TODO for AI
vs 
Cursor
By Marcell Havlik, founder of TODO for AI · Updated
A VS Code fork with built-in AI chat, unlimited tab completion and repo-scoped cloud agents. Here is where each one wins, with numbers, and who should pick which.
| Fact | Cursor | TODO for AI |
|---|---|---|
| Interface | IDE | Web, desktop, mobile, CLI, IDE (Zed, JetBrains, VS Code), voice |
| Models | Multi-vendor, metered | Any provider: Claude, GPT, Gemini, Grok, Ollama |
| Source | Closed | Edge + CLI public |
| Starts at | $20/mo | Free |
Key takeaways
- Models. Cursor model choice: Multi-vendor, metered. 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 89.9% on Terminal-Bench 2.1 with Opus 5.5 (high) (own harness, 80/89 tasks, 2026-10-08; not an official leaderboard submission).
- Price. Cursor pricing: Pro $20, Pro+ $60, Ultra $200, Teams from $40 per seat. Agent usage metered by model. 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. Cursor gets one task done inside the editor. 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 Cursor if you want autocomplete and inline edits while you type. Pick TODO for AI if you want to delegate tasks that do not end in a pull request.
Cursor
Multi-vendor, metered
TODO for AI
Any providerWe are not competing for the same job
Cursor gets the task done.
TODO for AI organises the whole company’s work.
Cursor answers one question: how do I get this task done, inside the editor? So do the others — Claude Code in one person's session, Lindy by asking its assistant, Manus mostly in their own cloud.
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 Cursor is, and where it stops
Cursor is the editor most AI-native teams type in. The tab completion and inline edits are the best in the category, unlimited on every paid plan, it supports models from several vendors, and it feels like VS Code because it is a VS Code fork.
Its cloud agents are real: they run in Cursor-managed VMs without your laptop, clone the repo, work on a branch and open a pull request. That is the shape of the whole product. Work that does not end in a diff — an inbox, a CRM, an ad account — has nowhere to land, and agent usage is metered by which model you reach for rather than included outright.
Engineers who want AI inside the editor while they type.
Three reasons Cursor users look elsewhere
Cloud agents run without your machine, but they clone a repo, push a branch and open a PR. Tasks that do not end in a diff have nowhere to land.
Tab is unlimited, agent runs are not. Heavy work on the strongest models draws down the included pools and then bills on.
The agent drives a browser to check the app it changed, but there is no inbox, CRM or ad account. Everything outside the repo is someone else's problem.
Subagents check into .cursor/agents, so configuration really does travel with the team. The work does not: there is no list where a colleague's task and an agent's task are the same item, and anything that is not a repo has nowhere to live.
Six dimensions that decide it
Cursor 14/30TODO for AI 29/30How does Cursor compare to TODO for AI, feature by feature?
| Feature | Cursor | TODO for AI |
|---|---|---|
Persistent cloud VM An always-on machine. Files, logins and sessions survive between runs. | No | Yes |
Model choice | Multi, metered | Any provider |
Cross-vendor review Review GPT output with Claude, or the other way around. | No | Yes |
Drives your real browser Browser extension (Chrome, Firefox) plus cloud browsers. | No | Yes |
Business tasks, not only code SEO, email, ads, social, CRM via CLI tools. | No | Yes |
Any CLI as an integration | 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. | Subagents, repo config | Unlimited, per task |
Projects for the whole company Engineering, marketing, ops, finance: separate projects and agents, one team and one bill. | Repos, per seat | Unlimited, shared |
Team roles, pooled usage | Per seat | Roles + pooled |
Tool permissions | Basic | Allow, approve, block |
Open runtime | No | Edge + CLI public |
Same ladder, different meter
Unlimited tab completion. Agent usage draws on an included Cursor-models pool and an other-models pool; Auto bills at the routed model's list price. Teams adds $0.25/M tokens.
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.