Native DSH plugin that lets text-only agents inspect video metadata, understand scenes with optional ASR, and answer time-anchored questions — all through OpenAI-compatible vision/ASR endpoints, no provider lock-in.
DSH integration
Native runtime
Author-claimed
Safety audit
Unaudited
Last verified
2026-08-30
License
MIT
01What can it help you accomplish?
Inspect a local video's technical specs before deeper analysis
Compact metadata JSON via `video_probe`: container, duration, resolution, fps, codecs, audio tracks, subtitles
Text-only DSH agents and developers who need cheap, instant video metadata without decoding frames
Understand video content and answer time-anchored questions for text-only DSH agents
Structured evidence JSON from scene-change-aware frame sampling plus optional timestamped ASR; `video_ask` returns grounded answers with confidence and supporting timestamps
DSH agents that must reason about scenes, speech, or specific moments (e.g. "at 3:20") in local video
02How to install into DeepSeek Harness
Not specified by the author
03DSH integration and capability boundaries
Native DSH plugin — text-only agents call `video_probe` / `video_analyze` / `video_ask` tools; vision & ASR use OpenAI-compatible `baseUrl` + `model` + key endpoints.
video_probe — instant metadata
local video file path→compact metadata JSON: container, duration, resolution, fps, codecs, audio tracks, subtitles
video_analyze — content understanding
local video file; optional ASR key env var→structured evidence JSON from scene-change-aware frame sampling fused with an OpenAI-compatible vision model; optional timestamped ASR transcript
video_ask — time-anchored Q&A
a prior analysis / transcript plus a natural-language question with time references→grounded answer with confidence and supporting timestamps, re-sampling frames from the matched windows
04Who is it for? When not to use it?
Good for
- Text-only DSH agents and developers who need cheap, instant video metadata without decoding frames
- DSH agents that must reason about scenes, speech, or specific moments (e.g. "at 3:20") in local video
Not for
- Requires `ffmpeg` and `ffprobe` on `PATH`; the plugin delegates all media work to them and does no native decoding.
05Compatibility, maintenance and safety notes
- Scene-change detection requires ffmpeg ≥ 6.0 (the `scdet` filter); videos without detectable cuts fall back to uniform midpoint sampling.
- Requires `ffmpeg` and `ffprobe` on `PATH`; the plugin delegates all media work to them and does no native decoding.
- ASR is strictly additive: if `asrApiKeyEnv` is unset or the provider fails, visual analysis still completes and `transcript` is `null`.
MIT license · latest release v0.3.1 (published 2026-08-18) · default branch main
06Frequently asked questions
How do I install dsh-video-lens for DeepSeek Harness?
The public README confirms the plugin needs `ffmpeg` and `ffprobe` on your `PATH` (ffmpeg ≥ 6.0 for scene-change detection), but the documented install steps were truncated in the snapshot we reviewed — check the repo's README for the exact `dsh` install/clone commands before deploying.
What are the prerequisites before using it?
Two things from the README: `ffmpeg` and `ffprobe` must be on `PATH` (all media work is delegated to them, no native decoding), and ffmpeg must be ≥ 6.0 so the `scdet` filter can detect scene changes. Videos without detectable cuts fall back to uniform midpoint sampling.
How does it connect to DeepSeek Harness?
It is a native DSH plugin: text-only LLM agents call `video_probe`, `video_analyze` and `video_ask` as tools. Vision and ASR are wired through OpenAI-compatible endpoints configured via `baseUrl` + `model` + a key env var, so it never locks you into a single provider.
How is it different from just calling an LLM on a video?
It does the media work itself — ffprobe metadata, ffmpeg `scdet` scene sampling and frame extraction, optional ASR — then fuses sampled frames with an OpenAI-compatible vision model into structured evidence JSON, and adds `video_ask` for time-anchored Q&A (e.g. "at 3:20") with confidence and supporting timestamps.
What happens if the ASR provider fails or no key is set?
ASR is strictly additive: if `asrApiKeyEnv` is unset or the provider fails, the visual analysis still completes and `transcript` is `null`. The plugin degrades gracefully instead of erroring out.
07Related DSH workflows
modlens
by liustack
Vision bridge for text-only models: paste an image, get structured JSON evidence (OCR, layout, semantics).
agent-vision-toolkit
by anionex
Vision toolkit and skills that give text-only LLMs eyes — multi-image understanding, image Q&A, OCR, frontend UI restoration and GUI automation, with optional agent integration.
dsh-vision-router
by ysr666
Eyes for text-only DeepSeek Harness agents: built-in free vision chain (no key) + pixel-level vision tools (Q&A, grounding, crop, pixel diff, colors, OCR, SVG trace, cutout, screenshots). One-command install, no Python, image turns work like ordinary tool-calling turns.
dsh-vision-toolkit
by anionex
为纯文本 DSH Agent 提供 10 个结构化视觉工具：意图感知图片问答、长截图 OCR、原始像素 grounding、UI 还原、像素 diff 等
08Data and sources
A [DeepSeek Harness](https://github.com/deepseek-ai/deepseek-harness) (DSH) plugin that lets text-only LLM agents unders…
v0.3.1. The plugin never locks you into a provider: vision and ASR are both OpenAI-compatible endpoints configured via `…
This page is generated from the project’s public documentation, repository metadata and a structured parse of DSH Plugins; last verified on 2026-08-30. Found an error? Submit a correction.
Best DeepSeek Harness Plugins
Twelve plugins worth installing first — picked from the whole catalog, across every category.