Swift Package IndexPackages for keyword “foundation-models”
These packages are available as a package collection, usable in Xcode or SwiftPM.
Swarm
Type-safe tools, on-device inference, multi-agent workflows, memory, and guardrails, in one Swift-native runtime
coreai-kit
Swift SDK for running chat, vision and speech models on iPhone and Mac with Apple's Core AI. Model download and caching, FoundationModels integration, and runnable examples with documented OS, SDK and model requirements.
Conduit
🦑 Unified Swift SDK for LLM inference across local and cloud providers
ManifoldKit
Reusable SwiftUI chat framework for local and cloud LLM inference on Apple platforms
DProvenanceKit
Local-first AI reasoning observability for Swift: record, diff, attest, and CI-gate agent execution paths. Complements OpenTelemetry and tools like LangSmith — does not replace them.
HybridRouterKit
iOS app + Swift package that routes each conversation turn between Apple on-device, Apple Private Cloud Compute, and Claude.
LocalLLMClient
Swift package to run local LLMs on iOS, macOS, Linux
TranscriptDebugMenu
A SwiftUI library that provides a debug menu for viewing and copying LanguageModelSession transcripts.
olleh
An Ollama-compatible CLI for Apple's Foundation Models
swift-language-models
A unified Swift API for Apple’s Foundation Models-style experience across cloud and local LLM providers. Bring OpenRouter, Ollama, Claude, GPT, Gemini and more into a consistent LanguageModelSession interface, with tool calling, guided generation, streaming, reasoning and typed model catalogs. Multi-provider support, with more integrations coming.
SwiftVectorKit
On-device semantic code search and vector indexing for Swift, Xcode, and AI agents. 100% local on Apple Silicon.
FoundationRadar
Measure what Apple's Foundation Models stack can actually do on this device — availability, real context size, real latency, PCC signals — instead of trusting a boolean.
ModelRelay
Composable AI workflows for Swift: small typed steps, a model per step, tools, MCP and on-device models.
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
swift-context-management
Smart context management for Swift LLM applications. Prune, summarize, and restructure conversation history automatically and more...
15 packages.