PanWatch
PanWatch, AI stock monitoring for A-shares, HK & US markets, powered by TradingAgents. Portfolio insights, real-time alerts & automated reports.｜盯盘侠：覆盖 A股/港股/美股的 AI 盯盘、持仓分析、实时提醒与自动报告。
Runssource: GitHubhomepagePythonMITcommit d2d2a869b735
Python, MIT licensed. The project labels itself: a share, agent, ai, ai agent, akshare, deepseek, fastapi and fintech.
PanWatch runs. An Argusic agent installed it in 6.3 minutes and hit 2 errors and fixed every one without help on a clean machine with no GPU, and the whole session was recorded.
Python 3.12 venv with all deps installed, 782/784 tests pass (3 skipped are Windows-only), server starts and responds 200 on /api/health, frontend builds cleanly via pnpm, WeasyPrint PDF renders Chinese characters as extractable text.
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.
- No CJK fonts on system; WeasyPrint PDF tests failed asserting Chinese text in PDF text layer2.5 minutes
- pnpm not installed globally, needed for frontend builds1.5 minutes
- Install time
- 6 minutes
- Cold machine to finish
- 8 minutes
- Errors hit and fixed
- 2 hit, 2 fixed with no human help
- How the result was proved
- pytest tests/ -q --tb=no returned 782 passed, 3 skipped; curl -s -o /dev/null -w '%{http_code}' http://localhost:8000/api/health returned 200
- Model tokens used
- 57,253
- Exact commit tested
- d2d2a869b735
- 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.
src/modules/reporting/pdf_export.py | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) All 782 tests pass, 3 skipped (Windows-only). The server starts and serves HTTP 200 on `/api/health… **Errors found and fixed:** 1. **pnpm not available** – Installed pnpm to `~/.npm-global` via `npm install -g pnpm --prefix` 2. **CJK fonts missing** – WeasyPrint rendered PDFs but Chinese characters appeared as `.notdef` bo… tokens used 57,253 All 782 tests pass, 3 skipped (Windows-only). The server starts and serves HTTP 200 on `/api/health… **Errors found and fixed:** 1. **pnpm not available** – Installed pnpm to `~/.npm-global` via `npm install -g pnpm --prefix` 2. **CJK fonts missing** – WeasyPrint rendered PDFs but Chinese characters appeared as `.notdef` bo…
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 6.3 minutes, faster than the median of the 4 comparable projects Argusic has measured.
- Recovered from all 2 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 5 a-share projects Argusic has installed and timed, PanWatch was the 2nd fastest to reach a running state, and 3 of 5 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 6.3 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)
a-shareagentaiai-agentaksharedeepseekfastapifintechlanggraphllmmcpopenaipwaquantself-hostedstockstock-analysisstock-markettrading-agentstrading-bot
Embed the badge
Markdown for the project README. It links back here; terms on the terms page.
[](https://argusic.com/subject/panwatch)Questions
- Does PanWatch run?
- Yes. PanWatch runs. Argusic installed and launched it on a clean machine in 6 minutes, hitting 2 errors on the way, and recorded the session.
- How did Argusic test PanWatch?
- On a fresh, disposable machine, with every command recorded and the repository pinned at commit d2d2a869b735. One attempt is recorded, and the full method is on the methodology page.
- What did it cost to test PanWatch?
- The run that produced this verdict cost $0.06: real compute and model cost, not a list price per million tokens. It is recorded on that run's page.
- How long does PanWatch take to install?
- 6.3 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 PanWatch need a GPU?
- Not to start. Argusic reached a running state on a machine with no GPU.
- What goes wrong when installing PanWatch?
- 2 things broke in the recorded run, and 2 were fixed without human help. Each one, and the time it cost, is listed on this page.
- How does PanWatch compare with the alternatives?
- Of the 5 a-share projects Argusic has installed and timed, PanWatch was the 2nd fastest to reach a running state, and 3 of 5 reached one at all.
- Where is the evidence for PanWatch?
- 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.