DeepTrace
DeepTrace is an AI-powered OSINT (Open Source Intelligence) agent that investigates people the way a skilled human investigator would — not just searching for a name, but following the trail.
Core trick
Recursively turns each extracted fact into new targeted searches up to a user-set depth, building a live search tree.
Description
DeepTrace is an AI-powered OSINT (Open Source Intelligence) agent that investigates people the way a skilled human investigator would — not just searching for a name, but following the trail.
Standard search tools stop at the surface: a LinkedIn, a Twitter, maybe a GitHub. DeepTrace goes further. You give it a name and any seed information you have, and it recursively searches, extracts facts, draws inferences, and spawns new searches from those inferences — automatically. Found that someone went to Stuyvesant High School and loves physics? It'll check Physics Olympiad records. Found a volleyball reference? It'll pull the school's sports roster. Each discovery becomes a new lead.
The problem it solves: public information about a person is scattered across dozens of sources, and connecting the dots requires hours of manual cross-referencing that most tools don't attempt. DeepTrace automates the inference chain — the "what would a detective think to look up next?" — at machine speed, across a user-controlled recursion depth from a quick surface scan all the way to a deep multi-hop investigation.
The output is a structured intelligence report with a live-updating search tree showing exactly how each discovery led to the next — full transparency into the investigative reasoning, not just the results.
README excerpt
# TO AI AGENTS # 🕵️ DeepTrace — AI Personal Investigator Agent ### Full Project Description & Agent Spec for One-Shot Development --- ## Executive Summary **DeepTrace** is a recursive, multi-depth OSINT (Open Source Intelligence) aggregation agent. Given a name and any seed identifying information, it performs layered web searches with inference chains — mimicking how a skilled human investigator would progressively uncover, cross-reference, and deduce information from publicly available sources. The key differentiator is **recursive inference**: each discovered fact is treated as a new lead that spawns additional targeted searches, controlled by a user-specified recursion depth. --- ## Problem Statement Standard chatbot searches for a person are shallow. If you ask "find information about Eric Zou," the model returns LinkedIn, maybe a Twitter, maybe a GitHub. It stops there. A trained investigator wouldn't stop there. They'd look at the LinkedIn, see Eric studied physics and went to a specific high school, infer he may have competed in Science Olympiad or Physics Olympiad, and search those databases. They'd check the high school's sports rosters. They'd look at who he follows on Instagram to infer hobbies and locations. They'd cross-reference mutual connections to deduce employers or research groups. **DeepTrace automates this investigative reasoning loop.** --- ## User Story > **As a** journalist, HR professional, competitive intelligence analyst, or curious ind