ddgs
A metasearch library that aggregates results from diverse web search services
Runssource: GitHubPythonMITcommit 70a5635510fb
Python, MIT licensed. The project labels itself: api, ddgs, dht, mcp, mcp server, metasearch, p2p and python.
ddgs runs. An Argusic agent installed it in 1 minute and hit 1 error on a clean machine with no GPU, and the whole session was recorded.
The ddgs package installs, lints, and formats cleanly; the CLI and Python API produce real results for text, images, news, and extract; videos and books tests fail because DuckDuckGo's v.js endpoint and Anna's Archive return 403 from this container.
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 80 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_videos_search, test_videos_command, test_books_search, test_books_command fail — DuckDuckGo videos API and Anna's Archive return HTTP 403 from this container's IP15 minutes
- Install time
- 1 minutes
- Cold machine to finish
- 12 minutes
- Errors hit and fixed
- 1 hit, 0 fixed with no human help
- How the result was proved
- .venv/bin/ddgs text -q 'hello world' -m 3 returned 3 real results from Wikipedia and Grokipedia; .venv/bin/pytest tests/ -v passed 13 of 17 (4 external-service failures); .venv/bin/ruff check and format --check both clean; .venv/bin/ddgs version returned 9.16.0
- Model tokens used
- 112,783
- Exact commit tested
- 70a5635510fb
- 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.
**Setup summary:** - **Install**: `python3 -m venv .venv` and `pip install -e .[dev]` both succeeded without errors. - **CLI**: `ddgs --help`, `ddgs version`, and `ddgs text -q "hello world" -m 3` all work. - **Lint/Format**: `ruff check` passes, `ruff format --check` shows all files already formatted. - **Tests**: 13 passed, 4 failed — all 4 failures are from external services blocking requests from… The core search functionality (text, images, news, extract) works reliably end-to-end. The videos a… exec /bin/sh -lc 'cd /work/repo && .venv/bin/ddgs version 2>&1' in /work/repo succeeded in 0ms: 9.16.0 tokens used 112,783
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 1 minute, faster than the median of the 12 comparable projects Argusic has measured.
- 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
- Hit 1 error during setup, 1 of which were not solved.
- Measured once so far. A single attempt shows it can run, not that it runs reliably.
Of the 13 api projects Argusic has installed and timed, ddgs was the 5th fastest to reach a running state, and 8 of 13 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 1 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)
Embed the badge
Markdown for the project README. It links back here; terms on the terms page.
[](https://argusic.com/subject/ddgs)Questions
- Does ddgs run?
- Yes. ddgs runs. Argusic installed and launched it on a clean machine in 1 minutes, hitting 1 error on the way, and recorded the session.
- How did Argusic test ddgs?
- On a fresh, disposable machine, with every command recorded and the repository pinned at commit 70a5635510fb. One attempt is recorded, and the full method is on the methodology page.
- What did it cost to test ddgs?
- 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 ddgs take to install?
- 1 minute in the run that decided this verdict, from a clean machine to a running state. That is one measured attempt, not an average.
- Does ddgs need a GPU?
- Not to start. Argusic reached a running state on a machine with no GPU.
- What goes wrong when installing ddgs?
- 1 thing broke in the recorded run. Each one, and the time it cost, is listed on this page.
- How does ddgs compare with the alternatives?
- Of the 13 api projects Argusic has installed and timed, ddgs was the 5th fastest to reach a running state, and 8 of 13 reached one at all.
- Where is the evidence for ddgs?
- 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.