# OpenOSINT/OpenOSINT

AI-powered OSINT agent with interactive REPL, MCP server, and CLI. 19 tools. Works with Claude, GPT-4, or local models. For authorized security research only.

Repository: https://github.com/OpenOSINT/OpenOSINT
Canonical: https://ross.abutalabs.com/products/openosint
Homepage: https://openosint.tech
Language: Python
License: MIT
License Family: permissive
Topics: ai-agent, anthropic, claude, cybersecurity, osint, python, security, terminal, cli, holehe, mcp, sherlock, llm, mcp-server, model-context-protocol, threat-intelligence, maigret, osint-tools, reconnaissance
Last push: 2026-08-26T10:46:40+00:00

## Health v2 (maintenance only)
Score: 81/100 (v2, computed 2026-09-02T17:46:02.011165+00:00)
- activity 99, release rhythm 99, longevity 8
- inputs: {"age_days": 119, "days_push": 7, "days_rel": 7, "gap_med": 1.0, "n_releases_24m": 31}
- flags: young
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 1470, forks 239 (observed 2026-08-28T04:04:48.873608+00:00)

## What it is
OpenOSINT is an AI-powered OSINT framework offering 19 investigation tools behind a natural-language agent, usable as an interactive REPL, direct CLI, MCP server, or browser Web UI. It works with Claude, GPT-4, OpenRouter, or local Ollama models and is intended for authorized security research only.

## Use cases
- run osint investigations from the terminal with an ai agent
- check email breach exposure from the command line
- find usernames across social platforms for a target handle
- expose osint tools to claude via an mcp server
- look up ip reputation and geolocation for threat intel
- automate reconnaissance workflows with llm tool chaining

## When to choose
- you want natural-language-driven OSINT investigations with 19 bundled tools
- you need an MCP server to give Claude or other agents OSINT capabilities
- you want both an interactive REPL and scriptable direct CLI modes
- you prefer local models via Ollama for sensitive investigations

## When to avoid
- you need a GUI-first OSINT platform rather than a terminal tool
- your use case is not authorized security research
- you want fully offline operation without any LLM or external APIs
- you need guaranteed accuracy — AI tool chaining can still misinterpret findings

## Facets
- artifact type: cli-tool
- maturity: active
- function: osint, agent-framework, mcp, cli, security, llm-inference
- domain: security, osint, artificial-intelligence, developer-tools
- platform: python, cli, cross-platform, browser
- tags: osint-framework, mcp-server, threat-intelligence, reconnaissance, repl, claude, ollama, openai, investigation-tools, pentest, ai-agents, command-line, docker

## Member repositories
- OpenOSINT/OpenOSINT (main) score 81

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:04:48.873608+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 2026-08-30T04:34:47.881958+00:00, confidence not recorded.
  - readme: https://github.com/OpenOSINT/OpenOSINT (fetched 2026-08-28T04:04:48.873608+00:00, sha 3fa99428d1cb)
  - homepage: https://openosint.tech (fetched 2026-08-29T11:42:41.410881+00:00, sha f06268fbd4f7)
  - registry_pypi: https://pypi.org/pypi/openosint/json (fetched 2026-08-29T11:42:41.422722+00:00, sha da8ebcc3eb84)
  - site_page: https://openosint.tech/sponsors.html (fetched 2026-08-29T11:42:41.420771+00:00, sha 2897d058e06e)
- Data as of 2026-08-30T08:39:29.467469+00:00.