OpenAI Launches ChatGPT Plugin That Reads and Replies to iMessages on Mac
OpenAI has released a plugin allowing ChatGPT to read and respond to Apple iMessages on Mac, currently limited to ChatGPT Work and Codex users. The feature requires users to grant Full Disk Access and contact permissions, and arrives amid an active lawsuit between Apple and OpenAI.
OpenAI has released a plugin that lets ChatGPT search, read, and respond to Apple iMessages directly from a Mac desktop. The feature is currently limited to ChatGPT Work and Codex users, according to reporting from Engadget and Bloomberg.
In a demonstration posted by OpenAI, a user asked ChatGPT to find conversations they had missed the previous day in the Messages app. The chatbot located the relevant threads, then drafted and sent a reply on the user's behalf — all without leaving the ChatGPT interface.
How access works
The integration is opt-in, but enabling it requires several deliberate steps. According to Bloomberg, users must:
- Grant ChatGPT access to on-device Messages history during setup
- Enable Full Disk Access for ChatGPT in macOS System Settings
- Allow ChatGPT to view contact names
- Authorize access to macOS automation tools
The multi-step permission process means the plugin cannot be enabled accidentally — a detail OpenAI appears to have built in given the sensitivity of granting an AI chatbot access to private message content.
Unclear relationship with Apple
It is not confirmed whether OpenAI built this plugin in partnership with Apple or reverse-engineered access independently. Apple has a documented history of blocking third-party access to iMessage without its cooperation. In 2024, Apple repeatedly disabled the Beeper Mini app's iMessage integration until the company abandoned efforts to restore it.
The timing is notable: Apple sued OpenAI in July, alleging trade secret theft. According to the lawsuit, Apple claims OpenAI specifically recruited its employees to obtain confidential company information. Neither company has commented publicly on how the ongoing litigation might affect the Messages integration or its future availability.
Privacy considerations
Giving any third-party application Full Disk Access on macOS is a significant permission grant — it exposes not just Messages data but potentially other files and system information. Combined with contact list access, the plugin gives ChatGPT visibility into both message content and the identities of the people a user communicates with. OpenAI has not disclosed specific data retention or training-use policies for message content processed through this plugin.
What this means: This is a feature launch, not a new model release — it extends ChatGPT's existing capabilities into a new data source (iMessage) rather than introducing new model weights. The restriction to ChatGPT Work and Codex users suggests OpenAI is testing the integration with a smaller, likely more security-conscious user base before any broader rollout. The unresolved question is whether Apple will tolerate this level of access given its active lawsuit against OpenAI and its track record of cutting off unauthorized iMessage integrations. Users considering enabling this plugin should weigh the convenience against the broad permissions required, particularly Full Disk Access, which extends well beyond what's strictly needed to read and send messages.
Related Articles
OpenAI Launches Apple Messages Plugin, Letting ChatGPT Read, Draft, and Send Texts
OpenAI has launched an Apple Messages plugin that lets ChatGPT read, sort, draft, and send texts on a user's behalf. The company says the plugin runs locally and does not index all messages, though it has not detailed exactly how that works.
OpenAI Adds Apple Messages Plugin to ChatGPT for Mac
OpenAI has added an Apple Messages plugin to ChatGPT for Mac, allowing the AI to read, search, and send iMessage, SMS, and RCS conversations. The feature is available across all plans but currently limited to Apple silicon Macs.
OpenAI Previews 'Private Safety Processing' to Detect Abuse Without Retaining Customer Data
OpenAI is previewing Private Safety Processing to select customers, an automated system that monitors for misuse across multiple sessions without retaining any customer data. The move directly contrasts with Anthropic's July policy allowing 30-day data retention for 'covered models' like Fable.
OpenAI Adds Transparent Background Generation to GPT-Image-2 API
OpenAI is previewing a transparent background feature for GPT-Image-2 through its API, letting developers generate PNGs with no background baked in at generation time. The company claims this produces cleaner results than traditional background removal, particularly on difficult edges like glass or thin fibers.
Comments
Loading...