ArkhamMirror

I hate that we have to expose data to the cloud in order to analyze it, so I decided to build a platform that would help people get to the truth of things without having anyone peeking over their shoulder.

ArkhamMirror: SHATTERED is a modular, air-gappable, local-first and AI-assisted platform. It can run entirely on your machine - no cloud, no telemetry, no ads, no subscriptions, no fees, no limits.

It’s designed for journalists, researchers, legal advocates, OSINT enthusiasts or anyone else who needs to find truth in documents but can’t (or won’t) expose them to Big Tech and can't afford to use Palantir.

Key features:

- 25 modular plug-and-play "shards" (CIA's Analysis of Competing Hypotheses tool, MOM/POP/MOSES/EVE techniques, entity extraction, timeline, graph visualization, contradiction detection, etc.) attach to the central "frame" - PostgreSQL-only infrastructure (pgvector for embeddings, SKIP LOCKED for job queues) - Runs on 4GB RAM using cloud embeddings, add ~1.2GB for local models - Full audit trails for evidence provenance - Dockerized for easy isolation and/or VPS deployment - Use pure local inference for sensitive data or use any OpenAI-compatible cloud endpoint for unclassified materials, your choice. (I personally use Anthropic inference through OpenRouter's BYOK option for cloud services and LM Studio's Qwen3-vl:8b for local inference)

Use cases we've focused on: investigative journalism, OSINT, legal self-advocacy, healthcare insurance appeals, civic oversight.

The "Healthcare Self-Advocacy" section exists because insurance companies are deploying AI to deny claims faster. This tool helps people fight back. There are 25 individual shards now, but more shards are in development.

MIT licensed. No VC funding. No growth metrics. Just trying to give powerful tools to people who need them. Intelligence for anyone.

I'm more than happy to answer any questions and welcome suggestions, criticisms, bug reports, you name it.

https://github.com/mantisfury/ArkhamMirror

We've added a standalone ACH tool you can use locally or even try in-browser:

https://mantisfury.github.io/ArkhamMirror/ach/

Enjoy

There is now a standalone ACH tool you can try online in-browser. You can download it and run it locally with local llm, or you can use it in the browser and plug in a Groq or OpenAI API key.

Ai-assist features can add hypotheses, challenge existing hypotheses (devil's advocate), add evidence, automatically suggests scores for evidence and hypotheses, generate insights for your hypotheses rankings, analyze sensitivity of findings, and generate suggested milestones.

An AI source must be connected in order to activate those features, but the ACH tool is fully functional without any AI.

Remember the AI suggestions are to be taken as suggestions, not gospel. Use your own best judgement, as the AI is not the one source of truth and can be wrong or make mistakes.

Exporting the JSON file allows you to re-load your progress later. The PDF is a brief report on the overall results, and the markdown contains all relevant data you gained from your analysis.

I'm very glad to hear that!

Let me tell you this - This version of the toolkit is pretty monolithic and reflex is kind of a pain to work with for me. This version of the tool will be polished from here, but I hesitate to add more features to it since it already has like 35 pages of features.

I'm about to release another version of the tool that's focused on modularity, so you anyone can mix and match the features they want instead of having to take the whole thing or nothing. ACH is going to be the first addon thing added, followed by the rest of the features.

Good question. TL;DR is you won't find those here.

ACH is a different sort of hypotheses testing tool. This tool does not do formal "Statistical Hypothesis Testing" using the formal statistical methods that would be used for the rigorous testing required in the scientific world. There is a null hypothesis found in ACH, but that's about the only real crossover. So, you won't be able to find any p-values, t-tests, chi squares or any statistical significance at all in this.

My Analysis of Competing Hypotheses tool uses the methodology created by Richard Heur - it's an intelligence analysis methodology designed to be used by analysts who need a way to avoid their own biases as much as possible when investigating a question. There's no p-value calcs, no actual statistical significance, or any real math at all (the only math involves adding up rows of values from -2 to 2 basically, and then putting them in order).

It doesn't have an online mode yet - although there's a lot of stuff in the works. However, since docker and LM Studio are already included in the setup, you can turn on MCP Toolkit in Docker and add the Docker MCP to LM Studio. With Docker Toolkit on, you get access to over 300 different MCPs for your local LLM including web search via DuckDuckGo or Brave Search, automation tools like n8n, web manipulation stuff with playwright, and all sorts of potentially useful stuff. (not a sponsor :P) Then your "local" LLM can suddenly do all sorts of agential stuff. This isn't out-of-the box capability, since I'm only building offline, local, privacy-focused features at the moment, but turning it on isn't a huge undertaking. If you are up for messing with some prompts in the files, you could even specify to the LLM what tool you want it to use for which task if it's not automatically using them when the need arises.

I dockerized most of what I could, the rest of it I put in a data silo for ease of destruction when necessary. Is there something in particular you think would work better or be more secure being added to the docker setup?

For sure - "conspiracy theorists" are just another group of people trying to find truth, patterns in the world and trying to connect the dots. The cork board feel was very much intentional in some of the visualizations. Specifically, the "lie web" visualization that uses "red yarn" visuals to connect detected contradictions across different entities and documents.

