TODO for AI
vs 
Gumloop
By Marcell Havlik, founder of TODO for AI · Updated
AI-native automation for business teams: chat-driven agents plus flows, priced in credits. Here is where each one wins, with numbers, and who should pick which.
| Fact | Gumloop | TODO for AI |
|---|---|---|
| Interface | Web, Chrome extension | Web, desktop, mobile, CLI, IDE (Zed, JetBrains, VS Code), voice |
| Models | Vendor managed, several available | Any provider: Claude, GPT, Gemini, Grok, Ollama |
| Source | Closed | Edge + CLI public |
| Starts at | $37/mo | Free |
Key takeaways
- Models. Gumloop model choice: Vendor managed, several available. 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. Gumloop pricing: Free tier for evaluation, Pro from $37 a month with 20,000 credits and an 8% orchestration fee, 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. Gumloop gets one task done inside the flow 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 Gumloop if your automations are mostly AI steps: scrape, summarise, classify, write. Pick TODO for AI if the task needs a shell, a repo, a deploy or your logged-in browser.
Gumloop
TODO for AI
Any providerWe are not competing for the same job
Gumloop gets the task done.
TODO for AI organises the whole company’s work.
Gumloop answers one question: how do I get this task done, inside the flow 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 Gumloop is, and where it stops
Gumloop is what an automation tool looks like when AI was the premise instead of an afterthought. It is agents-first now: you delegate in chat, Slack, Teams, Gmail or by voice, and the flow canvas sits underneath for the pipelines worth building explicitly. The nodes are scrape, summarise, classify and write rather than trigger and action, which makes marketing research and enrichment far less awkward than in Zapier or Make.
Where it stops is reach. Agents work through connected apps and the web, so there is no shell, no files that survive between runs and no session in your own logged-in Chrome. Pricing is the steepest entry in this category at $37 a month for 20,000 credits, with an 8% orchestration fee layered on top.
Marketing and ops teams automating AI-heavy research, enrichment and content pipelines.
Three reasons Gumloop users look elsewhere
Agents reach what Gumloop integrates with and what they can scrape. A tool without an integration, or one that needs a real logged-in session, is out of scope.
20,000 credits from $37 a month, with an 8% orchestration fee layered on top. Successful automation costs more than failed automation.
Everything runs in Gumloop's cloud. No shell, no persistent machine holding your files and logins, no browser of your own.
Six dimensions that decide it
Gumloop 14/30TODO for AI 29/30How does Gumloop compare to TODO for AI, feature by feature?
| Feature | Gumloop | TODO for AI |
|---|---|---|
Persistent cloud VM An always-on machine. Files, logins and sessions survive between runs. | No | Yes |
Model choice | Vendor managed, several | 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. | Extension trigger + scraping | Yes |
Business tasks, not only code SEO, email, ads, social, CRM via CLI tools. | Connected apps + web | Yes |
Any CLI as an integration | MCP | Any binary |
Voice control | Talk to agents | 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. | Chat-driven agents + flows | Unlimited, per task |
Projects for the whole company Engineering, marketing, ops, finance: separate projects and agents, one team and one bill. | Flows and workspaces | Unlimited, shared |
Team roles, pooled usage | Seats + credits + 8% fee | Roles + pooled |
Tool permissions | Basic | Allow, approve, block |
Open runtime | No | Edge + CLI public |
Same ladder, different meter
Credits per run, plus an 8% orchestration fee on Pro. Model calls are included in the credit cost rather than billed to your own key.
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.