High performance graph data structures and algorithms
High performance graph data structures and algorithms (legacy package)
Retriever combining unstructured similarity and structured document traversal.
Redis-backed data structures for building scalable and resilient applications
An interactive graph of your Django model structure.
Utilities for working with structure graphs
Python package for fast exact clustering of similar molecular structures through parameterized connectivity graphs.
Self-hosted RAG engine: hybrid dense+sparse retrieval, 28-format ingestion (docs, URLs, images, audio, video), 6 vector backends, 8 embedding providers, 12+ generation providers with automatic fallback, query rewriting (HyDE/contextual/multi-query), structured JSON output, real per-call cost tracking, and standalone retrieval via retrieve(). Composable with the optional ragleap-graph package for knowledge-graph-augmented retrieval. BYOK, no vendor lock-in, no hardcoded model defaults.
Frugal, embeddable graph building block for agentic systems — tree-sitter code impact analysis and structure explanation over a local DuckDB file, no external service.
Standalone observed-fact graph substrate for code and document structure
MCP code-intelligence server for AI agents — a more complete and more correct call graph with classified, cross-file edges. 8 facade MCP tools, 13 curated skills, structured JSON output, 100% local.
Andrey: accelerated, accurate, agentic causal discovery. Install andrey-core, import andrey.
A collection of robust, efficient and small classic algorithms and data structures.
A graph-based scheduler of nodes based on structure and conditions
MCP server wrapping AlphaFold DB and 8 other biomedical data sources, with a local SQLite knowledge graph.
A Python library for multi-object tracking data structures and algorithms
Local codebase intelligence system: structural graph + compass + wiki + agent memory
DTree (part of Triordinal): incremental encoding of the topology of directed trees by two projections (Q1, Q2): O(1) reachability, and/or queries on the topology of the tree, dynamic (incremental) updates
AnGIneer docs engine: parse pipeline (source_prep -> MinerU -> PoPo -> structure -> FTS -> vectors -> graph), retrieval and export
Production-ready Python framework for AI agents with multi-agent graphs, hybrid RAG, guardrails, audit logging, 50 evaluators, and a visual builder. Supports OpenAI, Anthropic, Gemini, Ollama. By NichevLabs.
Leveraging graph data structures for complex feature engineering pipelines.
Python bindings for the Surprise network community structure metric
Structural verification of multiagent systems
MCP server that gives LLMs a structural map of any codebase — entities, relationships, and flows — so they navigate to the right files without reading everything first.
Data structure and algorithm helpers for LeetCode-style Python: grids, adjacency, binary search bounds, heaps, trees, linked lists.
Ancestral recombination graph (ARG) data structure and operations
Python implementation of algorithms on string handling, data structure, graph processing, etc
A powerful tool for transforming documents into graph-based structures using Large Language Models (LLMs).
Open-source toolkit for explainable money-laundering detection on transaction graphs (structural motifs + Graph Neural Networks).
Turnkey zero-dependency four-pillar cognitive memory framework (Epistemic, Semantic, Episodic, Structural Code Graph) with MCP server for Claude Code, Cursor, Codex, OpenCode, Antigravity, and more
Local-first, deterministic repository structure and data lineage analysis
Tools for inferring relations from binary co-occurrence data
Graph-structured tool retrieval for LLM agents — zero-dependency, ontology-aware hybrid search
Library for extracting structured data from websites using ScrapeGraphAI
Code structure for coding agents: classes, functions, callers and headings with line numbers, as an MCP server and the sct shell command. 20+ languages, tree-sitter, no index.
Ontology Quality Suite -- assess OWL2 DL/RL/QL ontologies, TARQL/oxi-gen CONSTRUCT-query sketches, and the RDF data graphs they triplify -- structural, logical, documentation, efficiency, style, data quality, OWL2 profile membership, and reasoner-based consistency -- plus ontology-version and TARQL/ontology consistency checking with suggested repair diffs, locally or against a live Fuseki triplestore.
Associative memory and categories based on a directed acyclic graph data structure
CLI tool that analyzes GDScript codebases and produces a structured JSON graph of files, metrics, and relationships.
A comprehensive Python toolkit for deconstructing metal-organic frameworks (MOFs) into building units, analysing porosity, removing unbound guest molecules, determining framework topology with RCSR net identification and generating cheminformatics descriptors for structural components.
Meta-layer structural facts, governance audits, and narrative artifacts for AI coding sessions (Rust carrier): symbol truth queries, caller edges/closures, completeness audits, graph engine
Lifetime persistent memory for LLMs. A lightweight SDK for structured knowledge graphs.
Adjustment Identification Distance: A 𝚐𝚊𝚍𝚓𝚒𝚍 for Causal Structure Learning
Turn graphs, charts and numerical data into structured, navigable sound.
Project relational and structured data sources as a graph in ArangoDB.
Knowledge graph for TypeScript/JavaScript codebases — AST extraction, hybrid semantic+structural search