ArkhamMirror
Local-first AI-powered document intelligence platform for investigative journalism
Runssource: GitHubPythonMITcommit 26e7cd87275c
Python, MIT licensed. The project labels itself: air gapped, data visualization, digital forensics, docker, document intelligence, edge ai, entity extraction and intelligence analysis.
ArkhamMirror runs. An Argusic agent installed it in 19 minutes and hit 4 errors and fixed every one without help on a clean machine with no GPU, and the whole session was recorded.
The SHATTERED API server runs on http://127.0.0.1:8100 with 26 shards, 559 API endpoints, PostgreSQL+pgvector backend, serving a healthy health-check and Swagger UI. All core services (database, config, storage, chunks, vectors, events, workers, models) report active.
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.
What went wrong, in the agent's own words
The agent's own words, worst first, never rewritten into advice.
- pgvector headers missing from extracted pg package3 minutes
- Vector dimension mismatch (1024 default vs 384 actual)2 minutes
- media-forensics shutdown crashes without callback arg to unsubscribe1 minute
- Pretrained embedding model cannot download (no HF access)1 minute
- Install time
- 19 minutes
- Cold machine to finish
- 23 minutes
- Errors hit and fixed
- 4 hit, 4 fixed with no human help
- How the result was proved
- curl http://127.0.0.1:8100/health returned 200, openapi.json reported 559 endpoints, /api/shards/ returned 26 shards, Swagger UI at /docs renders. Frame tests: 116 passed, 18 failed (pre-existing), 66 skipped, 4 errors.
- Model tokens used
- 139,814
- Exact commit tested
- 26e7cd87275c
- 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.
- PostgreSQL 16.15 installed from Debian packages (extracting into a non-root directory) with pgvec… - PostgreSQL configured and started on port 5432 - Database `arkhamdb` created with user `arkham` and full migration run - Python virtual environment created with all dependencies installed - All 26 shards installed via `pip install -e` - spaCy `en_core_web_sm` model downloaded **Errors encountered and fixed:** 1. **pgvector include path** - The extracted PostgreSQL packages included an empty server include d… 2. **Vector dimension mismatch** - The initial migration used 1024 dimensions but the default all-M… 3. **media-forensics unsubscribe bug** - Shutdown called `unsubscribe(event)` without the required … 4. **Embedding model offline** - HuggingFace model download fails in this environment (no HF access… 5. **Pre-existing test issues** - Event bus tests fail because `subscribe()` is async but tests cal…
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 19 minutes.
- Recovered from all 4 errors without a human stepping in, which says the failures are documented well enough to solve.
- 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.
What it is a reasonable choice for
- Trying it on a laptop or a small server: it reached a running state without a GPU.
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 | 0.14 | |
| Argusic Runner | 1/3 | Runs | 100.00 | 0.14 |
Topics (from GitHub)
air-gappeddata-visualizationdigital-forensicsdockerdocument-intelligenceedge-aientity-extractionintelligence-analysisinvestigative-journalismknowledge-graphlocal-llmocroffline-aiopen-sourceosintpalantir-alternativeprivacy-firstragself-hostedsemantic-search
Embed the badge
Markdown for the project README. It links back here; terms on the terms page.
[](https://argusic.com/subject/arkhammirror)Questions
- Does ArkhamMirror run?
- Yes. ArkhamMirror runs. Argusic installed and launched it on a clean machine in 19 minutes, hitting 4 errors on the way, and recorded the session.
- How did Argusic test ArkhamMirror?
- On a fresh, disposable machine, with every command recorded and the repository pinned at commit 26e7cd87275c. 2 attempts are recorded, and the full method is on the methodology page.
- What did it cost to test ArkhamMirror?
- The run that produced this verdict cost $0.14: real compute and model cost, not a list price per million tokens. It is recorded on that run's page.
- How long does ArkhamMirror take to install?
- 19 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 ArkhamMirror need a GPU?
- Not to start. Argusic reached a running state on a machine with no GPU.
- What goes wrong when installing ArkhamMirror?
- 4 things broke in the recorded run, and 4 were fixed without human help. Each one, and the time it cost, is listed on this page.
- Where is the evidence for ArkhamMirror?
- 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.