Comparison
APX vs ChatGPT dots: A project crew or one always-on agent in ChatGPT?
Both keep working between conversations and learn how you work. APX runs a crew of agents on hardware you control; a dot is one always-on agent inside ChatGPT, with its own cloud computer.
The short answer
Choose APX if…
- You want an ongoing crew for your projects, with distinct roles, a shared task board and work you can follow in one place.
- Agents hand off work; tasks keep their status, discussion and results.
- Desktop app for macOS, Windows and Linux; Android app, web panel and terminal.
- MIT. Model and service usage can have separate costs.
Choose ChatGPT dots if…
- You already use ChatGPT and want one always-on agent with its own cloud computer, your ChatGPT memory and plugins, reachable from ChatGPT, Slack or Teams.
- One always-on agent that takes on ongoing goals and keeps making progress between conversations.
At a glance
Scroll the table to compare both products.
| What matters | ||
|---|---|---|
| Main focus | A team organized around projects, roles and tracked tasks.Source 1 ↗Source 2 ↗ | One always-on agent that takes on ongoing goals and keeps making progress between conversations.Source 1 ↗Source 2 ↗ |
| How you use it | Desktop app for macOS, Windows and Linux; Android app, web panel and terminal.Source 1 ↗Source 2 ↗Source 3 ↗ | ChatGPT desktop app, desktop web and iOS and Android apps; also Slack, Teams and voice calls.Source 1 ↗Source 2 ↗ |
| Where work runs | Your computer or a server you control. Model providers receive the prompts you send.Source 1 ↗Source 2 ↗ | Its own cloud computer and browser run by OpenAI; access to your own computer is optional and off by default.Source 1 ↗Source 2 ↗ |
| Working together | Agents hand off work; tasks keep their status, discussion and results.Source 1 ↗Source 2 ↗ | One dot per person today; it can create Codex and ChatGPT Work tasks. OpenAI previews specialized dots for organizations.Source 1 ↗Source 2 ↗ |
| Context over time | Persistent memory, project context and reusable skills.Source 1 ↗Source 2 ↗ | Starts with ChatGPT memory, forms its own memories, including from connected apps; local skills with a connected computer.Source 1 ↗Source 2 ↗ |
| Recurring work and chats | Scheduled routines and connected chat channels, including Telegram and Discord.Source 1 ↗Source 2 ↗ | Reminders, recurring tasks and background research; Slack and Teams, plus a limited texting beta for US Pro users.Source 1 ↗Source 2 ↗ |
| Models and extensions | Model providers, Claude Code, Codex and ACP agents; MCP and skills.Source 1 ↗Source 2 ↗Source 3 ↗ | OpenAI models (launched with GPT-6 Astra); ChatGPT plugins shared with ChatGPT, Work and Codex.Source 1 ↗Source 2 ↗ |
| License and costs | MIT. Model and service usage can have separate costs.Source 1 ↗Source 2 ↗ | Proprietary. First dot included in Pro (from $100/month) and Business Premium; Enterprise beta. Not in the EEA, Switzerland or UK.Source 1 ↗Source 2 ↗Source 3 ↗ |
With the models you already use
APX doesn't tie you to one model. Use your plan, an API or a local model, and give each agent the one that suits it.
- ChatGPTYour ChatGPT plan.
- ClaudeAnthropic's API, with your key.
- GeminiGoogle's Gemini API.
- Claude CodeIts sessions sit beside your chats.
- CodexIts sessions sit beside your chats.
- ACP agentsOpenCode, Qwen Code, goose and more.
- OpenAI-compatible APIsAnything that speaks that API.
- Local modelsOllama or LM Studio, with no key.
What makes the difference
A dot is one personal agent inside ChatGPT: it works on OpenAI's cloud computer, shares your ChatGPT memory and plugins, and asks for approval according to rules you set. APX gives you several named agents organized by projects and a task board, running on your computer or a server you control, with the model providers and coding agents you choose. OpenAI says it plans to let you add more dots, so the difference today is less about having one agent and more about where the work runs and which ecosystem holds it.
Try it on real work
Ask each to check your calendar every morning and follow up on one open project for a week. Compare what it remembers, where its files end up and how you approve its actions.
Sources and scope
Written by APX, using the primary sources below. This is a documented-feature comparison, not a hands-on benchmark or a security audit. Features, plans and terms can change. A missing detail is not a missing feature.
APX
Product names and logos belong to their respective owners. No affiliation or endorsement is implied.
Keep comparing
- APX vs Hermes AgentA project crew or a self-improving assistant?
- APX vs OpenClawYour project crew or your personal assistant?
- APX vs OpenBotTwo local crews. Different ways to own the work.
- APX vs Claude CoworkA crew for your projects or Claude on your files?
- APX vs ChatGPT dotsA project crew or one always-on agent in ChatGPT?
- APX vs ManusA project crew or a general agent in the cloud?
- APX vs DevinA project crew or an AI software engineer?
- APX vs PaperclipA project crew or an agent company?
- APX vs ViktorYour own crew or an AI teammate in Slack?
- APX vs Grok BotYour own hardware or a shared cloud computer?
- APX vs MuseA project crew or Meta's personal agent?
- APX vs InstinctA project crew or an assistant you text?




