πŸ§™β€β™‚οΈtrs: documentation

Threat intelligence report analysis via LLM

Overview πŸ•οΈ

trs is a command line tool that leverages an LLM (OpenAI) to chat with and analyze cyber threat intelligence reports and blogs.

Supply a threat report to pre-built commands for summarization, MITRE TTP extraction, mindmap creation, and identification of detection opportunities, or run your own custom prompts against the report content.

Each URL's text content is stored in a Chroma vector database so you can have QnA / Retrieval-Augmented-Generation (RAG) chat sessions with the processed reports.

The OpenAI model gpt-3.5-turbo-16k is used in order to support larger contexts more easily, but feel free to swap this out for the gpt-4-32k model in the config if you have access.

Last updated