If I had the skills, I would totally map that onto a cork board.

You're very welcome

I get it - pretty much everything I've been working with to build this platform is basically brand new to me, or just brand new in general, so I have to be wary of how I do things too.

The ACH method actively encourages you to start off with any and all plausible explanations and eliminate them as you go along, but the AI suggestions are definitely more limited than what a human could come up with.

There are LLM limitations on the call to generate hypotheses to return them in a certain format and to return a certain number of them, and that sort of thing, so it's usually in your best interest to use the LLM as more of an assistant to check if you missed anything or for a push to get started looking in different directions more than having the AI doing the whole thing (although if you are being lazy or don't know what to do, you could let the LLM do pretty much everything - I pretty much let the LLM handle everything it could in testing.)

There's a lot of potential for overlaps in features - e-discovery is one of the core concepts behind this platform, definitely.

Also, it's true that a lot of the existing tools that do similar things are anything but free.

I can imagine most or all of the things ArkhamMirror does are done elsewhere by other programs and tools. I don't know of any unclassified projects that do ACH better, but that's a pretty niche tool, and the government loves their 20-year-old software solutions.

Off-the-shelf programs designed for use by lawyers have layers of protections built in to make sure they are suitable for court-use. I don't make any claims as to the legal utilities of this program whatsoever. In fact, the ACH PDF report generated specifically calls attention to the AI-generated nature of the materials and warns against using any data generated or entered without human review and approval.

That said, you can make some pretty cool, non-legally useful, connections with tools like author unmask, where you feed the system docs by a known author and run them against docs written by an unknown or suspected alias to check for similar voice. During ingestion, the system automatically yanks all detected Regex data and puts it into a nice sortable, searchable list for you.

Legal e-discovery products are going to be highly polished, reliable programs designed to be used in a legal setting, while ArkhamMirror is designed to be used while you sit in your faraday cage in your hacker cabin in the woods with no Wi-Fi.

No shade intended - my stuff's not nearly as pretty or as well-put together as a decent off-the-shelf e-discovery program and I'm not trying to imply that it's better in any way, it's just differently aligned.

TL;DR is it should be fine, and thank you!

There's an isolated venv/ in the project folder, so no global packages or system python mods.

If your python is 3.11+, the install should recognize it. If you have 3.10 or lower, it's going to prompt you to install 3.11 for the project environment through winget or python.org. If you are running multiple pythons, it uses py -3.11 to pick the version.

For Docker, the app is going to want you to already have docker running, and will want to make and utilize 3 containers (PostgresSQL, Qdrant, Redis) in their own isolated docker-compose project. It uses nonstandard ports, but there could be conflicts there if you have stuff running on 5435, 6343/6344 or 6380. The backend wants to run at 8000, and the frontend wants to run at 3000, so those could conflict potentially as well.

The script is going to check if docker is running - if it is, you should be set. If it's not, it's going to prompt you to start it up.

Nothing in the install should touch your docker daemon config or your existing containers.

Let me know how it works for you!

That's awesome, thank you so much for getting more eyeballs on it!

My approach to security so far has been to keep it air-gapped and include a nukeitfromorbit.bat that will do everything but physically destroy your SSD to keep your privacy intact.

The narrative reconstruction tool was pretty fun to make, and it's been impressive in testing, but the real test will be if it actually helps someone in a real investigation.

If you see anything in my project that could help your project, then that's awesome news to me!

I'm definitely going to keep working, and hopefully soon it's going to do some pretty cool stuff. All the best to you and OSINTBuddy

This feature update is all about ACH, but there are several other functions that might also be of use for doing audit or compliance work.

Is there any particular function you had in mind?

ArkhamMirror can also scan your corpus for near duplicates, clusters, can check for signs of people using copy-paste in their work, find designated red flags, regex data, and that sort of thing. It's really generalized for as many use cases as possible at this stage, and I'm about to start working on modularity for specialization soon, so feel free to make suggestions on how you'd want to use it.

Thank you, I'm glad it's gathered some interest!

I don't have any background as an analyst or anything like that. ACH is a real tool, really used by the CIA, and the existing versions are basically crappy spreadsheets, or not free, or both.

I don't doubt someone with coding skills could do it better, it's just that no one else has stepped up. Probably because there's no profit angle, but that's conjecture on my part.

I'm sure if the right evidence were submitted and run against the right hypotheses a different frontrunner could emerge. Remember - this is a tool to help you investigate better and figure out what to look for, not a tool that tells you the answer. It helps you eliminate unlikely answers more than it ever points at the "right" answer, and even the most unlikely answers can still be the "right" ones! Hang in there

It would be enough to drive most local LLMs crazy if it tried to generate it all at once or if it was all part of one long session, but it's set up so the LLM doesn't have to produce much at a time. I only batch in small groups (like it will generate only 3 suggestions per request) and the session is refreshed between calls, and the output is generally force structured to fit correctly into the expected format. You can, however, ask for new batches of suggestions or conflicts or evidence more than once. Hallucinations can happen for any LLM use of course, but if they break the expected structure the output is generally thrown out. Even the matrix scoring suggestion - it works on the whole row, but behind the scenes the LLM is asked to return one response in one "chat" session per column, and then they are all entered at the same time once all of them have been individually returned. That way, if the LLM does hallucinate for the score, it outputs a neutral response for that cell and doesn't corrupt any of the neighboring cells.

