deep-searcher
Open Source Deep Research Alternative to Reason and Search on Private Data. Written in Python.
Runs with mockssource: GitHubhomepagePythonApache-2.0commit ddc36db31783
Python, Apache-2.0 licensed. The project labels itself: agent, agentic rag, claude, deep research, deepseek, deepseek r1, grok and grok3.
deep-searcher runs, with stand-ins for the services it depends on. An Argusic agent installed it in 1.5 minutes and hit 2 errors and fixed every one without help on a clean machine with no GPU, and the whole session was recorded.
DeepSearcher package installs with uv sync and pip install -e . and all 422 unit tests pass after fixing 2 test files with stale default model values.
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 56 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.
- XAI LLM test expected default model 'grok-2-latest' but source default was 'grok-4'0.5 minutes
- JiekouAI embedding test expected default model 'baai/bge-m3' but source default was 'qwen/qwen3-embedding-8b'0.5 minutes
- Install time
- 2 minutes
- Cold machine to finish
- 5 minutes
- Errors hit and fixed
- 2 hit, 2 fixed with no human help
- How the result was proved
- python -m pytest tests/ -q exited 0; 422 passed, 0 failed
- Model tokens used
- 43,839
- Exact commit tested
- ddc36db31783
- 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.
**Fixes applied**: - `tests/llm/test_xai.py` — 3 assertions updated from `grok-2-latest` to `grok-4` - `tests/embedding/test_jiekouai_embedding.py` — 6 assertions updated from `baai/bge-m3` to `qwen/q… tokens used 43,839 All done. Here's the summary: **Install**: `uv sync` completed, created `.venv` (Python 3.10.21) with all 338 dependencies. `pip … **Tests**: All 422 tests pass after fixing 2 test files that had stale default model values — the s… **CLI**: The `deepsearcher` CLI fails at startup because `init_config()` tries to instantiate Argus… **Fixes applied**: - `tests/llm/test_xai.py` — 3 assertions updated from `grok-2-latest` to `grok-4` - `tests/embedding/test_jiekouai_embedding.py` — 6 assertions updated from `baai/bge-m3` to `qwen/q…
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
- Installed in 1.5 minutes, faster than the median of the 49 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.
- Licensed Apache-2.0, as reported by its host.
- Measured 2 times, so the result is not a one-off.
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.
Of the 50 agent projects Argusic has installed and timed, deep-searcher was the 10th fastest to reach a running state, and 34 of 50 reached one at all.
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 with mocks | 92.00 | 0.03 | |
| Argusic Runner | 1/3 | Did not run | 20.00 | 0.00 |
Topics (from GitHub)
agentagentic-ragclaudedeep-researchdeepseekdeepseek-r1grokgrok3llama4llmmilvusopenaiqwen3ragreasoning-modelsvector-databasezilliz
Embed the badge
Markdown for the project README. It links back here; terms on the terms page.
[](https://argusic.com/subject/deep-searcher)Questions
- Does deep-searcher run?
- deep-searcher runs, with mocks standing in for external services. Argusic installed and launched it on a clean machine in 2 minutes, hitting 2 errors on the way, and recorded the session.
- How did Argusic test deep-searcher?
- On a fresh, disposable machine, with every command recorded and the repository pinned at commit ddc36db31783. 2 attempts are recorded, and the full method is on the methodology page.
- What did it cost to test deep-searcher?
- The run that produced this verdict cost $0.03: real compute and model cost, not a list price per million tokens. It is recorded on that run's page.
- How long does deep-searcher take to install?
- 1.5 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 deep-searcher need a GPU?
- Not to start. Argusic reached a running state on a machine with no GPU.
- What goes wrong when installing deep-searcher?
- 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 deep-searcher compare with the alternatives?
- Of the 50 agent projects Argusic has installed and timed, deep-searcher was the 10th fastest to reach a running state, and 34 of 50 reached one at all.
- Where is the evidence for deep-searcher?
- 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.