ByteZone
Back to listClaim this project

OpenOSINTSecurity & privacy

OpenOSINT

AI-powered OSINT investigation agent integrating 19 reconnaissance tools via REPL, CLI, and MCP.

  • Security
  • CLI
  • Web
  • API/SDK
  • Windows
  • macOS
  • Linux
  • Browser
  • Self-hostable
  • Runs locally
  • Docker supported
  • Needs API key
Open websiteView on GitHub
OpenOSINT screenshot
Popularity
1.6k Stars
GitHub stars
Recent activity
9/18/2026
Updated in the last 30 days
License
MIT
Permissive

Why it matters

We look beyond stars: what problem it solves, whether it creates real utility, and what makes its approach worth noticing.

Last 90 days

Problem

Security researchers often have to manually execute and chain findings across multiple OSINT tools and APIs like holehe, sherlock, and Shodan.

Practical value

Encapsulates 19 popular OSINT tools, supporting natural language tool chaining, concurrent execution, and automatic report saving.

Innovation / differentiation

Integrates traditional CLI and API OSINT utilities into an MCP server and AI agent framework, relying on deterministic tool execution to eliminate LLM hallucinations.

Leverage potential

Standardizes MCP interfaces and supports multiple LLM backends including local Ollama, making it easy to integrate into Claude Desktop, Cursor, or existing SOC workflows.

Why now

Aligns with the rapid adoption of Model Context Protocol (MCP) and growing demand for domain-specific AI security agents.

Community activity

In the last 90 days there were 10 new issues and 37 pull requests; the bounded issue/PR samples include 10 issue authors and 6 PR contributors, with 9 releases.

Maintainer responsiveness

The 10-issue window sample had a 0% close rate, and the 37-pull-request sample had a 84% merge rate. Maintainer-response observations covered 100% of that issue sample, with a 0% response rate and median first response of not enough data.

6 contributors in PR sample9 releasesIssue response rate 0% · sample 10 (100% coverage)PR merge rate 84% · 37 sampled in window

Key highlights

  • Autonomous Tool Chaining: Dynamically selects and chains tools based on prior investigation findings
  • 19 Modular Recon Tools: Covers email lookup, username search, data breaches, WHOIS, IP intelligence, and domain analysis
  • Flexible AI Backends: Works with Anthropic Claude, local Ollama models, or OpenAI-compatible endpoints

Quick start

How it is installed, how hard it is, and where to start.

Where it runs

To be confirmed

Difficulty

To be confirmed

Docker supportedSelf-hostableRuns locally
  1. 01Install the OpenOSINT package using pip
  2. 02Start the interactive AI REPL interface
  3. 03Enter a natural language command in the REPL to investigate a target
  4. 04Launch the browser-based Web UI for interactive chat
  5. 05Run a direct tool command without involving the AI agent

Best for

  • Teams that want data on their own servers
  • Developers who want to try it on their machine
  • People who prefer Docker deploys

More about it

OpenOSINT is an AI-driven agent tailored for security researchers and threat intelligence analysts. Wrapping 19 OSINT tools such as Holehe, Sherlock, and PhoneInfoga, it supports interaction through a CLI REPL, Web UI, or MCP server. The AI issues deterministic tool calls executed by local code, ensuring findings are derived entirely from real API and tool outputs.

Sources

Each field shows its status and source — expand to review.

15 · Expand

  • capability tags

    Verified

    Source: admin_cms · cms editor · 9/14/2026

  • editor note

    Verified

    {"en":"OpenOSINT provides security analysts with a natural language framework for OSINT investigations. It orchestrates 19 tools including Sherlock, Holehe, and Shodan using Claude, local Ollama, or OpenAI-compatible backends. All tools execute real code to prevent hallucinated output, generating structured Markdown and PDF reports.","zh":"OpenOSINT 为安全研究人员提供了自然语言驱动的开源情报调查框架。它集成了 Sherlock、Holehe、Shodan 等 19 种常用侦察工具，支持 Claude、本地 Ollama 以及 OpenAI 兼容模型。工具通过实际命令行或 API 执行，避免生成虚构的调查结果，并支持自动输出 Markdown 与 PDF 格式的调查报告。"}

