \|
19	\| 3-way positive/neutral/negative split \| Sentiment Analysis (`.sentimentAnalysis`) \| Built-in branch outputs. \|
20	\| Condense a long document \| Summarization Chain (`.chainSummarization`) \| Map-reduce summarization built in. \|
21	\| Generate an image / audio / video \| The provider's native single-call node (OpenAI, Gemini, ElevenLabs…) \| NEVER wrap media generation in an Agent — see "Binary and the agent boundary". \|
22
23	Text Classifier detail (the Agent + Switch anti-pattern): every category needs both a name AND a description. The model routes against the description, not the name — a category with no description gets picked by coin-flip. Set `options.enableAutoFixing: true` for robustness on edge inputs. One node, N branches, done. Reaching for an Agent that "decides" then a Switch that "routes" is two nodes plus prompt boilerplate for what Text Classifier does natively.
24
25	Chat-model nodes (`.lmChatOpenAi`, `.lmChatAnthropic`, `.lmChatOpenRouter`, …) are sub-nodes — they don't run standalone. They wire into a chain, agent, classifier, or extractor via the `ai_languageModel` connection.
26
27	---
28
29	## The sub-node pattern
30
31	The Agent has a main input (the prompt / user message) and up to four sub-node slots, each wired by its own `ai_*` connection type:
32
33	\| Slot \| Connection type \| Required? \| Node example \|
34	\|---\|---\|---\|---\|
35	\| model \| `ai_languageModel` \| Yes \| `.lmChatOpenAi`, `.lmChatAnthropic`, `.lmChatOpenRouter` \|
36	\| memory \| `ai_memory` \| Optional \| `.memoryBufferWindow`, `.memoryPostgresChat` \|
37	\| tools \| `ai_tool` \| Optional (but the point of an agent) \| `slackTool`, `.toolWorkflow`, `.toolHttpRequest`, `.toolCode` \|
38	\| outputParser \| `ai_outputParser` \| Optional \| `.outputParserStructured` \|
39
40	A sub-node connects FROM itself TO the agent. In workflow JSON the connection lives on the sub-node, keyed by the `ai_*` type:
41
42	```json
43	"Main LLM": {
44	"ai_languageModel": [[{ "node": "AI Agent", "type": "ai_languageModel", "index": 0 }]]
45	},
46	"Simple Memory": {
47	"ai_memory": [[{ "node": "AI Agent", "type": "ai_memory", "index": 0 }]]
48	},
49	"Search customer DB": {
50	"ai_tool": [[{ "node": "AI Agent", "type": "ai_tool", "index": 0 }]]
51	}
52	```
53
54	Multiple tools all connect into the same `ai_tool` index 0 — they stack, they don't fan into separate indices. With `n8n_update_partial_workflow` you wire each with an `addConnection` op using `sourceOutput: "ai_tool"`. The agent puts its final answer in `$json.output` (not `.text`, not `.response`) — downstream nodes read `{{ $json.output }}`.
55
56	See EXAMPLES.md for a complete stateless agent-co

People who liked this also viewed

6 picks

Type

n8n-agents

5.8kstars983forks

View on GitHub

How to install n8n-agents?

czlonkowski/n8n-skills/n8n-agents

$npx -y skills add czlonkowski/n8n-skills --skill n8n-agents

Installs into the current project.

