docs: add demo and social links to README

docs: update README to include a flowchart of the product pipeline and add a blog post link for Pozify

refactor: streamline evidence generation in coach summary; enhance JSON output contract and improve tokenization handling for local chat

chore: remove Linux-specific dependencies from pyproject.toml and requirements.txt; update README to clarify usage of Nemotron implementation for local model inference

chore: add pre-requirements.txt for torch installation; update pyproject.toml and requirements.txt with new dependencies for Linux platform

chore: add ninja-build and build-essential to package requirements; update README and documentation to reflect changes in model configuration and local Transformers usage

chore: update base model to NVIDIA-Nemotron-3-Nano-4B-BF16 across configurations and documentation; adjust max sequence length to 2048; upgrade GitHub Actions cache to v5

docs: update product demo image and enhance environment variable table formatting in README

feat: add support for local Transformers inference on Hugging Face Spaces with opt-in configuration

docs: refine hackathon README and add demo image

docs: update default coach-summary model to build-small-hackathon/pozify-coach-summary1 and clarify fallback behavior in documentation

docs: reorganize documentation structure and workflow

feat(coach): disable verifier by default

feat(slm): add llama.cpp coach summary provider

feat(coach): add local transformers provider

fix(hf-spaces): install mediapipe native libraries

fix(hf-spaces): avoid pickling analysis progress callbacks

feat(pose)!: use coco17 3d router features

feat(hf): use ZeroGPU for analysis

build: use python 3.10 and torch 2.11

Set default exercise router repo

pioritize BiLSTM model

Document Hugging Face router repo

Merge remote issue 4 updates

Add issue 10 training release assets

Merge branch 'main' into NLag/issue4

refactor(exercises): route pipeline through exercise objects

Implement frame-level issue markers

Merge branch 'main' into NLag/issue4

Add temporal router model selection

Implement exercise classifier router

Surface rep metrics in the app

chore: update pydantic and pydantic-core versions, adjust Python version in README, and enhance CI workflow with caching

chore: update short description in README and upgrade checkout action version in CI workflow

ci: configure Hugging Face Space sync

docs(readme): document real mode and annotated output

refactor(exercises): centralize exercise definitions

chore: add lefthook checks

feat(pose): add pluggable pose backends

feat(video): add intake quality gate

feat(pipeline): harden mock artifact contracts

first commit