Skip to main content

Find moments in your videos. Agent-first CLI for Marlin-2B: dense captioning + temporal grounding, local or hosted.

Project description

Marlin

Video understanding on your Mac. marlin is the command-line tool for Marlin-2B — a 2B video VLM for the two questions you actually ask a video: what is happening, and when. Runs free and local on Apple Silicon — no API key, no Hugging Face account.

Try it live Hugging Face PyPI

  • marlin caption → a Scene description + a <start>–<end> event timeline
  • marlin find → the single start → end span where your query happens

Install

Apple Silicon (M-series Mac) only for now. NVIDIA / other platforms are coming as a separate optimized build.

uv tool install nemostation      # or: pipx install nemostation
marlin setup                     # one-time: sign in, build the local engine
marlin caption clip.mp4          # describe what's in a video
marlin find clip.mp4 "a deer crossing"   # locate when it happens → start → end

First run opens your browser for a quick sign-in (two questions, then Google), detects your Mac, and builds the local MLX engine. The 8-bit weights are public — nothing gated. Add --json to any command for parseable output.

What it produces

marlin caption "video.mp4"what's in it

Marlin caption example

marlin find "video.mp4", "gunfight"when it happens

Marlin find example

Each call runs one model pass on one bounded clip (~2 min at 2 fps) — the same contract as the inference server. For longer videos, window with ffmpeg and loop.

Why Marlin

At 2B params it's the strongest open model in its weight class on dense captioning (DREAM-1K, CaReBench) and natural-language temporal grounding (TimeLens-Bench) — competitive with Gemini-2.5 at a fraction of the cost. See the benchmarks on the model card.

Use it from an agent

marlin skills install        # → .claude/skills/ + .agents/skills/

Installs the video-understanding skill so Claude Code / Codex use marlin as "eyes on a video" — clip-length and single-find limits baked in. Every verb honors --json (stdout parseable, progress on stderr).

Links

Project details


Download files

Download the file for your platform. If you're not sure which to choose, learn more about installing packages.

Source Distribution

nemostation-0.1.14.tar.gz (39.9 kB view details)

Uploaded Source

Built Distribution

If you're not sure about the file name format, learn more about wheel file names.

nemostation-0.1.14-py3-none-any.whl (44.2 kB view details)

Uploaded Python 3

File details

Details for the file nemostation-0.1.14.tar.gz.

File metadata

  • Download URL: nemostation-0.1.14.tar.gz
  • Upload date:
  • Size: 39.9 kB
  • Tags: Source
  • Uploaded using Trusted Publishing? No
  • Uploaded via: uv/0.8.13

File hashes

Hashes for nemostation-0.1.14.tar.gz
Algorithm Hash digest
SHA256 7824133f141b521d37ceeb3fb71c87ac3d590ef84e4294fdb53a1122bb8e7506
MD5 786adf580fbd2c975bee289fc3ebe1d5
BLAKE2b-256 f3b917785ecd74143e9870d6956d8bd3badecde72048a60f9bb9a1f5b3aa6e5e

See more details on using hashes here.

File details

Details for the file nemostation-0.1.14-py3-none-any.whl.

File metadata

File hashes

Hashes for nemostation-0.1.14-py3-none-any.whl
Algorithm Hash digest
SHA256 ff50bddbe180845b2dbb936da6b2b4e7f7eb326469188d4f11368f520f6419d7
MD5 f45145f6d2ce6e6e37c0a08293e113cb
BLAKE2b-256 503d1757bf3aae787a29bbc1b40674ef2a6b8001c729be9bc3c43b82bea385e1

See more details on using hashes here.

Supported by

AWS Cloud computing and Security Sponsor Datadog Monitoring Depot Continuous Integration Fastly CDN Google Download Analytics Pingdom Monitoring Sentry Error logging StatusPage Status page