Search results

Distributed system for embedding-based vector retrieval.

Open-source project that supports AI-assisted research, knowledge retrieval, summarization, or source analysis.

Google Dork Cheatsheet

github.com

GitHub cheatsheet of Google dork operators and search patterns for finding exposed information.

OSINT framework for finding public information linked to phone numbers, emails, usernames, and other identifiers.

snoop is an online tool that helps users work with usernames, digital identities, or related information for research and testing.

Easy way to turn any app into searchable data for LLMs.

AquilaDB

github.com

Easy to use Neural Search Engine. Index latent vectors along with JSON metadata and do efficient k-NN search.

BigSearch is an open source search or OSINT resource for finding information across public web sources.

Latest Papers and Datasets on Multimodal Large Language Models, and Their Evaluation.

Chiasmodon is an OSINT tool designed to assist in the process of gathering information about a target domain. Its primary functionality revolves around searching for domain-related data, including domain emails, domain credentials, CIDRs , ASNs , and subdomains, the tool also allows users to search Google Play application ID.

Open source OSINT tool for collecting public information from phone numbers and related online identifiers.

Command-line CPU information tool showing processor details in a terminal display.

Cyber Detective's OSINT Collection is an open source search or OSINT resource for finding information across public web sources.

Open-source project that provides machine-learning models, research, training resources, or evaluation tools.

Open-source project that provides machine-learning models, research, training resources, or evaluation tools.

Scala Library/REPL for Machine Learning Research.

The OSINT project, the main idea of which is to collect all the possible Google dorks search combinations and to find the information about the specific web-site: common admin panels, the widespread file types and path traversal. The 100% automated.

Framework for building applications with LLMs and Transformers (e.g. agents, semantic search, question-answering).

Implementation of image to image (pix2pix) translation from the paper by isola et al.[DEEP LEARNING].

AI-native database built for LLM applications, providing incredibly fast vector and full-text search.

Autograd and XLA for high-performance machine learning research.

A project to make it easier to use large external knowledge bases with LLMs.

A deep research tool for searching academic sources, the web, and private documents with local or cloud LLMs. opensource.

An MCP tool that connects Google Ads with Claude AI/Cursor and others, allowing you to analyze your advertising data through natural language conversations. This integration gives you access to campaign information, performance metrics, keyword analytics, and ad management—all through simple chat with Claude, Cursor or Windsurf.