Summary

Files · 1

View on GitHub

SKILL.md

1	# n8n Agents
2
3	The n8n AI Agent node (`@n8n/n8n-nodes-langchain.agent`) is a multi-turn LLM driver with sub-nodes for the model, memory, tools, and an optional output parser. This skill is the deep guide to designing agents and the LangChain family around them. For the high-level "where an agent fits in a workflow" picture, see n8n-workflow-patterns `ai_agent_workflow.md` — this skill goes one level down into how to build it well.
4
5	For node-type formats: in workflow JSON the LangChain nodes use the long `@n8n/n8n-nodes-langchain.` form (`.agent`, `.lmChatOpenAi`, `.memoryBufferWindow`, `.outputParserStructured`, `.toolWorkflow`, `.toolHttpRequest`, `.toolCode`). When you call `get_node` / `validate_node`, use the short* form (`nodes-langchain.agent`). See n8n-mcp-tools-expert for the format rules.
6
7	---
8
9	## Pick the right node first
10
11	Reaching for an Agent when the task is one-shot classification or extraction is the most common over-build. Decide before you wire anything:
12
13	\| You need to… \| Use \| Why \|
14	\|---\|---\|---\|
15	\| Call tools, reason over multiple turns, or hold memory \| AI Agent (`.agent`) \| The full loop: model + tools + memory + optional parser. Also a fine default when you'd rather standardize. \|
16	\| One-shot text in → text out, no tools \| Basic LLM Chain (`.chainLlm`) \| No agent loop, easier to debug. Still accepts an `outputParserStructured` sub-node. \|
17	\| Route a natural-language input to one of N branches \| Text Classifier (`.textClassifier`) \| ONE node, N output handles, downstream wires directly into each. Not Agent + Switch. \|
18	\| Pull structured fields out of free text \| Information Extractor (`.informationExtractor`) \| Purpose-built field extraction with a schema. \|
19	\| 3-way positive/neutral/negative split \| Sentiment Analysis (`.sentimentAnalysis`) \| Built-in branch outputs. \|
20	\| Condense a long document \| Summarization Chain (`.chainSummarization`) \| Map-reduce summarization built in. \|
21	\| Generate an image / audio / video \| The provider's native single-call node (OpenAI, Gemini, ElevenLabs…) \| NEVER wrap media generation in an Agent — see "Binary and the agent boundary". \|
22
23	Text Classifier detail (the Agent + Switch anti-pattern): every category needs both a name AND a description. The model routes against the description, not the name — a category with no description gets picked by coin-flip. Set `options.enableAutoFixing: true` for robustness on edge inputs. One node, N branches, done. Reaching for an Agent that "decides" then a Switch that "routes" is two nodes plus prompt boilerplate for what Text Classifier does natively.
24
25	Chat-model nodes (`.lmChatOpenAi`, `.lmChatAnthropic`, `.lmChatOpenRouter`, …) are sub-nodes — they don't run standalone. They wire into a chain, agent, classifier, or extractor via the `ai_languageModel` connection.
26
27	---
28
29	## The sub-node pattern
30
31	The Agent has a main input (the prompt / user message) and up to four sub-node slots, each wired by its own `ai_*` connection type:
32
33	\| Slot \| Connection type \| Required? \| Node example \|
34	\|---\|---\|---\|---\|
35	\| model \| `ai_languageModel` \| Yes \| `.lmChatOpenAi`, `.lmChatAnthropic`, `.lmChatOpenRouter` \|
36	\| memory \| `ai_memory` \| Optional \| `.memoryBufferWindow`, `.memoryPostgresChat` \|
37	\| tools \| `ai_tool` \| Optional (but the point of an agent) \| `slackTool`, `.toolWorkflow`, `.toolHttpRequest`, `.toolCode` \|
38	\| outputParser \| `ai_outputParser` \| Optional \| `.outputParserStructured` \|
39
40	A sub-node connects FROM itself TO the agent. In workflow JSON the connection lives on the sub-node, keyed by the `ai_*` type:
41
42	```json
43	"Main LLM": {
44	"ai_languageModel": [[{ "node": "AI Agent", "type": "ai_languageModel", "index": 0 }]]
45	},
46	"Simple Memory": {
47	"ai_memory": [[{ "node": "AI Agent", "type": "ai_memory", "index": 0 }]]
48	},
49	"Search customer DB": {
50	"ai_tool": [[{ "node": "AI Agent", "type": "ai_tool", "index": 0 }]]
51	}
52	```
53
54	Multiple tools all connect into the same `ai_tool` index 0 — they stack, they don't fan into separate indices. With `n8n_update_partial_workflow` you wire each with an `addConnection` op using `sourceOutput: "ai_tool"`. The agent puts its final answer in `$json.output` (not `.text`, not `.response`) — downstream nodes read `{{ $json.output }}`.
55
56	See EXAMPLES.md for a complete stateless agent-co

People who liked this also viewed

6 picks

Type