https://github.com/gaisma22/logsense-ai
AI-powered local tool that highlights unusual patterns in system logs.
https://github.com/gaisma22/logsense-ai
anomaly-detection flask isolation-forest log-analysis machine-learning nlp open-source python security-awareness system-logs
Last synced: 3 months ago
JSON representation
AI-powered local tool that highlights unusual patterns in system logs.
- Host: GitHub
- URL: https://github.com/gaisma22/logsense-ai
- Owner: gaisma22
- License: mit
- Created: 2025-11-28T18:35:43.000Z (7 months ago)
- Default Branch: main
- Last Pushed: 2026-04-03T23:50:16.000Z (3 months ago)
- Last Synced: 2026-04-04T01:23:20.919Z (3 months ago)
- Topics: anomaly-detection, flask, isolation-forest, log-analysis, machine-learning, nlp, open-source, python, security-awareness, system-logs
- Language: Python
- Homepage:
- Size: 67.4 KB
- Stars: 0
- Watchers: 0
- Forks: 0
- Open Issues: 0
-
Metadata Files:
- Readme: README.md
- Contributing: CONTRIBUTING.md
- License: LICENSE
- Roadmap: ROADMAP.md
Awesome Lists containing this project
README
# LogSense AI
Local log analysis and live Android monitoring. No cloud, no API calls, no accounts.
The **AI** in the name refers to rule-based triage and pattern inference, not a language model.
## What it does
- Parses `.log`, `.txt`, `.xml`, and `.evtx` files up to 64MB
- Reads Windows `.evtx` binary files directly, maps Security, System, Sysmon, Defender, AppLocker, PowerShell, RDP, and BitLocker events
- Severity classification with pattern matching and confidence scoring
- Adjustable threshold: Strict, Normal, Relaxed
- Live Android logcat monitoring via ADB
- Real-time triage with hover summaries and detail inspector
- Session activity chart in the inspector panel
- Export as TXT, CSV, or JSON
- Dark and light mode, fully offline
## Setup
**Linux and macOS**
```bash
git clone https://github.com/gaisma22/LogSense-AI.git
cd LogSense-AI
python -m venv venv
source venv/bin/activate
pip install -r requirements.txt
python app.py
```
**Windows** - use Command Prompt, not PowerShell
```
git clone https://github.com/gaisma22/LogSense-AI.git
cd LogSense-AI
python -m venv venv
venv\Scripts\activate
pip install -r requirements.txt
python app.py
```
## Android monitoring
Install ADB:
- Linux: `sudo apt install adb`
- macOS: `brew install android-platform-tools`
- Windows: download Platform Tools from the Android developer site and add to PATH
Enable USB debugging, connect via USB, tap Allow when prompted, then click Check Device on the home page.
## License
MIT