Natural language task management with Todoist and GPT-4o
Needs changesWhat this workflow does
This AI workflow has 33 nodes and runs when a chat message arrives (plus 1 other trigger). Along the way it connects OpenAI Chat Model, Todoist and HTTP Request. It also calls api.todoist.com over HTTP.
How it runs
Trigger: When a chat message arrives (plus 1 other trigger).
- Orchestrator (AI Agent): runs an AI agent, with model: OpenAI Chat Model; 1 tool (Call Todoist Agent); memory: Simple Memory
- Todoist Agent (AI Agent): runs an AI agent, with model: OpenAI Chat Model; 25 tools (Get a Task, Get a Label, Move a Task, Add a Comment…)
Services it uses
HTTP calls to: api.todoist.com
Before you upgrade to n8n 3.0
1 thing in this workflow is removed in n8n 3.0. Fix it before you upgrade:
- AI Agent v1 (old agent modes) in Todoist Agent (v1.7), Orchestrator (v1.9): replace with Latest AI Agent node (Tools Agent). For SQL Agent, use a Postgres or MySQL tool with a recent AI Agent.
Rather not rewrite it? Many of these flows can be rebuilt in Make (free plan).
| Removed in 3.0 | Replace with |
|---|---|
| AI Agent v1 (old agent modes) Todoist Agent (v1.7), Orchestrator (v1.9) | Latest AI Agent node (Tools Agent). For SQL Agent, use a Postgres or MySQL tool with a recent AI Agent. |
Nodes used (8)
- AI Agent
@n8n/n8n-nodes-langchain.agent - Execute Workflow Trigger
n8n-nodes-base.executeWorkflowTrigger - Chat Trigger
@n8n/n8n-nodes-langchain.chatTrigger - Call n8n Workflow Tool
@n8n/n8n-nodes-langchain.toolWorkflow - OpenAI Chat Model
@n8n/n8n-nodes-langchain.lmChatOpenAi - Simple Memory
@n8n/n8n-nodes-langchain.memoryBufferWindow - Todoist Tool
n8n-nodes-base.todoistTool - Http Request Tool
n8n-nodes-base.httpRequestTool
From the author
Turn plain-language chat like “Tomorrow 9 AM: write blog post” into neatly organised Todoist tasks with GPT-4o and n8n—zero code. 🪄 Ultimate Personal Todoist Agent Turn natural-language requests into perfectly-organized Todoist tasks—all on autopilot inside…