Swift Package Index

Packages for keyword “llm”

These packages are available as a package collection, usable in Xcode or SwiftPM.

• Arbiter

  Framework to talk to AI models and intelligently route

  • sabby3861/Arbiter
  • Active about 2 months ago
  • 15 stars

• Cast

  Type-safe structured output from any local LLM on Apple Silicon. Constrained decoding for MLX Swift.

  • jaylann/Cast
  • Active 2 months ago
  • 0 stars

• FiniteExtract

  On-device structured extraction engine (Swift Package)

  • FiniteHQ/finite-extract
  • Active 3 months ago
  • 1 stars

• MockableKit

  AI-powered mock data generator for Swift. Make Mocks in seconds, not minutes. Generate realistic Decodable mock data from Gemini with zero boilerplate.

  • senolmurat/MockableKit
  • Active 5 months ago
  • 1 stars

• Adapt

  On-device LoRA personalization for iOS and macOS. Trains, evaluates and rolls back adapters locally — no server, no Python.

  • asaptf/swift-adapt
  • Active 2 months ago
  • 1 stars

• swift-embeddings

  Text embeddings and reranking for Swift — one protocol, providers for Voyage, Jina, Cohere, OpenAI and on-device NaturalLanguage. Back-deploys to iOS 15.

  • Dean151/swift-embeddings
  • Active 4 months ago
  • 2 stars

• swift-llama

  Run LLMs natively in Swift. Actor-safe. Streaming. Tool-calling. Metal-accelerated.

  • profclaw/swift-llama
  • Active 6 months ago
  • 2 stars

• SwiftLLM

  Swift Package — 3-line LLM integration for iOS/macOS · Claude + OpenAI · async/await · zero dependencies

  • pintaste/swift-llm
  • Active 5 months ago
  • 1 stars

• ARCP

  Swift reference SDK for ARCP (Agent Runtime Control Protocol).

  • agentruntimecontrolprotocol/swift-sdk
  • Active 3 months ago
  • 1 stars

• swift-tiktoken

  A pure Swift implementation of OpenAI's tiktoken tokenizer

  • DePasqualeOrg/swift-tiktoken
  • Active 10 months ago
  • 6 stars

• WatermarkPurge

  On-device multi-pass text watermark remover for Apple Silicon (Swift + MLX)

  • asaptf/swift-watermark-remover
  • Active 2 months ago
  • 1 stars

• unswayed

  tatistical parity gate for swapping AI models: freeze a suite, sample every provider, fail CI only on certified regressions with an honest 'undecided' when n can't prove anything

  • Umer9538/unswayed
  • Active 3 months ago
  • 1 stars

• VeloxQuant

  Swift SDK for VeloxQuant (Apple Silicon MLX KV-cache compression) — sibling to the TS, Go, Rust, and Kotlin client SDKs.

  • rajveer43/veloxquant-swift
  • Active about 1 month ago
  • 0 stars

• GoogleGenerativeLanguage

  Swift SDK for the Google Generative Language API (Gemini). Auto-generated from Google's OpenAPI spec. No official Swift SDK exists. This fills the gap.

  • atacan/GoogleGenerativeLanguage
  • Active 7 months ago
  • 1 stars

• Yazman

  Türkçe teknik makale yazım denetleyicisi — yerel LLM + RAG ile. Turkish technical article wording checker powered by local LLM and RAG.

  • alpozcan/yazman
  • Active 8 months ago
  • 2 stars

• AccessibleText

  A macro designed to help make static text more accessible by generating dynamically scaling text instead.

  • Mcrich23/AccessibleText
  • Active about 1 year ago
  • 5 stars

• swift-context-management

  Smart context management for Swift LLM applications. Prune, summarize, and restructure conversation history automatically and more...

  • Silo-Labs/swift-context-management
  • Active 8 months ago
  • 12 stars

• Cachly

  Official Swift SDK for cachly — persistent AI memory and managed Valkey/Redis with semantic caching. Free tier, EU-hosted.

  • cachly-dev/cachly-swift
  • Active 6 months ago
  • 1 stars

• Previous Page