Projects sharing features with GraphGPT

llm-graph-builder is a tool for transforming unstructured data into structured Neo4j graph databases using large language models. It functions as a graph orchestrator that automates the construction of nodes and relationships from raw text based on custom schemas. The project provides a visualizer for analyzing relational data as interactive networks and a token monitor to track daily and monthly API consumption per user. It also includes a vector embedding generator that utilizes configurable model providers to enable semantic search and retrieval augmented generation. The system covers cap

Memgraph is an in-memory, distributed graph database designed for high-performance labeled property graph management. It utilizes a Cypher query engine for declarative data retrieval and manipulation, providing a scalable knowledge graph backend that integrates vector search and graph traversals. The system distinguishes itself as a real-time graph analytics platform, employing native C++ and CUDA implementations to execute complex network analysis and dynamic community detection on streaming data. It provides specialized support for AI integration, including GraphRAG capabilities, the constr

Hyper-Extract is a framework designed for automated knowledge extraction, graph construction, and retrieval-augmented generation. It functions as a command-line tool that transforms unstructured text into structured knowledge graphs and hypergraphs, enabling users to build interconnected, searchable, and machine-readable data repositories from their documents. The system distinguishes itself through its focus on personal knowledge management and incremental processing. It allows users to update existing knowledge bases by processing only new document deltas, avoiding redundant computation. Th

Entity-Relation-Extraction is a machine learning framework designed to identify entities and their logical connections within unstructured text. It functions as a pipeline that transforms raw documents into structured knowledge graphs by utilizing deep learning models and transformer architectures. The project distinguishes itself through a schema-driven approach, which maps extracted information to predefined relational templates to ensure output consistency. It employs a multi-stage process that combines sequence-labeling token classification with contextual encoding to delineate entity bou

OpenViking is a multi-tenant context server and knowledge base administration system designed to provide AI agents with persistent long-term memory. It enables the indexing of diverse documents and codebases to support retrieval-augmented generation, allowing agents to recall past interactions, user preferences, and learned experiences across sessions. The project is distinguished by its use of a URI-based virtual filesystem to organize memories, resources, and skills. It implements a tiered context loading system that balances retrieval precision with token budgets by structuring data into a

gbrain is an agent framework and retrieval-augmented generation system that combines a durable task queue, a git-synced vector store, and a knowledge graph engine. It provides a foundation for building AI agents that interact with structured knowledge bases using the Model Context Protocol. The system synchronizes markdown files from a git repository into a database for high-performance semantic retrieval and creates typed edges between data pages by extracting entity references and wikilinks. It uses a database-backed queue to execute persistent background jobs and tool loops, ensuring relia

DeepKE is a knowledge extraction toolkit and framework designed to transform unstructured text into structured knowledge graphs. It provides a pipeline for identifying and classifying named entities, semantic relations, and events, converting raw datasets into structured triples. The project utilizes large language models as tool callers through a standardized context protocol to drive automated data extraction processes. It supports schema-driven extraction across multiple domains and bilingual text, employing joint entity and relation extraction to identify components in a single structured

AgentMemory is a persistent knowledge store and memory server designed to provide AI coding agents with long-term memory. It functions as a knowledge graph engine and vector database store that saves and recalls project context, architectural decisions, and patterns across different sessions. The system distinguishes itself by using a tiered-memory consolidation pipeline that compresses raw observations into episodic, semantic, and procedural layers to optimize token usage. It employs a hybrid retrieval strategy combining keyword matching, vector embeddings, and graph traversal to surface rel

KnowledgeGraphCourse is a structured collection of graduate-level academic materials, lecture notes, and a comprehensive curriculum focused on the theory and application of knowledge graphs. It serves as a markdown-based educational resource that provides navigable course modules and study guides. The material covers specialized research on integrating knowledge graphs with large language models to reduce hallucinations. It includes detailed guides on using the SPARQL language for storing large-scale graph datasets and executing optimized queries. The curriculum spans a broad range of capabi

