TODO for AI
vs 
OpenAI Codex
By Marcell Havlik, founder of TODO for AI · Updated
OpenAI's coding agent: an open-source CLI plus a cloud sandbox inside ChatGPT. Here is where each one wins, with numbers, and who should pick which.
| Fact | OpenAI Codex | TODO for AI |
|---|---|---|
| Interface | Terminal, ChatGPT web, IDE | Web, desktop, mobile, CLI, IDE (Zed, JetBrains, VS Code), voice |
| Models | OpenAI only | Claude, GPT, Gemini, Grok and other supported models |
| Source | Partly open | Edge + CLI public |
| Starts at | $8/mo | Free |
Key takeaways
- Models. OpenAI Codex model choice: OpenAI only. TODO for AI includes Claude, GPT, Gemini and Grok on paid plans. Pick the model for each job; let another review the result.
- Benchmark. TODO for AI scored 91.0% on Terminal-Bench 2.1 with Opus 5.5 (high) (own harness, 81/89 tasks, 2026-10-26; not an official leaderboard submission). OpenAI Codex is listed at 84.3% with Opus 5.5 (high) on the public leaderboard.
- Price. OpenAI Codex pricing: Included with ChatGPT: Go $8, Plus $20, Pro $100 or $200. Usage limits per window. TODO for AI has a free plan (Claude Sonnet only), then Starter $20, Pro $100 or Ultra $200 a month with the supported multi-vendor catalog.
- Shared business work. TODO for AI: Your whole team and its AI agents, on one board. Shared company context, brand voice and memory. AI working in your connected tools, signed-in browser and machines.
- Included usage. One shared pool of credits, with the cloud VM and browser included. Personal session and weekly limits apply. Credit usage depends on the model; see the pricing page for plan details.
- Who should pick which. Pick OpenAI Codex if you are OpenAI-only by policy. Pick TODO for AI if you want to run GPT-5.6 and have Claude review it.
OpenAI Codex
OpenAI only
TODO for AI
Supported vendorsWhere our product fits
One board for the company’s work.
People decide. Agents do the work.
Your whole team and its AI agents, on one board. Shared company context, brand voice and memory. AI working in your connected tools, signed-in browser and machines.
Chase the invoice. Ship the website update. Prepare the report. Fix the code. Every task keeps its request, contributors and result together, ready for the next colleague or agent to pick up.
Keep OpenAI Codex where it fits. Bring the rest of the company’s backlog here.
Plans and usage limitsWhat OpenAI Codex is, and where it stops
Codex is OpenAI's answer to Claude Code: an open-source CLI for local work and a cloud sandbox you launch from ChatGPT for parallel tasks. On GPT-5.6 it is unusually token-efficient, and being bundled into ChatGPT Plus makes it the cheapest way for an existing OpenAI customer to get an agent.
The trade-offs mirror Claude Code's. OpenAI models only, sandboxes that are fresh every task and scoped to a repo, and nothing for the browser or the business side. The CLI being open is genuinely useful; the cloud agent that does the heavy lifting is not.
Teams already on ChatGPT Plus or Pro who want GPT-native coding.
Three reasons OpenAI Codex users look elsewhere
No Claude, no Gemini, no way to cross-check output with a different model family.
Each cloud task starts clean. Logins, installed tools and half-finished state do not carry over.
It is built to produce pull requests. Anything outside a git repository is not a task it can take.
Six dimensions that decide it
OpenAI Codex 14/30TODO for AI 28/30TODO for AI · Opus 5.5 (high)91.0%OpenAI Codex · Opus 5.5 (high)84.3%Same 89 tasks, same model (Opus 5.5, high), one trial each, all runs done by us; refusals fall back to Opus 4.8, remaining refusals count as failures. Noise is about ±3 tasks, so treat it as indicative, not a controlled A/B or a leaderboard result.
How does OpenAI Codex compare to TODO for AI, feature by feature?
| Feature | OpenAI Codex | TODO for AI |
|---|---|---|
Persistent cloud VM A hosted workspace with persistent files, separate from the machines you connect. | Ephemeral sandbox | Yes |
Model choice | OpenAI only | Supported models across vendors |
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. Runs remain subject to usage limits. | Profiles + AGENTS.md | Configured per task |
Projects for the whole company Engineering, marketing, ops, finance: separate projects and agents, one team and one bill. | Repo folders | Unlimited, shared |
Team roles and usage Pooling is not exclusive to TODO for AI. A shared budget does not remove personal session or weekly limits. | Plan dependent | Shared credits, per-seat limits |
Tool permissions | Basic | Allow, approve, block |
Open runtime | CLI only | Edge + CLI public |
Same ladder, different meter
Message and feature caps per plan, counted per surface. Deep research and agent runs have their own quotas.
One shared pool of credits, with the cloud VM and browser included. Personal session and weekly limits apply. Credit usage depends on the model; see the pricing page for plan details.