TODO for AI
vs 
OpenCode
By Marcell Havlik, founder of TODO for AI · Updated
Open-source terminal coding agent, bring your own keys, any provider. Here is where each one wins, with numbers, and who should pick which.
| Fact | OpenCode | TODO for AI |
|---|---|---|
| Interface | Terminal | Web, desktop, mobile, CLI, IDE (Zed, JetBrains, VS Code), voice |
| Models | Any provider (BYOK) | Any provider: Claude, GPT, Gemini, Grok, Ollama |
| Source | Open | Edge + CLI public |
| Starts at | Free | Free |
Key takeaways
- Models. OpenCode model choice: Any provider (BYOK). 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. OpenCode pricing: Free, MIT. You pay each provider for tokens. 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. OpenCode gets one task done in one person's terminal. 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 OpenCode if you want a free MIT tool and have API keys. Pick TODO for AI if you want one flat plan covering every model.
OpenCode
Any provider (BYOK)
TODO for AI
Any providerWe are not competing for the same job
OpenCode gets the task done.
TODO for AI organises the whole company’s work.
OpenCode answers one question: how do I get this task done, in one person's terminal? 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 OpenCode is, and where it stops
OpenCode is the open-source terminal agent for people who want to own the whole stack. MIT licensed, any provider through your own API keys, a fast TUI, and nothing running anywhere you did not put it. If you already hold keys and like reading source, it is the most hackable option on this list.
You also carry every operational burden. Token bills arrive per provider with no cap, there is no cloud machine, no scheduling, no team roles, and the scope is code. It is a great tool, and a great tool is not a platform.
Developers who want a free, hackable terminal agent and already hold API keys.
Three reasons OpenCode users look elsewhere
Per-token, per-provider, no pooled plan. One runaway loop is a surprise invoice.
Runs on whatever box you are at. Nothing persists, nothing is scheduled.
No roles, approvals or shared usage. Fine for one person, hard for a team.
Six dimensions that decide it
OpenCode 15/30TODO for AI 29/30How does OpenCode compare to TODO for AI, feature by feature?
| Feature | OpenCode | TODO for AI |
|---|---|---|
Persistent cloud VM An always-on machine. Files, logins and sessions survive between runs. | No | Yes |
Model choice | Any (BYOK) | 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. | Agents + subagents | Unlimited, per task |
Projects for the whole company Engineering, marketing, ops, finance: separate projects and agents, one team and one bill. | No | Unlimited, shared |
Team roles, pooled usage | No | Roles + pooled |
Tool permissions | Basic | Allow, approve, block |
Open runtime | Yes | Edge + CLI public |
What it costs
Free, MIT. You pay each provider for tokens.
Hobby free (Sonnet only), Starter $20, Pro $100, Ultra $200. Paid plans include any model provider.