deep-research
Use any LLMs (Large Language Models) for Deep Research. Support SSE API and MCP server.
Could not verifysource: GitHubhomepageJavaScriptMITcommit 4a211edd9fac
JavaScript, MIT licensed. The project labels itself: anthropic, deep research, deep research api, deepresearch, deepseek, gemini, grok and mcp server.
Argusic could not get deep-research running. An Argusic agent installed it in 17 minutes and hit 1 error and fixed every one without help on a clean machine with no GPU, and the whole session was recorded.
pnpm dependencies installed, next build completed with all 25 route handlers compiled, and the production server serves the Deep Research Next.js app at localhost:3000 responding HTTP 200 with a fully rendered page.
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.
- next build killed by OOM (8GB cgroup limit) during static page generation2 minutes
- Install time
- 17 minutes
- Cold machine to finish
- 17 minutes
- Errors hit and fixed
- 1 hit, 1 fixed with no human help
- How the result was proved
- curl http://localhost:3000/ returned HTTP 200 with 28136 byte HTML body containing <title>Deep Research</title> and full app shell; curl -X POST http://localhost:3000/api/mcp returned HTTP 200
- Model tokens used
- 42,791
- Exact commit tested
- 4a211edd9fac
- 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
- Whether it works at all
- this run verified nothing, so this page makes no claim either way
The end of the recording
The last lines of the terminal session that decided this verdict, exactly as they were recorded.
/work/repo/node_modules/.pnpm/[email protected]/node_modules/zod/src/v4/classic/tests/catch.test.ts /work/repo/node_modules/.pnpm/[email protected]/node_modules/zod/src/v4/classic/tests/description.test.ts /work/repo/node_modules/.pnpm/[email protected]/node_modules/zod/src/v4/classic/tests/index.test.ts /work/repo/node_modules/.pnpm/[email protected]/node_modules/zod/src/v4/classic/tests/string-formats.test… /work/repo/node_modules/.pnpm/[email protected]/node_modules/zod/src/v4/classic/tests/date.test.ts /work/repo/node_modules/.pnpm/[email protected]/node_modules/zod/src/v4/classic/tests/datetime.test.ts /work/repo/node_modules/.pnpm/[email protected]/node_modules/cytoscape/tests-examples/demo-todo-app.… /work/repo/node_modules/.pnpm/[email protected]/node_modules/cytoscape/playwright-tests/renderer.spe… All verified successfully. Here's the final result: tokens used 42,791 All verified successfully. Here's the final result:
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 17 minutes.
- Recovered from all 1 error without a human stepping in, which says the failures are documented well enough to solve.
- Licensed MIT, as reported by its host.
- Measured 2 times, so the result is not a one-off.
What did not, or is not known
- An agent with no time limit did not get it running.
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 | Unverified | 80.00 | 0.05 | |
| Argusic Runner | 1/3 | Unverified | 80.00 | 0.12 |
Topics (from GitHub)
anthropicdeep-researchdeep-research-apideepresearchdeepseekgeminigrokmcp-serverollamaopenai
Embed the badge
Markdown for the project README. It links back here; terms on the terms page.
[](https://argusic.com/subject/deep-research)Questions
- Does deep-research run?
- Argusic could not verify that deep-research runs. Argusic installed and launched it on a clean machine in 17 minutes, hitting 1 error on the way, and recorded the session.
- How did Argusic test deep-research?
- On a fresh, disposable machine, with every command recorded and the repository pinned at commit 4a211edd9fac. 2 attempts are recorded, and the full method is on the methodology page.
- What did it cost to test deep-research?
- The run that produced this verdict cost $0.05: real compute and model cost, not a list price per million tokens. It is recorded on that run's page.
- How long does deep-research take to install?
- 17 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-research need a GPU?
- Not to start. Argusic reached a running state on a machine with no GPU.
- What goes wrong when installing deep-research?
- 1 thing broke in the recorded run, and 1 were fixed without human help. Each one, and the time it cost, is listed on this page.
- Where is the evidence for deep-research?
- 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.