hyperresearch

Convert Claude Code or Codex into the most intelligent Deep Research Agent. Collect, search, and synthesize web research into a persistent, searchable wiki that builds on itself. Hosted API + MCP: hyperresearch.ai

Runs with mockssource: GitHubhomepagePythonMITcommit 7790041c8705

Python, MIT licensed. The project labels itself: agents, agentskills, citations, claude code, codex, codex plugin, codex skill and deep research.

hyperresearch runs, with stand-ins for the services it depends on. An Argusic agent installed it in 20.6 minutes and hit 1 error and fixed every one without help on a clean machine with no GPU, and the whole session was recorded.

Hyperresearch 0.12.0 is installed from source, a vault is initialized at /work/repo, all 18 step skills and 16 agent docs are installed, the CLI produces correct --version output and valid JSON responses, and 69 of 69 runnable tests pass (2 skipped for missing optional mcp dependency).

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 92 of 100 (the mean of this project's run scores).

At a glance

verdict
Runs with mocks
Argusic Score
92 / 100
cost of the verifying run
$0.18 (measured)
recorded runs
2
last tested
stars
4,822
forks
500
open issues
19
watchers
18
size
7 MB
created
last push

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.

Time lost to each failure while testing hyperresearch, drawn from the recorded run
Every bar is a failure the agent recorded, with the time it cost. Drawn from this run, not from anywhere else.

What went wrong, in the agent's own words

The agent's own words, worst first, never rewritten into advice.

  • test_stripping_is_per_instance_not_global and test_opt_out_keeps_crawl4ai_launch_flags failed because crawl4ai 0.9.5 removed --ignore-certificate-errors flags from _build_browser_args and build_browser_flags (they are now conditionally added in get_launch_args() when ignore_https_errors=True)15 minutes
Install time
21 minutes
Cold machine to finish
20 minutes
Errors hit and fixed
1 hit, 1 fixed with no human help
How the result was proved
python3 -m pytest tests/ -q --tb=short: 71 collected, 69 passed, 2 skipped (mcp optional dep missing), 0 failed. hyperresearch --version returned 'hyperresearch v0.12.0'. hyperresearch init, hyperresearch status, hyperresearch install all returned valid JSON with ok:true.
Model tokens used
203,815
Exact commit tested
7790041c8705
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

Watch the session

The whole run, from a clean machine, at the speed it actually happened. Nothing is cut and nothing is sped up.

A recording of attempt 2, run , the attempt that decided the verdict above. The terminal recording it was made from is the evidence, stored with a sha256 fingerprint; the video is a rendering of it. Nothing loads from the video host until you press play.

The end of the recording

The last lines of the terminal session that decided this verdict, exactly as they were recorded.

/bin/sh -lc 'echo "Total elapsed: $(echo "$(date +%s) - $(stat -c %Y /work/repo/README.md 2>/dev/nu…
 succeeded in 0ms:
/bin/sh: 1: bc: not found
Total elapsed:  seconds
exec
/bin/sh -lc 'echo $(( $(date +%s) - $(date -d "2026-11-08 13:16:00" +%s) )) seconds' in /work/repo
 succeeded in 0ms:
1238 seconds
About 20 minutes elapsed. Let me compile the final report.
tokens used
203,815
About 20 minutes elapsed. Let me compile the final report.

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

  • 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

  • Only reached a running state against stand-in services, so nothing here proves it works against the real ones.
  • Took 20.6 minutes to install, slower than the median of the 40 comparable projects Argusic has measured.

Of the 41 agents projects Argusic has installed and timed, hyperresearch was the 35th fastest to reach a running state, and 29 of 41 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 byattemptoutcomescorecost USDwhen
Argusic Runner2/3Runs with mocks92.000.18
Argusic Runner1/3Runs with mocks92.000.01

Topics (from GitHub)

agentsagentskillscitationsclaude-codecodexcodex-plugincodex-skilldeep-researchdeep-research-agentdeepresearchmcp-serverresearchresearch-agentresearch-tools

Embed the badge

Markdown for the project README. It links back here; terms on the terms page.

[![Tested by Argusic](https://argusic.com/badge/hyperresearch.svg)](https://argusic.com/subject/hyperresearch)

Questions

Does hyperresearch run?
hyperresearch runs, with mocks standing in for external services. Argusic installed and launched it on a clean machine in 21 minutes, hitting 1 error on the way, and recorded the session.
How did Argusic test hyperresearch?
On a fresh, disposable machine, with every command recorded and the repository pinned at commit 7790041c8705. 2 attempts are recorded, and the full method is on the methodology page.
What did it cost to test hyperresearch?
The run that produced this verdict cost $0.18: real compute and model cost, not a list price per million tokens. It is recorded on that run's page.
How long does hyperresearch take to install?
20.6 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 hyperresearch need a GPU?
Not to start. Argusic reached a running state on a machine with no GPU.
What goes wrong when installing hyperresearch?
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.
How does hyperresearch compare with the alternatives?
Of the 41 agents projects Argusic has installed and timed, hyperresearch was the 35th fastest to reach a running state, and 29 of 41 reached one at all.
Where is the evidence for hyperresearch?
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.

Discussion