Our take
Activeregular commits and releases- Activity
- 72
- Community
- 20
- Issues
- 57
- Pull requests
- 20
+26 stars in the last 30 days
- Releases more often than 80% of the projects we track
PYAS is an actively developed and feature-rich Windows security project, but its kernel capabilities and highly concentrated maintenance make it better suited to careful evaluation than unreviewed production deployment.
Good fit if
- You are studying Windows endpoint security and can test the application and driver in an isolated environment.
- You want a Windows desktop scanner combining YARA, PE machine learning, signature checks, and optional cloud analysis.
- You can review the source and accept that most development comes from one contributor, despite recent commits, releases, and issue responses.
Look elsewhere if
- You need a product with a clearly stated repository-wide license for redistribution or commercial use.
- You need a broadly maintained project: most contributions come from one person, and no pull requests were merged in the measured recent period.
- You need a cross-platform endpoint tool or cannot meet the Windows-specific privilege and driver requirements.
All health signals
| Last commit | 2026-09-25 (13 days ago) |
|---|---|
| Commits, last 90 days | 80 |
| Releases, last 12 months | 31 (latest v3.7.0, 2026-09-23) |
| Contributors | 7 (top contributor: 99% of commits) |
| Issues closed, last 90 days | 11 (typically closed in 6 days) |
| Pull requests merged, last 90 days | 0 |
| Project age | 5 years |
Checked on 2026-10-09 with the GitHub API.
Project history
Daily GitHub snapshots since Oct 7, 2026. History covers stars and forks; health signals are not tracked historically.
Stars
606Forks
53Change since Nov 17, 2026: 0 stars·0 forks
Overview
PYAS is a Windows endpoint security application that combines several detection methods with real-time monitoring and optional kernel-level enforcement. It aims to help users identify and respond to suspicious files and activity through local scanning, signature checks, cloud analysis, and remediation tools.
It is also a research-oriented codebase, with model-training utilities, a rule editor, and a separate online analysis service. That makes it relevant to Windows security learners and developers, as well as users evaluating a layered endpoint defense tool.
Key Features
- Scans Windows executables with YARA rules, PE feature extraction, and ONNX machine-learning models.
- Checks file signatures using Windows Authenticode verification.
- Offers optional cloud file analysis, including uploads and report retrieval.
- Monitors processes, files, memory, and network activity, with configurable protection modules.
- Includes a native Windows minifilter driver for kernel-level enforcement across file, process, registry, memory, and image-load activity.
- Provides quarantine, allow/block lists, system repair, startup management, cleanup, and activity reporting.
- Includes tools for training PE models and creating driver protection rules.
Use Cases
- Windows users who want to evaluate layered local scanning and real-time protection in a desktop application.
- Security researchers studying PE classification, YARA rules, Windows internals, or driver-based enforcement.
- Developers building or testing rule-driven protections who can use the included driver source and visual rule editor.
- Teams that need to submit samples to an online analysis service, provided they have authorization and can protect sensitive files.
What you need
Detected in the repository
- YARA (main language on GitHub)
Getting Started
For a packaged install, use the GitHub Releases page. To run from source, use Python 3.10 on Windows:
git clone https://github.com/87owo/PYAS.git
cd PYAS
py -3.10 -m venv .venv
.\.venv\Scripts\Activate.ps1
pip install pystray pefile requests pywebview Pillow yara-python numpy onnxruntime
python PYAS.py
See the README for setup details, driver building, and the online analysis service.
License in Plain Words
No standard license was detected. Without a license, the default copyright rules apply: you may read the code, but not reuse it. Check the repository or ask the authors.
Alternatives
- QDoctor: QDoctor focuses on incident response and anti-rootkit inspection, while PYAS combines malware scanning, machine-learning classification, and preventive kernel protections.
| Project | Language | License | Stars | Status |
|---|---|---|---|---|
| PYAS | YARA | – | 565 | Active |
| QDoctor | not specified | not specified | 688 | Quiet |
Considerations
PYAS targets Windows 10 and 11, and full protection may require administrator privileges. Kernel driver development requires Visual Studio and a compatible Windows Driver Kit; the README recommends isolated virtual-machine testing. Cloud analysis is optional, but submitted files may contain sensitive information. The online service uses Flask and PostgreSQL, so operating that component requires managing a database and securing the deployment. The repository has no identified repository-wide SPDX license, and the README advises reviewing component licenses and asking the maintainer before redistribution or commercial use. While development and releases are recent, nearly all contributor activity is concentrated in one person, which creates a maintenance dependency.
Found this useful?
Share it with someone who would like PYAS.