openserp
Self-hosted web search for AI agents and SEO. Google, Bing, Yandex, Baidu, DuckDuckGo & Ecosia, rendered in a real browser: ranked results and clean page Markdown. API, CLI, MCP 🎉
Runssource: GitHubhomepageGoMITcommit 98e48e6a8300
Go, MIT licensed. The project labels itself: ai agents, baidu, bing, duckduckgo, google, google search, headless browser and llm.
openserp runs. An Argusic agent installed it in 0.5 minutes and hit no errors on a clean machine with no GPU, and the whole session was recorded.
OpenSERP builds from source, all 12 unit test suites pass, the HTTP server serves /health (200) and handles live DuckDuckGo searches (200) returning structured JSON with organic results and SERP features
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 96 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.
- Install time
- under a minute
- Cold machine to finish
- 6 minutes
- Errors hit and fixed
- 0 hit, 0 fixed with no human help
- How the result was proved
- curl -s -o /dev/null -w '%{http_code}' 'http://127.0.0.1:7472/health' returned 200; curl -s 'http://127.0.0.1:7472/duck/search?text=golang&limit=1&format=json' returned 200 with live results; 'go test -race -count=1 ./...' passed all 12 test packages
- Model tokens used
- 71,251
- Exact commit tested
- 98e48e6a8300
- 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.
**Install:** Downloaded Go 1.24.6 binary release, built with `go build`. **Tests:** `go test -race -count=1 ./...` passed — all 12 packages with test files reported `ok`. **Launch:** Server started on port 7472, health endpoint returned 200 with all 6 engines ready, and… 2026-11-14T16:21:55.971569Z ERROR codex_core::session: failed to record rollout items: thread 01a1d… 2026-11-14T16:21:55.971606Z ERROR codex_core::session: failed to record rollout items: thread 01a1d… tokens used 71,251 Everything verified end to end. Let me summarize. **Errors encountered:** None — everything worked on the first try. The only minor note is that Go w… **Install:** Downloaded Go 1.24.6 binary release, built with `go build`. **Tests:** `go test -race -count=1 ./...` passed — all 12 packages with test files reported `ok`. **Launch:** Server started on port 7472, health endpoint returned 200 with all 6 engines ready, and…
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 0.5 minutes, faster than the median of the 236 comparable projects Argusic has measured.
- Nothing broke on the way: zero errors between clone and running.
- Ran without a GPU, so it does not need one to start.
- Licensed MIT, as reported by its host.
- Measured 2 times, so the result is not a one-off.
Of the 237 ai projects Argusic has installed and timed, openserp was the 14th fastest to reach a running state, and 168 of 237 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 0.5 minutes after the clone.
- Following its own README: the documented path worked with nothing to fix.
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
| tested by | attempt | outcome | score | cost USD | when |
|---|---|---|---|---|---|
| Argusic Runner | 2/3 | Runs | 100.00 | 0.07 | |
| Argusic Runner | 1/3 | Runs with mocks | 92.00 | 0.12 |
Topics (from GitHub)
ai-agentsbaidubingduckduckgogooglegoogle-searchheadless-browserllmmcpmcp-serverragself-hostedseoserpserp-apiserpapitavily-alternativeweb-scrapingweb-searchyandex
Embed the badge
Markdown for the project README. It links back here; terms on the terms page.
[](https://argusic.com/subject/openserp)Questions
- Does openserp run?
- Yes. openserp runs. Argusic installed and launched it on a clean machine in 1 minutes, hitting 0 errors on the way, and recorded the session.
- How did Argusic test openserp?
- On a fresh, disposable machine, with every command recorded and the repository pinned at commit 98e48e6a8300. 2 attempts are recorded, and the full method is on the methodology page.
- What did it cost to test openserp?
- The run that produced this verdict cost $0.07: real compute and model cost, not a list price per million tokens. It is recorded on that run's page.
- How long does openserp take to install?
- 0.5 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 openserp need a GPU?
- Not to start. Argusic reached a running state on a machine with no GPU.
- What goes wrong when installing openserp?
- Nothing did, in the recorded run: zero errors between clone and running.
- How does openserp compare with the alternatives?
- Of the 237 ai projects Argusic has installed and timed, openserp was the 14th fastest to reach a running state, and 168 of 237 reached one at all.
- Where is the evidence for openserp?
- All 2 recorded runs are on this page, each linking to its full log and terminal recording, stored with a sha256 fingerprint so it cannot be quietly altered.