ViNote
ViNote(视记AI)|DeepSeek Harness SDK 驱动的开源视频知识 Agent。以工具编排、SQLite 会话恢复和流式交互,串联 YouTube / Bilibili 检索、下载、转写与笔记生成,支持视频问答、知识卡片和思维导图。FastAPI + React,支持 OpenAI 兼容接口模型。
Runssource: GitHubPythonMITcommit e8e46a144caa
Python, MIT licensed. The project labels itself: agent harness, ai agent, bilibili, deepseek harness, deepseek harness sdk, fastapi, faster whisper and knowledge management.
ViNote runs. An Argusic agent installed it in 4 minutes and hit 3 errors and fixed every one without help on a clean machine with no GPU, and the whole session was recorded.
ViNote v1.4.0 backend serves SPA on port 8999, SQLite initialized with 17 categories, all 50+ API endpoints respond, full test suite passes (214 backend + 18 frontend + media smoke).
What the agent ended up with on a clean machine, in its own words. How this is measured
Measured by Argusic on a fresh machine every time. Every number links to its evidence. Argusic Score 100 of 100 (the mean of this project's run scores).
At a glance
Subject data from GitHub, linked at the top of this page, refreshed . Test data by Argusic (CC BY 4.0); every number links to a run page with the full log, the recording, and their sha256 hashes.
What was measured
From the run that decided this verdict. Every line is a recorded value, not an estimate.

What went wrong, in the agent's own words
The agent's own words, worst first, never rewritten into advice.
- test_content_generation.py and test_reasoning_effort_config.py fail on sibling imports2 minutes
- uv not found in PATH1 minute
- pytest module not found at import1 minute
- Install time
- 4 minutes
- Cold machine to finish
- 15 minutes
- Errors hit and fixed
- 3 hit, 3 fixed with no human help
- How the result was proved
- backend pytest: 214 passed (221 subtests); frontend node --test: 18 passed; media smoke (FFmpeg+HTTP pipeline): PASSED; curl /health returned 200
- Model tokens used
- 87,402
- Exact commit tested
- e8e46a144caa
- Container image
- sha256:cdd920bce783
What was not measured
The other half, so you can see exactly how far this evidence goes. A gap is printed as a gap and never filled in.
- Peak GPU memory
- this ran on a CPU machine, so there was no GPU to sample
- Behaviour over a long run
- each attempt uses the smallest documented settings and a fixed time budget, so this measures whether it runs, not how it holds up under load
The end of the recording
The last lines of the terminal session that decided this verdict, exactly as they were recorded.
Here is the final report. **Initial setup issues and fixes:** 1. `uv` not installed → installed via `curl -LsSf https://astral.sh/uv/install.sh | sh` (1 min) 2. `pytest` not in dependencies → added via `uv add --dev pytest` (1 min) 3. Two test files had wrong sibling imports (`from test_text_quality import`) → changed to absolute… **What was verified:** - Backend serves HTTP 200 on `/health` and all 50+ API endpoints respond correctly - SQLite database auto-initialized with 17 default categories and schema - **Backend pytest suite**: 214 passed (221 subtests) in 34s - **Frontend node test suite**: 18 passed in 1.4s - **Media smoke test** (real FFmpeg + HTTP pipeline with embedded subtitles, no real LLM/ASR): PASS… **Not verified:** Browser smoke tests require Playwright + Chrome, both unavailable.
Replay the whole session, every command from a clean machine to this point.
How it was tested
One agent, one container, no human help. It installs the project the way its own documentation says to, runs it, and fixes what breaks. Everything below is recorded as it happened: the terminal session, the log and the exact commit. The full method.
Strengths and limits
Measured facts, not opinions. How this is written.
What went well
- Reached a running state on a clean machine, with the session recorded.
- Installed in 4 minutes, faster than the median of the 10 comparable projects Argusic has measured.
- Recovered from all 3 errors without a human stepping in, which says the failures are documented well enough to solve.
- Ran without a GPU, so it does not need one to start.
- Licensed MIT, as reported by its host.
What did not, or is not known
- Measured once so far. A single attempt shows it can run, not that it runs reliably.
Of the 11 agent-harness projects Argusic has installed and timed, ViNote was the 6th fastest to reach a running state, and 9 of 11 reached one at all.
What it is a reasonable choice for
- Trying it on a laptop or a small server: it reached a running state without a GPU.
- A quick evaluation: it was running 4 minutes after the clone.
Also tested, in the same area
Every one of these was installed and run by Argusic on a clean machine. Nothing appears here that was not tested.
Run history
Topics (from GitHub)
agent-harnessai-agentbilibilideepseek-harnessdeepseek-harness-sdkfastapifaster-whisperknowledge-managementopenai-compatiblereactsqlitetool-callingvideo-searchvideo-to-notesyoutubeyt-dlp
Embed the badge
Markdown for the project README. It links back here; terms on the terms page.
[](https://argusic.com/subject/vinote)Questions
- Does ViNote run?
- Yes. ViNote runs. Argusic installed and launched it on a clean machine in 4 minutes, hitting 3 errors on the way, and recorded the session.
- How did Argusic test ViNote?
- On a fresh, disposable machine, with every command recorded and the repository pinned at commit e8e46a144caa. One attempt is recorded, and the full method is on the methodology page.
- What did it cost to test ViNote?
- The run that produced this verdict cost $0.09: real compute and model cost, not a list price per million tokens. It is recorded on that run's page.
- How long does ViNote take to install?
- 4 minutes in the run that decided this verdict, from a clean machine to a running state. That is one measured attempt, not an average.
- Does ViNote need a GPU?
- Not to start. Argusic reached a running state on a machine with no GPU.
- What goes wrong when installing ViNote?
- 3 things broke in the recorded run, and 3 were fixed without human help. Each one, and the time it cost, is listed on this page.
- How does ViNote compare with the alternatives?
- Of the 11 agent-harness projects Argusic has installed and timed, ViNote was the 6th fastest to reach a running state, and 9 of 11 reached one at all.
- Where is the evidence for ViNote?
- The recorded run is on this page, each linking to its full log and terminal recording, stored with a sha256 fingerprint so it cannot be quietly altered.