# apurvsinghgautam/robin

AI-Powered Dark Web OSINT Tool

Repository: https://github.com/apurvsinghgautam/robin
Canonical: https://ross.abutalabs.com/products/robin
Language: Python
License: MIT
License Family: permissive
Topics: ai-tool, darkweb, darkweb-osint, investigation-tool, llm-powered, osint, osint-tool
Last push: 2026-08-25T00:38:05+00:00

## Health v2 (maintenance only)
Score: 84/100 (v2, computed 2026-09-03T02:20:16.233290+00:00)
- activity 99, release rhythm 93, longevity 36
- inputs: {"age_days": 512, "days_push": 9, "days_rel": 49, "gap_med": 4.5, "n_releases_24m": 25}
- flags: none
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 6438, forks 1230 (observed 2026-08-28T04:09:43.389852+00:00)

## What it is
Robin is an AI-powered dark web OSINT investigation tool that uses LLMs to refine queries, filter results from dark web search engines, and generate investigation summaries. It provides a Streamlit web UI, conversational follow-ups grounded in investigation data, and supports multiple LLM providers including OpenAI, Claude, Gemini, and local models via Ollama.

## Use cases
- investigate dark web marketplaces and forums for threat intelligence
- search the dark web for leaked credentials or data breaches
- run OSINT investigations with AI-filtered dark web search results
- generate investigation summaries and reports from dark web findings
- ask follow-up questions about a dark web investigation without re-searching
- use local LLMs like Ollama for private dark web research

## When to choose
- you need LLM-assisted dark web OSINT with an interactive web UI
- you want to switch between cloud and local LLM providers for investigations
- you need grounded conversational follow-ups and one-click query pivots during an investigation
- you prefer a Docker-deployable tool with modular, extensible search and LLM workflows

## When to avoid
- you need general surface-web OSINT rather than dark web (Tor-based) search
- you cannot or should not access dark web content in your jurisdiction
- you need a fully automated pipeline without interactive investigation
- you are unwilling to run Tor or expose queries to third-party LLM APIs

## Facets
- artifact type: application
- maturity: active
- function: osint, search-engine, web-scraping, llm-inference, rag, chat-interface
- domain: osint, security, artificial-intelligence, large-language-models
- platform: windows, python, self-hosted
- tags: dark-web, tor, streamlit, investigation, multi-model-llm, open-source-intelligence, search, linux, docker, web-server

## Member repositories
- apurvsinghgautam/robin (main) score 84

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:09:43.389852+00:00.
- Health v2: computed from the inputs above; adoption is never an input.
- Inferred fields (summary, facets, guidance): AI-extracted, prompt v1, taxonomy v1, on 2026-08-29T17:44:43.013092+00:00, confidence not recorded.
  - readme: https://github.com/apurvsinghgautam/robin (fetched 2026-08-28T04:09:43.389852+00:00, sha ab8e6013a743)
- Data as of 2026-08-30T08:39:29.467469+00:00.