TODO for AI
vs 
GitHub Copilot
By Marcell Havlik, founder of TODO for AI · Updated
GitHub's coding agent: completions in the editor, a cloud agent that takes an issue and opens a pull request. Here is where each one wins, with numbers, and who should pick which.
| Fact | GitHub Copilot | TODO for AI |
|---|---|---|
| Interface | IDE, GitHub.com, CLI | Web, desktop, mobile, CLI, IDE (Zed, JetBrains, VS Code), voice |
| Models | OpenAI, Anthropic, Google, xAI, more | Any provider: Claude, GPT, Gemini, Grok, Ollama |
| Source | Closed | Edge + CLI public |
| Starts at | Free | Free |
Key takeaways
- Models. GitHub Copilot model choice: OpenAI, Anthropic, Google, xAI, more. 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. GitHub Copilot pricing: Free tier, Pro $10, Pro+ $39, Max $100 per month. Business and Enterprise seats add org controls. Premium requests are metered per 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. GitHub Copilot gets one task done from issue to pull request. 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 GitHub Copilot if your work is GitHub issues and pull requests. Pick TODO for AI if a lot of your backlog never becomes a pull request.
GitHub Copilot
OpenAI, Anthropic, Google, xAI, more
TODO for AI
Any providerWe are not competing for the same job
GitHub Copilot gets the task done.
TODO for AI organises the whole company’s work.
GitHub Copilot answers one question: how do I get this task done, from issue to pull request? 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 GitHub Copilot is, and where it stops
Copilot is the default coding agent by distribution. It completes in the editor, reviews pull requests, and the cloud agent picks up an issue, works on GitHub's runners and opens a PR. The model picker is the most open of any coding agent here: OpenAI, Anthropic, Google, xAI, Moonshot and Microsoft models, with Claude Code and Codex available as third-party agents on the same surface.
The shape is the constraint. Copilot works where GitHub works: repositories, issues, pull requests, Actions. Anything that is not a diff has no home. Copilot CLI does run in your terminal with per-command approval, but the agent that works unattended runs on GitHub's runners, and premium requests meter per model so an active team's bill follows its habits.
Teams whose work lives on GitHub and who want agents attached to issues and pull requests.
Three reasons GitHub Copilot users look elsewhere
The unit of work is a diff, tracked as an issue on a repository. An invoice to chase, a campaign to launch or an inbox to triage has no shape in Copilot.
Copilot CLI runs locally, but the agent that works unattended does so on GitHub's runners, on a clone of the repo. It reaches neither your servers nor your logged-in browser.
Completions are unlimited, agent work is not. Premium requests carry a per-model multiplier and overage bills per request.
Six dimensions that decide it
GitHub Copilot 16/30TODO for AI 29/30How does GitHub Copilot compare to TODO for AI, feature by feature?
| Feature | GitHub Copilot | TODO for AI |
|---|---|---|
Persistent cloud VM An always-on machine. Files, logins and sessions survive between runs. | GitHub runners per task | Yes |
Model choice | OpenAI, Anthropic, Google, xAI | 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. | Code and pull requests | Yes |
Any CLI as an integration | CLI locally, 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. | Yes, issues and pull requests | Yes |
Many agents, each configured Each agent gets its own model, prompt, tools and permissions. Pick which one takes an item. | Coding agent + custom agents | Unlimited, per task |
Projects for the whole company Engineering, marketing, ops, finance: separate projects and agents, one team and one bill. | Repos and issues | Unlimited, shared |
Team roles, pooled usage | Per seat | Roles + pooled |
Tool permissions | Repo scopes + command approval | Allow, approve, block |
Open runtime | No | Edge + CLI public |
Same ladder, different meter
Completions are unlimited on paid plans. Agent work spends premium requests, multiplied per model, and overage bills per request.
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.