# rudrankriyam/Foundation-Models-Framework-Lab

A practical lab for building, testing, and evaluating apps with Apple's Foundation Models framework.

Repository: https://github.com/rudrankriyam/Foundation-Models-Framework-Lab
Canonical: https://ross.abutalabs.com/products/foundation-models-framework-lab
Language: Swift
License: MIT
License Family: permissive
Topics: ai, apple-intelligence, foundation-models, foundation-models-framework, generative-ai, healthkit, ios, llm, macos, multilingual, rag, speech-recognition, swift, swiftui, text-to-speech, tool-calling, xcode, apple-foundation-models, large-language-models, on-device-ai
Last push: 2026-08-25T19:37:05+00:00

## Health v2 (maintenance only)
Score: 82/100 (v2, computed 2026-09-03T02:20:16.233290+00:00)
- activity 99, release rhythm 90, longevity 32
- inputs: {"age_days": 450, "days_push": 8, "days_rel": 71, "gap_med": 4.0, "n_releases_24m": 5}
- flags: none
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 1177, forks 69 (observed 2026-08-28T04:03:52.841831+00:00)

## What it is
A native iOS and macOS workbench app for learning, testing, and evaluating Apple's Foundation Models framework. It provides editable recipes, guided labs, a playground for prompt and tool experimentation, and run inspection with exportable evidence.

## Use cases
- experiment with Apple Foundation Models prompts and tools on device
- learn the Foundation Models framework through guided labs and recipes
- compare model adapters and inspect run transcripts and token usage
- test tool calling and streaming responses from Apple Intelligence
- build and evaluate on-device LLM apps for iOS and macOS
- export reproducible Swift code from prompt experiments

## When to choose
- you are developing with Apple's Foundation Models framework on iOS 26+/macOS 26+
- you want a hands-on playground to explore Apple Intelligence on-device models
- you need to compare adapters, tools, and configurations with persisted run evidence

## When to avoid
- you need cross-platform or non-Apple LLM tooling
- your devices do not run iOS/macOS 26+ with Apple Silicon and Apple Intelligence enabled
- you want a library or SDK to embed rather than a standalone learning and testing app

## Facets
- artifact type: application
- maturity: active
- function: llm-inference, rag, speech-recognition, tts, prompt-engineering, developer-tools, gui
- domain: artificial-intelligence, large-language-models, developer-tools, apple-ecosystem
- platform: -
- tags: apple-foundation-models, apple-intelligence, on-device-ai, swiftui, playground, tool-calling, recipes, labs, ios, macos, swift

## Member repositories
- rudrankriyam/Foundation-Models-Framework-Lab (main) score 82

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:03:52.841831+00:00.
- Health v2: computed from the inputs above; adoption is never an input.
- Inferred fields (summary, facets, guidance): AI-extracted, prompt v1, taxonomy v1, on 2026-08-30T06:26:18.131139+00:00, confidence not recorded.
  - readme: https://github.com/rudrankriyam/Foundation-Models-Framework-Lab (fetched 2026-08-28T04:03:52.841831+00:00, sha 6eca739bdb18)
- Data as of 2026-08-30T08:39:29.467469+00:00.