Cocoindex is an incremental data processing engine that builds and maintains live indexes for AI agents, with a core focus on codebase indexing and knowledge graph extraction. The engine uses a function-graph execution model where user-defined Python functions are composed into a directed acyclic graph, and it processes data incrementally so only changed source records or code paths are re-computed, avoiding full recomputation at any scale. It supports automatic schema inference from transformation pipeline type annotations and provides full data lineage tracing, tagging every output record wi

KnowledgeGraphData is a collection of structured datasets and corpora designed to provide a foundational layer for cognitive intelligence and artificial intelligence systems. It primarily consists of large-scale Chinese knowledge graph datasets, including entity-relation data and NLP training sets used to drive semantic understanding and automated question answering. The project focuses on the construction and export of massive entity-attribute-value graphs, organizing knowledge into portable formats. It provides specialized domain partitioning to tailor information retrieval for professional

Agriculture Knowledge Graph is a structured triple-store system and decision support platform designed to transform raw agricultural documents into a machine-readable graph. It functions as a domain information retrieval system that extracts and queries agricultural data to provide intelligent answers and planning support. The project implements a full pipeline for knowledge graph construction, featuring a relation extraction framework and named entity recognition tools. It utilizes remote supervision and machine learning to identify and classify relationships between entities, converting uns

Ragas is an evaluation framework designed to measure the performance of retrieval-augmented generation pipelines and autonomous agent workflows. It provides a comprehensive suite of tools for benchmarking system outputs, utilizing language models as automated judges to score performance against defined rubrics and reference data. By standardizing inputs, retrieved contexts, and generated responses into a unified schema, the project enables consistent analysis across complex AI applications. The framework distinguishes itself through its ability to generate synthetic test datasets from existin

This project is a Python-based framework that functions as a generative AI agent for programmatic data analysis. It enables users to interact with structured data sources through natural language prompts, translating these requests into executable code to perform analysis, data cleaning, and visualization. By maintaining conversational context across multi-turn interactions, the system allows for iterative exploration and the building of complex data narratives. The framework distinguishes itself through a robust semantic layer and secure execution model. It maps raw datasets to descriptive m

whodb is a multi-database management interface and notebook client designed for exploring and managing data across various engines, including Postgres, MySQL, MongoDB, and Redis. It functions as a graphical interface for managing database connections, records, and schemas through a unified layer. The project features a natural language query interface that uses large language models to translate plain English into executable SQL or NoSQL queries. This is supported by schema-aware prompting that injects database metadata into the model context to ensure generated queries match actual table def

Page-agent is an LLM browser automation agent and JavaScript in-page GUI controller. It translates natural language instructions into direct browser interface actions to automate web-based tasks and manipulate web page elements through a programmable interface. The system coordinates complex sequences of actions across multiple browser tabs and different websites. It functions as a remote browser control server, providing an interface that allows external clients to operate a browser and manage page interactions. Its capabilities include natural language intent decoding and action mapping, D

Pandas AI is a data analysis library and natural language interface that uses large language models to perform conversational querying on structured datasets. It functions as a retrieval-augmented generation framework designed to translate plain text questions into executable code for extracting insights from dataframes and structured files. The system includes a dedicated sandbox execution environment that runs AI-generated analysis code within an isolated container to prevent security risks and system compromise. It employs a natural language translation layer and contextual retrieval to ma

Transformers Tasks is a collection of toolkits and scripts dedicated to language model fine-tuning, natural language processing tasks, and transformer-based pipelines. The project functions as a natural language processing toolkit and transformer pipeline library, providing Python scripts and algorithms designed to adapt foundational language models and route text inputs through modular processing workflows. The repository covers supervised fine-tuning pipelines and reinforcement learning alignment procedures that optimize generative text outputs through reward modeling and policy gradient lo

