swift-ai-sdk 0.2.0 enables Apple computer use

// 1h agoPRODUCT UPDATE

swift-ai-sdk 0.2.0 enables Apple computer use

Zaid Mukaddam has released swift-ai-sdk 0.2.0, a major update that transitions the library from simple model querying to active agency on iOS and macOS. This update introduces native computer use with OpenAI and Anthropic, a full Model Context Protocol (MCP) client, ten new providers, structured repair, and support for images, speech, and video.

// ANALYSIS

This release brings powerful agentic AI capabilities natively to the Apple developer ecosystem, making it easier than ever to build complex local and cloud-based AI workflows without the overhead of web-based frameworks.

* Computer use on OpenAI and Anthropic allows developers to build native desktop automation features.

* The full Model Context Protocol (MCP) client allows native Swift applications to seamlessly integrate with any MCP server.

* Support for ten new providers and structured repair ensures robust multi-provider application designs.

// TAGS

swiftiosmacosswift-ai-sdkmcpcomputer-useaiopen-source

DISCOVERED

1h ago

2026-07-15

PUBLISHED

2h ago

2026-07-15

RELEVANCE

7/ 10

AUTHOR

zaidmukaddam

// KEEP READING

More AI developer news from the feed

EXPLORE FULL FEED

OPEN SOURCE16m ago

Perplexity open-sources WANDR research benchmark

Perplexity AI has open-sourced WANDR (Wide ANd Deep Research), an evaluation benchmark and dataset consisting of 500 production-grade tasks designed to test AI research agents. The benchmark measures an agent's ability to conduct complex, multi-step web research involving wide entity discovery and deep fact verification.

UPDATE42m ago

ChatGPT/Codex Regression Bug Crashes Embedded Browser

Following the merger of the ChatGPT and Codex applications, a critical regression bug has emerged where dragging and dropping local files into the embedded browser causes a crash. This issue directly disrupts workflows for the ChatCut plugin, which requires importing local media files into the in-Codex video editing interface.

RESEARCH1h ago

PRISM Edit unlocks temporal LLM editing

PRISM Edit is a model editing method for LLMs that resolves temporal knowledge conflicts by optimizing a single polysemous vector to encode multiple time-bound answers. Leveraging the model's inherent modulation pathways, it routes prompts to the correct historical or current facts without requiring architectural modifications.