OpenViSTAI · Agents · Blockchain · Crypto
Submit a project
Menu
Research Agents

Openosint

Openosint is a Python OSINT investigation agent for security researchers and analysts. It provides a natural-language interface to 21 investigation tools and can run as a REPL, CLI, MCP server or browser-based web UI. Its MCP server exposes tools to compatible AI clients, and findings are shown with the tool calls that produced them.

Explore the practical guide ↓

Independent OpenViST project profile, based on linked sources.

Openosint — OpenViST project profile in Research Agents.
OpenViST project illustration. See the linked sources for product details.
Understand the project

Practical overview

When it fits

Use Openosint when you need an interactive, tool-backed OSINT workflow through a terminal, browser UI or MCP-compatible AI client, and can verify the resulting leads independently.

Who it is for

  • Security researchers conducting authorized OSINT investigations.
  • Analysts who want to coordinate investigation tools through natural-language prompts.
  • Users of MCP-compatible AI clients who want those clients to invoke Openosint tools.

Documented uses

  • Investigate email addresses, usernames, domains, IPs and related leads using available research tools.
  • Chain tools as findings emerge, such as pivoting from breach findings to a GitHub profile.
  • Review the tool calls associated with findings and save CLI or REPL investigation reports.
  • Expose investigation tools to a compatible AI client through MCP.
Before you choose

Requirements & limits

The repository is public and MIT-licensed. The self-hosted project is described as free. Its local web UI can start without an AI key for keyless tools; AI chat needs a provider key or local Ollama.

  • Choose the browser UI for interactive chat and tool cards; choose the CLI or REPL when you need reports saved to a local reports directory.
  • The web UI writes no reports. CLI and REPL reports are saved as Markdown and PDF; PDF generation uses optional reportlab.
  • AI backends include Claude, local Ollama and OpenAI-compatible endpoints. The repository describes passive MCP tools as enabled by default and active tools as requiring an explicit option.
  • The README cautions that AI summaries are leads to verify, not proof, and limits intended use to legal and authorized research.

Check current requirements in the official documentation. Source-based guidance does not mean OpenViST has run or independently tested this project.

Source-based practical guide

Start the browser-based interface with uvx

Launch the local Openosint web interface and know what is needed for AI chat.

Before you start

  • Install uv using the instructions for your operating system.
  • For AI chat, configure a provider key such as ANTHROPIC_API_KEY or use local Ollama; keyless tools can start without these.

Steps

  1. Run uvx openosint web in a terminal.

  2. Open the displayed local address, normally http://127.0.0.1:8080/, if the browser does not open automatically.

  3. Use keyless tools directly, or configure an AI provider key or local Ollama for AI chat.

Expected outcome

The browser UI runs locally, with keyless tools available and AI chat available when a provider is configured.

Guide limitations

  • The web UI does not save investigation reports.
  • This is a setup guide; it does not verify a particular investigation or provider configuration.
Documentation 1 ↗
Evidence and transparency

Sources & review

Official repository ↗
Source record details
Source availability
Active
Sources checked
11 October 2026
Original website title
OpenOSINT/OpenOSINT · Official homepage title · retained in its source language
How we review sourcesSuggest a correction