#110110th of 144 in Agent frameworks and SDKs
openai
Swift client library for the OpenAI API and compatible providers
Documentation ↗
(opens in a new tab)Website ↗
(opens in a new tab)Repository on GitHub ↗
(opens in a new tab)
- Stars
- 2.9k
- License
- MIT
- Last commit
- Oct 2026
- Last release
- Oct 2026
- Language
- Swift
Missed the latest GitHub check; these facts may be older.
Overview
A community-maintained Swift package that wraps the OpenAI REST API: Responses, Chat Completions, images, audio, embeddings, moderations, Assistants, files and models. It supports async/await, closures and Combine, plus streaming and request cancellation. A configurable host, base path and a relaxed parsing mode let it talk to other OpenAI-compatible providers such as Gemini, DeepSeek, Perplexity and OpenRouter.
Who it is for: Swift and iOS/macOS developers calling OpenAI or compatible APIs
Strengths
- Covers Responses, Chat Completions, audio, images, embeddings, Assistants and MCP tools in one package
- Offers async/await, closure and Combine APIs, with request cancellation for each
- Configurable host, port, base path and headers, with a relaxed parsing mode for other providers
- Installs through Swift Package Manager with Xcode or Package.swift
Weaknesses
- Swift and Apple-platform oriented; no support for other languages
- Needs a hosted API key; the README warns against embedding it in client apps
- Compatibility with non-OpenAI providers depends on their API matching OpenAI's
- Some documented image limits (256x256 to 1024x1024, DALL-E era) look dated
What it needs
- no GPU
- Needs OpenAI API key or OpenAI-compatible provider, Swift Package Manager
- Models: OpenAI Responses API, OpenAI Chat Completions API, OpenAI-compatible providers (Gemini, DeepSeek, Perplexity, OpenRouter)
Also in Agent frameworks and SDKs
See all 144| Rank | Project | Score |
|---|---|---|
| 1 | ppt-masterAgent skill that turns documents into natively editable PowerPoint decks | 96 out of 100 |
| 2 | openai-agents-pythonPython SDK for multi-agent workflows with handoffs, guardrails and tracing | 92 out of 100 |
| 3 | mastraTypeScript framework for building AI agents, workflows and MCP servers | 92 out of 100 |
| #4 | browser-usePython library that lets an LLM agent control a web browser | 90 out of 100 |
| #5 | copilotkitReact and Angular SDK for adding agent chat and generative UI to apps | 90 out of 100 |