    Source: admin_cms · cms editor · 9/14/2026

  • how to use

    Verified

    {"steps":[{"en":"Install the OpenOSINT package using pip","zh":"使用 pip 安装 OpenOSINT 软件包"},{"en":"Start the interactive AI REPL interface","zh":"启动交互式 AI REPL 终端"},{"en":"Enter a natural language command in the REPL to investigate a target","zh":"在 REPL 终端中输入自然语言指令开始调查目标"},{"en":"Launch the browser-based Web UI for interactive chat","zh":"启动基于浏览器的 Web 界面进行交互"},{"en":"Run a direct tool command without involving the AI agent","zh":"不使用 AI，直接调用单项侦察工具查询目标"}],"installAt":"unknown","difficulty":"unknown"}

    Source: admin_cms · cms editor · 9/14/2026

  • intro

    Verified

    {"en":"OpenOSINT is an AI-driven agent tailored for security researchers and threat intelligence analysts. Wrapping 19 OSINT tools such as Holehe, Sherlock, and PhoneInfoga, it supports interaction through a CLI REPL, Web UI, or MCP server. The AI issues deterministic tool calls executed by local code, ensuring findings are derived entirely from real API and tool outputs.","zh":"OpenOSINT 是面向安全研究员与威胁情报分析师的智能体工具。系统封装了 Holehe、Sherlock、PhoneInfoga 等 19 种开源情报组件，允许用户通过命令行 REPL、Web 界面或 MCP 服务进行自然语言交互。在调查过程中，大语言模型仅负责下发具体的工具调用指令，实际执行过程由本地代码完成，从而保证调查数据的真实性。"}

    Source: admin_cms · cms editor · 9/14/2026

  • Latest release

    Verified

    v2.29.0

    Source: GitHub API · latest_release=v2.29.0 · 9/20/2026

  • License

    Verified

    MIT

    Source: GitHub API · license.spdx_id=MIT · 9/20/2026

  • needs api key

    Verified

    Yes

    Source: admin_cms · cms editor · 9/14/2026

  • One-liner

    Verified

    {"en":"AI-powered OSINT investigation agent integrating 19 reconnaissance tools via REPL, CLI, and MCP.","zh":"基于 AI 智能体与 19 种工具集成的开源情报 (OSINT) 调查框架"}

    Source: admin_cms · cms editor · 9/14/2026

  • Platforms

    Verified

    windows, macos, linux, browser

    Source: admin_cms · cms editor · 9/14/2026

  • Category hint

    Inferred from materials

    ai-apps

    Source: Project README · hint=ai-apps · 8/17/2026

  • product forms

    Verified

    cli, web, api_sdk

    Source: admin_cms · cms editor · 9/14/2026

  • role tags

    Verified

    security

    Source: admin_cms · cms editor · 9/14/2026

  • supports docker

    Verified

    Yes

    Source: Repository file · dockerfile=true; compose=true · 9/20/2026

  • supports local

    Verified

    Yes

    Source: admin_cms · cms editor · 9/14/2026

  • supports self host

    Verified

    Yes

    Source: admin_cms · cms editor · 9/14/2026

Related projects

Other verified projects matched by category, capabilities, and intended roles.

vault

An open-source security platform for centralized management, encryption, and auditing of sensitive credentials like API keys, passwords, and certificates.

Same Security & privacy categoryBoth fit Security

openbao

An open-source secrets management system for storing, distributing, rotating, and controlling access to secrets, certificates, and keys.

Same Security & privacy categoryBoth fit Security

fleet

A device-management platform for IT and security teams covering MDM, software deployment, patching, inventory queries, and compliance across desktop and mobile operating systems.

Same Security & privacy categoryBoth fit Security

syzkaller

An unsupervised, coverage-guided kernel fuzzer that supports multiple operating systems.

Same Security & privacy categoryBoth fit Security

agent-governance-toolkit

A governance toolkit for AI agents that adds policy checks, identity, audit trails, sandboxing, and SRE controls across multiple agent frameworks.

Same Security & privacy categoryBoth fit Security

cli

Command-line tool to scan and monitor software projects for security vulnerabilities.

Same Security & privacy categoryBoth fit Security