Skip to content

screenlens.stub

Nicolas Cravino edited this page Jul 22, 2026 · 7 revisions

id: screenlens name: ScreenLens repo_path: ~/Documents/sw30labs/repos/screen-lens-mlx remote_url: https://github.com/sw30labs/screen-lens-mlx.git primary_language: Python framework: LangGraph + oMLX (OpenAI-compatible) + OpenCLIP + ChromaDB ingested: 2026-04-11 last_commit_date: 2026-07-13 category: local-inference-mlx stacks: [mlx, langgraph, rag]

ScreenLens

Purpose

Local video scene intelligence for Apple Silicon (inspired by NVIDIA VSS, rebuilt from scratch). Processes screen recordings through a LangGraph-orchestrated pipeline: smart keyframe extraction, Qwen3.5-VL captioning via a local oMLX server, CLIP embedding, ChromaDB vector search, and LLM summarization — no cloud dependencies. v0.2 adds a reconstruction pipeline that classifies recordings (code / docs / PDF / GUI demo) and rebuilds source, docs, and demo artifacts from what was on screen. Renamed on GitHub to screen-lens-mlx (July 2026) when the CUDA-only fork screen-lens-dgx split off; this stub keeps the stable id screenlens.

Architecture

LangGraph StateGraph pipeline: Ingest → Caption → Embed → Classify → Plan → Reconstruct → QA (reflection, retry when incomplete) → Save. Search path: query → semantic search → summarize.

  • Hybrid keyframe detection: SSIM (scene change) + pHash (visual similarity) + HSV histogram (color) — only distinct screens are captured
  • Vision captioning via oMLX: dedicated omlx_client speaks the OpenAI-compatible VLM API (default http://127.0.0.1:8000/v1); auth via MLX_API_KEY/OMLX_API_KEY, model selection via MLX_MODEL/OMLX_MODEL/--omlx-model; dashboard-style URLs normalized to /v1. Replaced the original in-process mlx-vlm path (mlx-vlm and huggingface-hub dropped from deps — vision inference now sits behind the oMLX HTTP seam)
  • Fallback captioning: Ollama (llama3.2-vision) for cross-platform use
  • Helper modules: transcribe (audio) and OCR alongside the captioner
  • Launcher: idempotent Conda setup + launcher setup_and_run.sh (SCREENLENS_CONDA_ENV overrides env name)

Key Technologies

  • Framework: LangGraph; oMLX server for all VLM/LLM inference (Apple Silicon native)
  • Vision-Language: Qwen3.5-VL via oMLX OpenAI-compatible API
  • Embedding: OpenCLIP ViT-B-32
  • Vector DB: ChromaDB
  • CLI: Typer + Rich

Dependencies

langgraph, langchain, langchain-ollama, langchain-community, chromadb, open-clip-torch, opencv-python-headless, scikit-image, Pillow, numpy, torch, tqdm, typer, rich, pydantic. Apache-2.0, v0.2.0.

Tags

python, langgraph, mlx, apple-silicon, local-inference, chromadb, video, ocr

Cross-references

Clone this wiki locally