Taranis AI: Pioneering AI-Driven OSINT
summary
Taranis AI is a fully open-source OSINT platform that layers ML on the Taranis-NG/Taranis3 workflow to cut analyst bottlenecks. It uses named entity recognition (regex for CVEs, separate models for technical vs general news), topic clustering to aggregate duplicate stories, MISP-backed bidirectional sharing for preserved context, on-demand summarization for a human-in-the-loop, CPU and GPU model options, OCI-container HTTP model interfaces, Playwright-generated demo videos, and RabbitMQ/Celery pipelines (plans to move to Prefect).
AI-written summary · about
chapters (11)
- 0:00Introduction to OSINT
- 2:27The Taranis platform
- 6:42Named entity recognition
- 11:50Topic clustering
- 13:43Threat collaboration
- 15:51Contextual enrichment
- 20:01AI development challenges
- 24:40Deployment and infrastructure
- 25:47Live software demonstration
- 29:37Conclusion and call to action
- 30:51Q&A session
related talks
31mSkynet the CTI Intern: Building Effective Machine Augmented...
21mEnhancing Threat Intelligence Using AI
29mOpen Source Sovereign AI: Building Enterprise GenAI Platforms for Control & Comp...
42mAI for security - friend or foe?
25mTIS Group’s AI Journey: From Healthcare to Agriculture
25mOpen Source Projects and AI Security
25mOpenTide: From Raw Intelligence to Structured Threat-Informed Detections
14mReliable Agentic AI, the Open Way