Is this a real antivirus engine or a model reading a feature summary?

The second. Extraction is deterministic code; Jev receives the extracted features and returns a calibrated verdict and severity score. There is no signature database and no packer unpacking described, so a novel sample that produces innocuous-looking features is exactly where this approach is weakest. Treat output as triage ranking, not as a blocking verdict.

Does the EDR half work on anything other than Windows?

No. Live process triage, parent-child anomaly detection, masquerading checks outside System32, socket monitoring and the terminate or suspend controls are all Windows-specific, and the GUI ships a Windows 11 dark theme. File, folder and URL scanning are ordinary Python, and ELF binary inspection is listed, so the static side is portable.

What happens to a scan when the API key is missing or the call fails?

The engine settings screen shows API key status and lets you select models, so you can check configuration before a sweep. The README does not say what a scan does without a valid key, whether it fails open or open, or whether verdicts are cached, so treat that as unknown and test it on your own machine rather than assuming a safe default.

Why is there a downloadable APK in a repository about antivirus?

The repo also contains Android projects: a Jev Guard app with its own release workflow, a self-contained native Java scanner, and a Veil VPN plus DNS blocker. The native scanner links a tested APK download directly from the repository. If you want the desktop tool, ignore the Android directories entirely and install the Python CLI.

What file formats can Jev-AV inspect?

PE executables and DLLs, Linux ELF binaries, PDFs, Office documents, archives and containers, Windows shortcuts, scripts, web markup, and plain text or JSON prompts, with structural checks for each.

How does the bulk triage mode work?

Commands such as bulk-files, bulk-urls, and bulk-edr pre-filter thousands of files, URLs, or running processes in one batch call, described as under two seconds for a full process audit.

CommunityJev Tools & CLIs

Antivirus

Q: What features does Jev-AV extract before asking Jev?

Shannon entropy, hashes, strings, PE imports and sections, PDF triggers, macros, process lineage, LOLBIN arguments, and network sockets, depending on the artifact type.

Windows-first scanner and EDR triage tool that extracts structural features from binaries, scripts, documents and URLs, then has Jev return a severity score and a verdict for each target.

See highlights

Open github.com

Stars: 2
Language: Python
Published by: Community
Author: newuser7171
Last verified: Oct 2026

newuser7171/antivirus

User repository on GitHub

View on GitHub

Forks: 0
Last pushed: Updated Sep 2026

Repo stats from the GitHub API, cached Oct 2026.

About this project

A next-generation antivirus scanner, URL threat intelligence engine, and real-time Endpoint Detection & Response (EDR) sentinel powered by TypeSafe's Jev (jev-latest). Jev-AV inspects binary executables, running processes, scripts, documents, plain text, and web links—extracting structural features (Shannon entropy, hashes, strings, PE imports/sections, PDF triggers, macros, process lineage, LOLBIN arguments, network sockets) and applying System One decision intelligence to deliver calibrated threat verdicts,…

Quoted from the project's README. Read the full README.

Tagscommunity awesomejev catalog-import

Works forJev for Classification Jev for Evaluation

Used inJev for Software & DevTools

Languages: Python

Highlights

CustomTkinter GUI with dashboard, file scanner, link scanner, live EDR, folder scan, sentinel guard, quarantine vault and settings.
Extraction covers PE sections and imports, ELF symbols, VBA macros, PDF launch actions, LNK argument smuggling and archive payloads.
EDR mode reads process lineage, LOLBIN arguments and outbound sockets, with one-click terminate and suspend by PID.
Bulk subcommands pack folders, URL lists and a full process audit into a single batch call.

Watch out

Jev never sees the file. A deterministic extractor computes entropy, hashes, strings, PE imports and sections, PDF triggers, macros, process lineage and sockets, and the model judges that summary, so detection quality is bounded by the extractor. Process triage, System32 masquerade checks and the live monitor are Windows-only, and the GUI is themed for Windows 11. The settings panel reports API key status and lets you pick models and a Strict, Balanced or Permissive threshold, but the README documents no measured detection or false-positive rates, so calibrate on a sample set you already trust before pointing the sentinel at a real Downloads folder. The repository also links a prebuilt Android APK for the native preview, and installing a binary you have not read is your call. Copy reviewed against the repository README on 2026-10-04, not from running it.

Questions about this entry

Short answers drawn from the linked project or page.

More Jev resources like this

jevclip

Video tool where Jev scores subtitle segments and code assembles a short highlights cut plus a de-watered full cut with timestamped summaries.

Jev Tools & CLIs#community#jevbest#catalog-import

Community

cclank/jevclipPython

lejudge-jev-jepa

English-programmable cost module for JEPA PushT planning: linear probes verbalize imagined latents and Jev judges each constraint step, folded into CEM cost with memoised step facts.

Jev Tools & CLIs#community#awesomejev#catalog-import

Community

AbdelStark/lejudge-jev-jepaPython

jev-dimabsa

Research code that tackles dimensional sentiment scoring with Jev typed Score, Choice, and Noul calls plus small corpus statistics, without generation, fine-tuning, or GPU.

Jev Tools & CLIs#community#awesomejev#catalog-import

Community

ZhangYiqun018/jev-dimabsaPython

jev-trade-cc

A point-in-time backtest of a William O'Neil momentum strategy where jev picks the entries and decides the exits, paired against the same rules with no model — and honest enough to report the model as indistinguishable from them.

Jev Tools & CLIs#community#awesomejev#catalog-import

Community

michaelpersonal/jev-trade-ccPython

typesafe-comment

A Python linter that scores code comments with System One on five heuristics — usefulness, readability, accuracy, redundancy, coverage — and fails the pipeline when a comment falls under a threshold.

Jev Tools & CLIs#community#jevbest#catalog-import

Community

Hexdigest123/typesafe-commentPython

jev-seo

547

Live SEO audit that crawls a site from one homepage URL, checks 52 rules tied to Google Search Central, and asks Jev typed questions about every page to rank fixes.

Jev Tools & CLIs#community#jevbest#catalog-import

Community

AgriciDaniel/jev-seoPython

From the Jev guides

Original write-ups on what this entry is for.

Jev on the Gateways: Vercel, Workers AI, and OpenRouter

Oct 12, 2026

The request shape barely changes across surfaces; the surrounding contract does. When to call the API directly and when a gateway, a Worker binding, or a router entry earns its extra hop.

Jev Tools & CLIs#gateway#vercel#cloudflare

Read article

Exporting Decision Models: GGUF, ONNX, and Device Runtimes

Oct 10, 2026

Taking a decision checkpoint out of Python: what the GGUF and browser WebGPU exports preserve, what they change, and the parity evidence the model cards publish.

Jev Tools & CLIs#open-models#local#onnx

Read article

Records at Rest: Documents, Inboxes, and Risk Queues

Sep 28, 2026

Jev labels a record that already exists. Code moves, flags, or holds it. How the document, mail, and transfer tools keep the action out of the model.

Jev Tools & CLIs#classification#email#security

Read article

Back to all resources

From the Jev community

Posts from builders shipping with Jev right now.

Follow @typesafeai