TODO for AI
vs 
n8n
By Marcell Havlik, founder of TODO for AI · Updated
Fair-code workflow automation you can self-host, priced per whole workflow run. Here is where each one wins, with numbers, and who should pick which.
| Fact | n8n | TODO for AI |
|---|---|---|
| Interface | Web, self-hosted or cloud | Web, desktop, mobile, CLI, IDE (Zed, JetBrains, VS Code), voice |
| Models | Any, you supply the keys | Any provider: Claude, GPT, Gemini, Grok, Ollama |
| Source | Partly open | Edge + CLI public |
| Starts at | Self-host free | Free |
Key takeaways
- Models. n8n model choice: Any, you supply the keys. TODO for AI runs any provider, Claude, GPT, Gemini, Grok or a local Ollama model, on one plan, and one model can review another's work.
- Benchmark. TODO for AI scored 95.1% on Terminal-Bench 2.1 with Opus 5.5 (own harness, 77/81 tasks, refused tasks excluded, 2026-09-30; not an official leaderboard submission).
- Price. n8n pricing: Community Edition free to self-host under a fair-code licence. Cloud Starter €20/month for 2,500 executions, Pro €50 for 10,000, Business €667 self-hosted for 40,000, Enterprise custom. TODO for AI has a free plan (Claude Sonnet only), then Starter $20, Pro $100 or Ultra $200 a month with any provider included.
- Where the work happens. n8n gets one task done inside the workflow you built. TODO for AI is one board your team and agents work through together, on your own PC, a cloud VM and your logged-in Chrome.
- Who should pick which. Pick n8n if Data must stay on your own infrastructure. Pick TODO for AI if the people with the work are not going to build workflows.
n8n
Any, you supply the keys
TODO for AI
Any providerWe are not competing for the same job
n8n gets the task done.
TODO for AI organises the whole company’s work.
n8n answers one question: how do I get this task done, inside the workflow you built? So do the others — Cursor inside the editor, Claude Code in one person's session, Lindy by asking its assistant.
We answer a different one: where does the work live? One board per project, and a project for each part of the company — engineering, marketing, ops, finance, one per client. Your colleagues work on it. So do your agents, as many as you want to run, each with its own model, tools and permissions. Items carry the people who worked them and the agent that ran them, and the board filters by person, so what the company has in flight is one screen instead of a Slack thread.
That is not a team plan bolted onto an AI tool. It is the product. The agents are how items get closed; the board is what the company runs on.
What n8n is, and where it stops
n8n is the developer's answer in this category. Self-host it and the data never leaves your infrastructure, the Code node runs real JavaScript or Python, the Execute Command node reaches the host itself, the AI agent nodes are the deepest here, and executions are counted per whole workflow run rather than per step, so elaborate workflows are not punished. For a technical team it is the best value in automation.
It asks for a developer, though. Building in n8n means understanding nodes, expressions and data shapes, which is why it rarely spreads past the person who set it up. And it remains a builder: the workflow exists before the value does. Self-hosting is free in the sense that your own uptime, upgrades and secret management are free.
Technical teams who want automation they can self-host and extend in code.
Three reasons n8n users look elsewhere
n8n workflows tend to live with whoever built them. A colleague who wants the same job done writes a ticket rather than a workflow.
The workflow has to exist before it runs. A task you would describe once in a sentence never justifies the build.
Self-hosted, the Execute Command node reaches the host you administer, which is a real capability and a real security decision. On Cloud there is no such host at all, and neither mode gives an agent a session in your own logged-in Chrome.
Six dimensions that decide it
n8n 23/30TODO for AI 29/30How does n8n compare to TODO for AI, feature by feature?
| Feature | n8n | TODO for AI |
|---|---|---|
Persistent cloud VM An always-on machine. Files, logins and sessions survive between runs. | Your own server, self-hosted | Yes |
Model choice | Any, your own keys | Any provider |
Cross-vendor review Review GPT output with Claude, or the other way around. | No | Yes |
Drives your real browser Chrome extension plus cloud browsers. | Community browser nodes | Yes |
Business tasks, not only code SEO, email, ads, social, CRM via CLI tools. | Nodes + HTTP + code | Yes |
Any CLI as an integration | Code node + MCP | Any binary |
Voice control | No | Yes |
People and agents on one board Colleagues and agents work the same list. Items show who contributed and which agent ran them; filter the board by person. | No | Yes |
Many agents, each configured Each agent gets its own model, prompt, tools and permissions. Pick which one takes an item. | AI agent + LangChain nodes | Unlimited, per task |
Projects for the whole company Engineering, marketing, ops, finance: separate projects and agents, one team and one bill. | Workflows and projects | Unlimited, shared |
Team roles, pooled usage | Seats, self-host unlimited | Roles + pooled |
Tool permissions | Project-level | Allow, approve, block |
Open runtime | Fair-code, self-hostable | Edge + CLI public |
Same ladder, different meter
Executions count whole workflow runs with unlimited steps inside, which is the friendliest meter in this category. Model calls are billed by whichever provider's key you supply.
One pool priced in dollars of model cost, spendable on any vendor. Session and weekly windows pace it, and a 1.3-1.5x plan multiplier applies, so a $20 plan is about $15 of list-price API. Team seat prices go into one shared pool.