Awesome GitHub RepositoriesMetadata Filtering

PageIndex is an agent-ready knowledge engine that processes documents into hierarchical tree structures to enable reasoning-based information retrieval. By organizing content into logical trees rather than relying on traditional vector database chunking, the platform preserves the original structure and flow of complex documents. It functions as a Model Context Protocol server, allowing external AI agents to connect to and query indexed knowledge bases through standardized communication protocols. The platform distinguishes itself by using vision-language models to process raw document images

Qdrant is a high-performance vector similarity database designed to store, index, and search high-dimensional vectors alongside structured metadata. It functions as a distributed search engine that manages large-scale data clusters, providing low-latency retrieval and complex filtering capabilities. The system is built to serve as a specialized middleware layer, connecting machine learning pipelines and AI agents to persistent storage for intelligent information retrieval and recommendation tasks. The platform distinguishes itself through advanced retrieval techniques, including support for h

Chroma is a specialized vector database designed to index and retrieve high-dimensional data representations for semantic similarity search. It functions as a comprehensive platform for information retrieval, enabling the storage and management of unstructured documents alongside structured metadata. By mapping data into numerical representations, the system facilitates rapid similarity lookups across large datasets. The platform distinguishes itself through a hybrid search infrastructure that combines dense vector embeddings with sparse keyword and regular expression matching to balance sema

ILSpy is a .NET decompiler and binary analyzer designed to convert compiled .NET assemblies back into readable C# source code. It functions as a metadata explorer and a common intermediate language viewer, enabling the analysis of compiled code and the execution of reverse engineering workflows. The project distinguishes itself through specialized translation capabilities, such as converting compiled binary XML (BAML) back into human-readable XAML for user interface analysis. It also provides tools for inspecting native machine code and extracting metadata from program database (PDB) files.

Deepagents is an LLM agent orchestration platform and stateful application server designed for deploying and managing AI agents built with computational graphs. It provides a containerized runtime environment that handles agent execution, state persistence, and the versioning of AI assistants. The platform distinguishes itself through deep integration with the Model Context Protocol, allowing agents to function as servers that expose tools and capabilities to external clients. It features a sophisticated observability suite for capturing execution traces, performing LLM-based evaluations agai

Calibre is a comprehensive suite for digital library management, serving as a centralized hub for organizing, converting, and editing e-book collections. It functions as a multi-purpose platform that combines a relational database for metadata tracking with a powerful processing engine capable of transforming document formats and restructuring internal markup. Beyond local management, the software acts as a content server, enabling users to host their libraries over a network for remote access and reading via standard web browsers. The project distinguishes itself through its deep extensibili

This project is a retrieval-augmented generation pipeline designed for building custom ChatGPT plugins that allow language models to query private or professional documents. It implements a full retrieval workflow, from processing and indexing document chunks to retrieving relevant context for natural language queries. The system distinguishes itself through a hybrid retrieval approach that combines dense vector embeddings with sparse keyword matching, further refined by a two-stage semantic re-ranking process. It includes specialized data privacy tools for screening personally identifiable i

New-Grad-Positions is a centralized job aggregation platform designed to track and filter entry-level career opportunities for recent graduates across technical industries. The system functions as an automated career search tool, utilizing a relational database schema to organize job listings and user profiles for efficient querying. The platform distinguishes itself through integrated browser-based automation that populates online job application fields to reduce manual data entry. It further supports career search automation by monitoring new listings and triggering email alerts based on sp

Tolaria is a markdown knowledge base manager and bidirectional note linking system. It functions as an integrated environment for organizing notes and structured data, utilizing YAML frontmatter and wikilinks to establish relational mappings between documents. The project distinguishes itself by integrating language model capabilities directly into the editor for content generation and analysis. It further combines prose with structured data through a markdown spreadsheet editor that renders CSV-formatted files as interactive grids with formula support and cross-sheet referencing. The platfo

Weaviate is a cloud-native vector database and distributed vector store designed to save high-dimensional vectors alongside structured data. It functions as a hybrid search engine that combines vector similarity, keyword matching, and structured metadata filtering within a single query. The system is optimized for retrieval-augmented generation, integrating vector search with generative AI and reranking to power question-and-answer workflows. It distinguishes itself through the ability to merge semantic search with traditional keyword queries and structured metadata filters to improve result

