N8N Tools - Agno Basic Agent icon

N8N Tools - Agno Basic Agent

Level 1 AI Agent with ultra-fast performance (~3μs) - Basic tools and instructions powered by Agno framework
Join our community

Overview

This node implements a Level 1 AI agent powered by the Agno framework, designed for ultra-fast performance (~3 microseconds execution). It acts as a basic AI assistant that can process input messages or queries and return intelligent responses using configurable AI models from providers like OpenAI or Anthropic (Claude).

Common scenarios where this node is beneficial include:

  • Generating or editing content such as articles, summaries, or emails.
  • Performing data analysis, calculations, or providing insights.
  • Conducting web research and fact-checking.
  • Engaging in conversational support or chat companion roles.
  • Solving tasks involving problem-solving or troubleshooting.

Practical examples:

  • A marketing team uses the node to generate concise social media posts based on brief instructions.
  • A data analyst leverages the node to summarize complex datasets or perform quick calculations.
  • A researcher automates fact-checking by querying web search tools integrated into the agent.
  • Customer support teams use it as a chat companion to provide instant answers to common questions.

Properties

Name Meaning
Model Provider Choose your AI model provider. Options: OpenAI, Anthropic (Claude).
Model Select the specific AI model depending on the provider:
OpenAI: GPT-4o, GPT-4o Mini, GPT-4 Turbo, GPT-3.5 Turbo
Anthropic: Claude 3.5 Sonnet, Claude 3.5 Haiku, Claude 3 Opus
Instructions System instructions guiding the AI assistant's behavior (e.g., "You are a helpful AI assistant. Be concise, accurate, and helpful.").
Message The input message or query to send to the AI agent.
Quick Setup Mode Choose configuration complexity:
🚀 Beginner (Recommended) - pre-configured settings.
🔧 Custom Setup - full control over all settings.
Agent Preset (Shown only in Beginner mode) Pre-configured agent types for common use cases:
📝 Content Assistant (writing, editing, summarizing)
📊 Data Helper (analysis, calculations, insights)
🔍 Research Agent (web search, fact-checking)
💬 Chat Companion (conversational support)
🛠️ Task Solver (problem-solving, troubleshooting)
Enable Tools (Shown only in Custom mode) Enable native Agno tools for ultra-fast performance.
Agno Native Tools (Shown if Enable Tools is true and in Custom mode) Select which native tools to enable:
🧮 Reasoning Tools
🔍 Web Search Tools
📊 Data Analysis Tools
💰 Finance Tools (YFinance)
📧 Email Tools
🌐 HTTP Request Tools
📁 File System Tools
🗃️ Database Tools
🔄 Shell Tools
Tool Configurations (Shown if Enable Tools is true and in Custom mode) Configure options for enabled tools, including:
- File System (S3, Cloudflare R2, MinIO, Google Cloud Storage)
- Email (SMTP server, port, credentials)
- Database (type, connection string)
- Finance Tools (default period, currency)
Advanced Options Additional fine-tuning parameters:
- Temperature (0–2): randomness of responses.
- Max Tokens: max tokens in response.
- Output Format: Text, Markdown, JSON.
- Enable Streaming: real-time streaming responses.
- Enable Cost Estimation: show cost metrics and safety limits.
- Max Credits per Request: safety limit on spending.
- Prefer Cost Efficiency: optimize for lower costs.
Report Issue Notice with links to report bugs or get help.

Output

The node outputs an array of items, each containing a json object with the following fields:

  • response: The AI-generated response text from the agent.
  • agentType: Always "basicAgent".
  • agentLevel: Numeric level of the agent, here always 1.
  • agnoVersion: Version of the underlying Agno framework.
  • executionTime: Time taken for the request in milliseconds.
  • llmCalls: Number of calls made to the language model.
  • tokensUsed: Object detailing token usage statistics.
  • cacheHits: Number of cache hits during processing.
  • reasoningSteps: Array of reasoning steps performed (if any).
  • toolsUsed: List of tools invoked during the request.
  • memoryOperations: Memory operations performed (empty here as memory is disabled).
  • sessionId: Unique session identifier for the request.
  • model: The selected AI model name.
  • modelProvider: The chosen AI model provider.
  • agnoFramework: Always true, indicating use of Agno framework.
  • nativeLLM: Always true, indicating native LLM integration.
  • ultraFastProcessing: Always true, highlighting performance.
  • originalMessage: The original input message sent to the agent.
  • timestamp: ISO timestamp of when the response was generated.

If an error occurs and "Continue On Fail" is enabled, the output item will contain an error field with the error message, status code, and additional error data.

The node does not output binary data.

Dependencies

  • Requires an API key credential for the N8N Tools API to authenticate requests.
  • Connects to the remote Agno Basic Agent API endpoint at https://n8ntools-agno-production.up.railway.app/api/v1/agent.
  • Optional configurations may require access credentials for external services such as:
    • Amazon S3 or compatible cloud storage (Cloudflare R2, MinIO, Google Cloud Storage).
    • SMTP email servers.
    • Databases (PostgreSQL, MySQL, SQLite, MongoDB).
    • Financial data APIs via YFinance.
  • Proper network connectivity to these services is necessary.

Troubleshooting

  • Missing Credentials Error: If the node throws an error about missing API credentials, ensure you have configured the required API key credential for the N8N Tools API in n8n.
  • Timeouts or Slow Responses: Network issues or service outages at the remote API endpoint can cause delays or failures. Check connectivity and retry.
  • Invalid Model or Provider Selection: Selecting incompatible model-provider combinations may cause errors. Verify that the model matches the chosen provider.
  • Tool Configuration Errors: Misconfigured tool credentials (e.g., wrong SMTP password, invalid S3 keys) can cause failures when those tools are enabled.
  • Cost Limit Exceeded: If cost estimation is enabled and the request exceeds the max credits per request, the node may reject or limit the operation.
  • Streaming Disabled but Expected: Enabling streaming requires client support; otherwise, responses come fully after completion.
  • Error Handling: When "Continue On Fail" is enabled, errors are returned as part of output items instead of stopping workflow execution.

Links and References

Discussion