Skip to content

Your code contains inventions you don't know about yet.

Obviously Not reads your codebase and surfaces the distinctive technical concepts inside it, each one scored and tied to the exact code that implements it. Free and open source. Run it on your own machine, in CI, or inside your own AI agent.

👉 Scan Your Code
Open source · Runs on your hardware · Results in minutes
27 concepts across 7 technical clusters, from one 39-minute scan of a public flight-control codebase.

Code scanners ask what is wrong. We ask what is distinctive.

Not a patent scanner. It reads your code for distinctive technical concepts. That is engineering work, not legal work. Whether any concept is worth patenting is a separate question for a patent attorney, and that is the only place the legal judgment belongs.

Distinctive engineering rarely announces itself.

def uncertainty_guided_cache_invalidation(query, E, cache):
    """ML-guided selective invalidation using uncertainty/drift"""
    drift = cosine_sim(E[query], cache.E).std()              # semantic drift (uncertainty)
    thresh = base_thresh * (1 + cache.staleness(query))      # adapt to recency/frequency
    if drift > thresh:
        keys = cache.semantic_neighbors(query, radius=drift) # target related entries only
        return cache.invalidate(keys, decay=drift)           # selective, proportional purge
    return cache.get(query)

Nobody writes a design doc for a loop like this. It ships, it works, and the reasoning behind it lives in one engineer's head. That is the material the scanner is built to find and write down.

See it on a codebase you can check.

27
concepts, each linked to its source
7
technical clusters
39
minutes, one unattended pass
A second pass that read the repository differently returned the same mechanisms, one of them almost word for word. Figures describe that specific run, and recent runs return more. Read the full scan, including three concepts walked through end to end.

How it works.

1

Pick how you want to run it

Download the CLI and scan locally with Ollama, add the GitHub Action to your pipeline, or install the agent skills into Claude Code, Gemini CLI, or Cursor. Same engine, three entry points. All open source, all free.

2

Point it at your code

It reads your source the way an engineer would, looking for the decisions that are not standard practice. With the local CLI, nothing leaves your machine: no cloud upload, no API key, no external call.

3

Review what comes back

Each concept arrives with a plain-language description, the problem it solves, scores across four engineering axes, and the specific files and line ranges behind it. Textbook findings are held back by default, but the count is always reported. Nothing is silently dropped.

Compare the three ways to run it

And patent attorneys.

Intake that starts from code

Scored concepts with file and line-range citations, instead of a blank disclosure form and an hour of interview to fill it in.

Anchored to implementation

Every finding is tied to the specific mechanism in the source and the problem it solves, which is the level of technical detail an eligibility analysis needs to work from.

Scans where the work happens

Repositories and pull requests, not Confluence pages and meeting notes.

The legal call stays yours

We find and structure the engineering. Novelty, eligibility, inventorship, and what to claim are yours. The tool is built around that line, not apologetic about it.

Learn more about partnering

Managing a patent portfolio?

Systematic discovery

Scan across repositories and teams to surface the work engineers never flag. Portfolio building stops depending on which engineers happen to volunteer.

Scales with your org

From a single team to hundreds of engineers. Structured disclosures feed directly into your existing patent workflow.

Runs inside your perimeter

Local-first scanning keeps source code within your corporate environment: no external API calls and no cloud uploads. Security, export-control and client-policy requirements still apply to the particular deployment.

Talk to us about enterprise

You've already built something distinctive. Find out what it is.

Scan it yourself
👉 Scan Your Code

Local CLI, GitHub Action, or agent skills. Open source and free. With the local CLI your code never leaves your machine.

Run it inside your own agent
Browse the Skills

The same scanning packaged as open-source skills for Claude Code, Gemini CLI, and Cursor. Portable, MIT-0, and readable line by line before you run it.

Want to learn more about protecting your innovations? Check out our Resources →

Questions we get a lot.

What does it cost?
The scanner is free and open source in all three forms. You supply the model. Running the CLI against local Ollama costs nothing but your own hardware. Pointing the GitHub Action at a hosted provider costs whatever that provider charges you directly, on your own account.
Does my code leave my machine?
Not with the local CLI. It runs entirely on your hardware against a local model: no cloud upload, no API key, no external call. That matters before you file, because an unfiled invention is a trade secret and sending it to a third-party service is a decision worth making deliberately. See why local-first matters. The GitHub Action is your choice of provider, including a self-hosted runner with local Ollama for a no-egress scan.
Is this a patent search?
No. It does not search patent databases, check novelty, or assess patentability. It reads your code and describes what is distinctive in it. Prior-art searching and the patentability analysis are separate steps, and they belong to a registered patent practitioner.
What does the output actually look like?
For each concept: a plain-language summary of the mechanism, the problem it solves, an interface and component breakdown, scores on four engineering axes, and source evidence down to specific files and line ranges. The PX4 scan shows real output, with three concepts walked through in full.
Can I run it on every pull request?
Yes. The GitHub Concept Scanner runs as a Docker action on Linux runners, so you can scan each change while the author is still in the review, or gate a release so distinctive work is captured before it goes public and the disclosure clock starts.
What do I do with the results?
That is your call. Some teams take the output to a patent attorney as a starting point, which is far more useful than a blank disclosure form. Others use it for diligence, defensive documentation, or simply to keep a record of what their team has built. If filing is on the table, timing matters more than most people expect: read what publishing does to your rights first.
👉 Scan Your Code
Open source. Runs on your hardware. Takes minutes.