open-webSearch
Multi-engine MCP server, CLI, and local daemon for agent web search and content retrieval, skill-guided workflows, no API keys.
Runs with mockssource: GitHubhomepageTypeScriptApache-2.0commit a61bc65fc5ed
TypeScript, Apache-2.0 licensed.
open-webSearch runs, with stand-ins for the services it depends on. An Argusic agent installed it in 30 minutes and hit 4 errors on a clean machine with no GPU, and the whole session was recorded.
npm install and npm run build compile cleanly; 35/38 tests pass (3 live tests excused for external network limits); the daemon starts, health endpoint returns HTTP 200, and DuckDuckGo search returns real results; Playwright-dependent features are unavailable because the container runs Node 18 (requires 20+).
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 77 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.
- playwright-core bootstrap.js calls process.exit(1) on Node < 20, killing test subprocesses before they run5 minutes
- test-bing-live.js: Bing HTTP scraping returns zero results from this environment2 minutes
- test-dialog-capture.js: requires Playwright with a real browser, which needs Node >= 201 minute
- test-article-fetch-live.js: HTTP 521 from target CSDN server1 minute
- Install time
- 30 minutes
- Cold machine to finish
- 16 minutes
- Errors hit and fixed
- 4 hit, 1 fixed with no human help
- How the result was proved
- node build/tools/runCurrentTests.js: 35 pass, 3 excused. curl -s -o /dev/null -w %{http_code} localhost:43213/health returned 200. open-websearch search 'test' --limit 1 --engine duckduckgo --json returned real results. open-websearch status --json returned capabilities JSON.
- Model tokens used
- 143,014
- Exact commit tested
- a61bc65fc5ed
- 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
- Behaviour against real services
- this run was verified against stand-in services only
The end of the recording
The last lines of the terminal session that decided this verdict, exactly as they were recorded.
Start time estimation: ~30 minutes total (install, fix, test, verify) **Install time**: `npm install` and `npm run build` both completed cleanly. **Daemon**: on port 43213, health returned HTTP 200, status daemon=running runtime=ready version=2.… **Tests**: `node build/tools/runCurrentTests.js` — 35 pass, 3 excused for external network limits (… **Fix applied**: one change to `src/config.ts` — added a Node.js version guard in `checkPlaywrightM… 2026-10-05T16:31:42.644894Z ERROR codex_core::session: failed to record rollout items: thread 01a10… tokens used 143,014 **Install time**: `npm install` and `npm run build` both completed cleanly. **Daemon**: on port 43213, health returned HTTP 200, status daemon=running runtime=ready version=2.… **Tests**: `node build/tools/runCurrentTests.js` — 35 pass, 3 excused for external network limits (… **Fix applied**: one change to `src/config.ts` — added a Node.js version guard in `checkPlaywrightM…
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
- Licensed Apache-2.0, as reported by its host.
What did not, or is not known
- Only reached a running state against stand-in services, so nothing here proves it works against the real ones.
- Took 30 minutes to install, slower than the median of the 27 comparable projects Argusic has measured.
- Hit 4 errors during setup, 3 of which were not solved.
- Measured once so far. A single attempt shows it can run, not that it runs reliably.
Of the 28 TypeScript projects Argusic has installed and timed, open-webSearch was the 28th fastest to reach a running state, and 20 of 28 reached one at all.
Run history
| tested by | attempt | outcome | score | cost USD | when |
|---|---|---|---|---|---|
| Argusic Runner | 1/3 | Runs with mocks | 77.00 | 0.23 |
Embed the badge
Markdown for the project README. It links back here; terms on the terms page.
[](https://argusic.com/subject/open-websearch)Questions
- Does open-webSearch run?
- open-webSearch runs, with mocks standing in for external services. Argusic installed and launched it on a clean machine in 30 minutes, hitting 4 errors on the way, and recorded the session.
- How did Argusic test open-webSearch?
- On a fresh, disposable machine, with every command recorded and the repository pinned at commit a61bc65fc5ed. One attempt is recorded, and the full method is on the methodology page.
- What did it cost to test open-webSearch?
- The run that produced this verdict cost $0.23: real compute and model cost, not a list price per million tokens. It is recorded on that run's page.
- How long does open-webSearch take to install?
- 30 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 open-webSearch need a GPU?
- Not to start. Argusic reached a running state on a machine with no GPU.
- What goes wrong when installing open-webSearch?
- 4 things broke in the recorded run, and 1 were fixed without human help. Each one, and the time it cost, is listed on this page.
- How does open-webSearch compare with the alternatives?
- Of the 28 TypeScript projects Argusic has installed and timed, open-webSearch was the 28th fastest to reach a running state, and 20 of 28 reached one at all.
- Where is the evidence for open-webSearch?
- 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.