This project is a platform that orchestrates multiple AI agents to automate data science workflows—covering data loading, cleaning, feature engineering, modeling, and querying. It also functions as a natural language database query interface, converting plain English questions into SQL, and as a visual data pipeline builder. Custom agents are generated on demand by filling prompt templates for tasks like data cleaning and feature engineering. Pipelines incorporate human-in-the-loop checkpoints that pause execution for review and approval. Intermediate results are saved as versioned files, ena

FinGPT is a suite of specialized financial tools and a framework for adapting large language models to the financial domain. It provides a set of pipelines for financial entity extraction, sentiment analysis, and retrieval-augmented generation to improve the accuracy of financial information systems. The project distinguishes itself through efficient training workflows, utilizing low-rank adaptation and quantized low-rank adaptation to fine-tune models on consumer-grade hardware. It employs market-labeled datasets and reinforcement learning that uses actual stock price movements as reward sig

SQL Chat is a Docker-deployed chat interface that translates natural language questions into SQL queries and executes them against connected databases. It uses a large language model to generate SQL from plain English instructions, supporting both querying and record modification through INSERT, UPDATE, and DELETE statements within the chat conversation flow. The application connects to MySQL, PostgreSQL, MSSQL, TiDB Cloud, and OceanBase databases through a unified driver abstraction layer, allowing users to interact with multiple database types from a single chat interface. Users provide the

Shell GPT is an AI-powered command-line interface that generates shell commands and source code from natural language prompts. It serves as a terminal-based tool for automating technical tasks, producing executable commands, and generating code snippets directly within the shell. The tool distinguishes itself through a read-eval-print loop for interactive chatting and the ability to maintain stateful conversational history via named sessions. It supports flexible backend routing, allowing users to connect to cloud-based APIs or local language model hosts for offline operation and data privacy

Pulse is an AI-driven infrastructure monitoring platform that unifies observation of Docker, Kubernetes, and Proxmox environments. It uses historical baselines and anomaly detection to scan infrastructure for actionable issues, and offers a natural language interface for querying system state. The platform distinguishes itself with agent-based auto-discovery—a single binary automatically detects container and virtualization hosts without manual setup. It supports approval-based remediation workflows, where AI-proposed fix commands are presented to the user and executed only after explicit aut

Scrapegraph-ai is a Python framework that uses large language models to automate the extraction of structured data from websites and documents. It functions as an AI-driven data extraction pipeline that converts unstructured web content into structured formats using natural language processing and graph-based logic. The project utilizes graph-based task orchestration to model scraping workflows as interconnected nodes. It features a pluggable model interface for connecting to cloud or local artificial intelligence providers and can generate executable Python code on the fly to handle site-spe

OpenNRE is a natural language processing library and neural relation extraction framework designed to transform unstructured text into structured relational data. It serves as a toolkit for identifying relationship types between entities and generating entity-relation-entity triples to populate and expand knowledge bases. The framework provides tools for both supervised and distantly supervised relation extraction, allowing neural models to be trained on labeled datasets or via automated pipelines that align knowledge base triples with raw text. The project covers a full information extracti

Cocoindex is a command-line code search engine and indexing tool that combines abstract syntax tree pattern matching and semantic vector embeddings for precise code discovery. It functions locally and integrates with AI coding assistants to automatically retrieve necessary codebase context through standardized communication protocols and persistent background daemon services. The platform employs an asymmetric embedding architecture that generates vector representations using separate parameters for document indexing and search queries. It supports incremental index maintenance by tracking fi

Understand-Anything is a codebase architecture visualization tool that transforms source code and documentation into interactive knowledge graphs. It maps files, functions, and classes into a node-edge model to visualize architectural dependencies and project structures. The project provides specialized workflows for impact analysis, tracing connectivity paths from code modifications to identify affected downstream components. It also enables technical onboarding through automated architecture tours and the conversion of technical documentation into navigable networks of interconnected ideas.