This project is a centralized index and aggregator for public, free-to-air television broadcasts. It functions as a searchable database and directory that organizes open-access internet streams, allowing users to discover and browse international television channels without subscription requirements. The platform distinguishes itself by utilizing standardized playlist formats to map remote stream URLs into a structured directory. It supports international media discovery by applying hierarchical metadata to filter content by geographic region and genre, facilitating the management of curated

Subfinder is a security reconnaissance framework designed for subdomain enumeration and attack surface management. It functions as a discovery engine that identifies and maps internet-exposed infrastructure, cloud-hosted assets, and network ranges to maintain a comprehensive inventory of an organization's digital footprint. The project distinguishes itself through a modular, template-driven scanning engine that executes security checks against discovered assets. It leverages cloud-native asset discovery to query provider APIs and infrastructure metadata, while supporting distributed agent orc

This project serves as a comprehensive resource hub for individuals navigating remote work, functioning as both a job aggregator and a professional development guide. It provides a centralized platform for discovering remote employment opportunities across diverse industries while offering structured insights into the challenges and requirements of a home-based career. The platform distinguishes itself by combining automated job discovery with a curated knowledge base focused on the nuances of distributed work. It enables users to filter listings based on specific professional taxonomies and

Instaloader is a Python library and command-line utility designed for the automated retrieval, archiving, and analysis of Instagram content. It provides a programmatic interface to fetch media, captions, and metadata from public or private profiles, hashtags, and stories, while maintaining persistent user sessions for authorized access. The tool distinguishes itself through robust archive management and traffic control mechanisms. It supports incremental synchronization, allowing users to resume interrupted downloads and update local collections without redundant requests. To ensure reliable

Isotope is a JavaScript grid layout library used to create filterable and sortable grids with automatic element positioning in the browser. It functions as a layout engine that calculates absolute coordinates for elements to maintain a dense grid regardless of individual item dimensions. The library features a masonry layout engine that arranges items of varying heights into a compact grid to eliminate vertical gaps. It includes a coordinate-based layout animator for smooth transitions during layout shifts and a CSS selector filtering tool to show or hide elements without reloading the page.

LanceDB is a vector database and columnar data store designed to function as a versioned dataset manager and vector search engine. It serves as a high-performance backend for indexing and retrieving high-dimensional embeddings, providing the foundation for machine learning data pipelines. The system distinguishes itself through a combination of cloud-native object storage and immutable version tracking, allowing for data time-travel and reproducible AI experiments. It integrates hybrid search capabilities, merging dense vector similarity with BM25 full-text search and SQL-like scalar filters

Maltrail is a malicious traffic detection system used for network intrusion detection. It consists of a network intrusion sensor for monitoring interfaces, a threat intelligence aggregator for syncing blacklists, and a detection engine that identifies security threats through signature matching and heuristic attack patterns. The system distinguishes itself through a distributed sensor architecture that collects traffic data from multiple remote probes and forwards events to a central analysis server. It employs heuristic behavioral analysis to identify unknown threats, such as port scanning o

This project is a metadata query engine and indexer for markdown files, designed to transform YAML frontmatter and inline fields into dynamic tables and lists. It provides a background process that extracts tags and custom fields into a searchable database, enabling the automated indexing of notes. The system is distinguished by its dual approach to data retrieval: a dedicated query language for SQL-like filtering and grouping, and a JavaScript data API. This API allows for programmatic metadata extraction and the creation of custom views and extensions using TypeScript typings. Its broader

git-standup is a command line interface tool that functions as a git commit activity summarizer and version control report generator. It aggregates commit messages and metadata from one or multiple repositories to track work activity and generate daily standup reports. The tool differentiates itself by providing multi-repository aggregation, scanning directories to compile a combined activity report across several projects. It includes features to synchronize remote data across these projects and utilizes a configurable work week schedule to calculate date ranges between workdays. The capabi

TubeArchivist is a self-hosted YouTube video archiving system and metadata indexer. It functions as a personal media library and download manager that allows users to create a searchable offline collection of videos, channels, and playlists. The system distinguishes itself by indexing subtitles, comments, and channel information for full-text search and retrieval. It features automated media synchronization to track subscriptions and playlists, ensuring new content is automatically queued and downloaded as it is published. The project provides a broad set of capabilities for digital asset ma