Privacy-First Patent Discovery

Your code never leaves your machine.

Patent Scanner runs entirely on your hardware using a local LLM. No cloud uploads, no API keys, no external calls. Scan your codebase for patentable innovations with complete confidentiality.

Download for macOS View All Releases
Free and open source. macOS, Linux, and Windows.

Why local matters for patents.

Unfiled inventions are trade secrets. Uploading your code to cloud AI services before filing can compromise patent rights and create foreign filing license complications. From scan to structured disclosure in minutes — minimize your exposure window.

Complete confidentiality

Your source code and analysis results stay on your machine. No data is transmitted to any external service. Critical for pre-filing confidentiality.

Works offline

After the initial model download, the scanner operates entirely offline. No internet connection required. No API keys to manage or pay for.

Filing compliance

Patent documents processed on foreign servers can create foreign filing license issues under 35 U.S.C. 184. Local processing avoids this entirely.

What the scanner finds.

The scanner produces structured technical disclosures — not vague suggestions. Every discovery links back to the specific code that contains the innovation.

Structured disclosures

Each discovery includes a technical description, problem-solution framing, and novelty assessment formatted for patent review.

Evidence linking

Every concept traces back to specific files and code sections. Verifiable provenance that attorneys can review against the actual implementation.

Novelty scoring

Discoveries are scored for patentability, helping you prioritize which innovations are worth pursuing first.

Prior art context

Each discovery includes relevant prior art considerations, giving you a head start on understanding the competitive landscape.

Three steps to your first scan.

1

Download and install

Grab the binary for your platform. Install Ollama for the local LLM runtime. One-time setup takes about 5 minutes.

2

Point at your codebase

Run the scanner against any local directory. It reads your source files, analyzes patterns, and identifies concepts that may be novel and patentable.

./patent-scanner-local scan ./your-project --verbose
3

Review discoveries

Examine scored patent concepts with evidence from your actual code. Each discovery links to specific files and lines so you can verify the analysis.

Download.

All binaries are published on GitHub. Free and open source.

macOS

Apple Silicon

macOS

Intel

Linux

x86_64

Linux

ARM64

Windows

x86_64

Requirements.

Ollama

Local LLM runtime. Free and open source. Install from ollama.ai

8 GB RAM minimum

16 GB recommended for larger codebases and faster analysis.

4 GB disk space

For the LLM model download. One-time download on first run.

Found something? Here's what to do next.

The scanner discovers and structures. What happens next depends on your goals.

File a provisional patent

Use the structured disclosure as a starting point for a provisional patent application. A PPA gives you 12 months of patent-pending protection while you refine your claims.

Connect with a patent attorney

Share your structured disclosures with an attorney who can draft proper claims, conduct thorough prior art searches, and file with the USPTO. The scanner does the intake work so the attorney can focus on legal strategy.

Scan more with our hosted service

Need to scan GitHub repos or want a web-based experience? Our hosted scanner connects directly to your repos. First scan is free.

Your code. Your machine. Your patents.

Download Patent Scanner
Prefer AI agents? Browse patent skills for Claude Code, Gemini CLI, and more.
Want a hosted solution? Try the web scanner — first scan is free.