If you use a smaller model with smaller context, it might be more prone to hallucinations and provide less nuanced suggestions, but the default model seems to be able to handle the jobs pretty well without having to regenerate output very often (it does happen sometimes, but it just means you have to run it again.) Also, depending on the model, you might get less variety or creativity in suggestions. It's definitely not perfect, and it definitely shouldn't be trusted to replace human judgement.

Thanks, glad to hear it!

Short answer - no, not right now.

However, instead of going through locally hosted docker and local LLMs, you could reroute it wherever you like, but I don't have a cloud option set up at this time.

I'm focused on the developing the local, private applications myself, but nothing is stopping someone from hooking it up to stronger cloud-based stuff if they want.

The good news is that my plans for this include making it more modular, so people have better options for what it does and how powerful it is.

That would be a cool test - let me know if you decide to do it!

Supposed to be the Mirror of Galadriel showing Arkham asylum. Just joshing on Palantir Gotham a little bit

Well, based on the evidence provided against our competing hypotheses, The least problematic hypothesis is that we landed on the moon in 1969. Second least problematic hypothesis was "The Apollo 11 mission was a hoax staged by NASA and the U.S. government for public relations and Cold War propaganda, but the moon landing itself was real — only the public narrative was fabricated." Third least problematic was "The Apollo 11 mission was a real event, but the moon landing was not achieved by humans — it was an automated robotic mission that was misinterpreted or falsely attributed to astronauts due to technical errors or media misreporting." - The winning hypothesis had a score of 0 (lower is better), second place had a score of 6 (out of possible 10 for our evidence set), and third place had a score of 8. There was also a tie for 4th place "It was just a government coverup to protect the firmament. There is no "outer space."" and "The Apollo 11 mission never occurred; all evidence — including photos, video, and lunar rocks — was fabricated in secret laboratories using early 20th-century special effects and staged experiments, possibly by a small group of scientists and engineers working under government contract." - both of these scored 10 out of 10, making them the most problematic. Sorry guys.

I didn't think a video would be very exciting. It did feel like deep magic when I tested it though. For the scenario in the screenshots, I provided the question, "Did we really land a man on the moon?" and the null hypothesis "We landed on the moon in 1969", and the low value piece of evidence "My dad told me he saw Stanley Kubrick's moon landing set one time and he never lies." Literally everything else the LLM generated on demand for me based on its existing training data, offline. It gave me hypotheses, challenges, evidence, filled out the matrix, did the calculations, everything.

Probably - LLMs definitely benefit from having decision-making frameworks. ACH is a super-widely useful tool, so I don't see why you couldn't tune an AI with it too.

In case it wasn't clear, the ACH update is on the reflex-dev branch -

https://github.com/mantisfury/ArkhamMirror/tree/reflex-dev

It's mainly useful for journalism purposes, yes. Audit and compliance uses were also a consideration. It's a unified tool for right now, but I'm working on turning the base of it into the frame and adding individual shards for specialized applications.

It's not just for people doing interesting things. It just helps people answer questions about stuff. The stuff can be interesting or boring or dangerous or silly. The last question I tested the ACH tool on was "Did William Shakespeare really author all of the works he was credited for?" - You can use this stuff to research whatever you want. That's the point of it - it's no one's business what you are interested in getting to the bottom of.

Thanks for the interest! I agree, the less people that need it the better, but I want it to exist just in case.

The cheesy noir persona is for the AI assisted install and that's it. Inside the app, the prompts are strictly business. (They still have roles, but not "characters" or "personas").

I got tired of expensive SaaS tools that want my sensitive documents in their cloud. I built ArkhamMirror to do forensic document analysis 100% locally, free and open source.

What makes this different:

Air-gapped: Zero cloud dependencies. Uses local LLMs via LM Studio (Qwen, etc.)

ACH Methodology: Implements the CIA's "Analysis of Competing Hypotheses" technique which forces you to look for evidence that disproves your theories instead of confirming them

Corpus Integration: Import evidence directly from your documents with source links

Sensitivity Analysis: Shows which evidence is critical, so if it's wrong, would your conclusion change?

The ACH feature just dropped with an 8-step guided workflow, AI assistance at every stage, and PDF/Markdown/JSON export with AI disclosure flags. It's better than what any given 3-lettered agency uses.

Tech stack: Python/Reflex (React frontend), PostgreSQL, Qdrant (vectors), Redis (job queue), PaddleOCR, Spacy NER, BGE-M3 embeddings.

All MIT licensed. Happy to answer questions about the methodology or implementation! Intelligence for anyone.

Links: Repo https://github.com/mantisfury/ArkhamMirror

ACH guide with screenshots at https://github.com/mantisfury/ArkhamMirror/blob/reflex-dev/d...