site_name: Hypabase
site_url: https://docs.hypabase.app/
site_description: A Python library for storing and querying n-ary relationships with provenance tracking. SQLite-backed, zero configuration.
repo_url: https://github.com/hypabase/hypabase
repo_name: hypabase/hypabase
theme:
name: material
custom_dir: overrides
palette:
- scheme: slate
primary: black
accent: blue
toggle:
icon: material/brightness-4
name: Switch to light mode
- scheme: default
primary: black
accent: blue
toggle:
icon: material/brightness-7
name: Switch to dark mode
features:
- content.code.copy
- content.tabs.link
- navigation.instant
- navigation.expand
- navigation.top
- search.highlight
- search.suggest
- toc.follow
plugins:
- search
- mkdocstrings:
handlers:
python:
options:
show_source: false
show_root_heading: true
heading_level: 2
members_order: source
docstring_style: google
show_signature_annotations: true
separate_signature: true
- mike:
alias_type: symlink
canonical_version: latest
- llmstxt:
full_output: llms-full.txt
markdown_description: >
Hypabase is a Python library for storing and querying relationships
between entities. A single edge connects two or more nodes, every edge
tracks where it came from (source and confidence), and the whole graph
lives in a local SQLite file with no server or configuration. Use it to
build knowledge graphs, RAG pipelines, and structured agent memory.
Python 3.10+. uv add hypabase.
sections:
Getting Started:
- index.md: "Quick install and first hypergraph — go from zero to a working knowledge graph"
- getting-started.md: "Step-by-step setup with SQLite persistence, namespace isolation, and provenance"
- concepts.md: "Core mental model — hyperedges, provenance, vertex-set index"
Guides:
- guides/traversal.md: "Find neighbors, shortest paths, and multi-hop connections through hyperedges"
- guides/provenance.md: "Track where every relationship came from and how confident you are in it"
- guides/batch-operations.md: "Ingest thousands of nodes and edges efficiently with batch, upsert, and cascade delete"
- guides/cli.md: "Create nodes, edges, and run queries from the terminal without writing Python"
- guides/hif.md: "Import and export hypergraphs using the HIF interchange format"
- guides/mcp.md: "Set up the MCP server so AI agents in Claude Code, Claude Desktop, Cursor, or Windsurf can use Hypabase as structured memory"
Examples:
- examples/medical-kg.md: "Build a clinical knowledge graph with treatment events, provenance, and query patterns"
- examples/rag-extraction.md: "Extract structured relationships from documents and query them as a hypergraph"
- examples/agent-memory.md: "Give AI agents persistent structured memory that survives across sessions and conversations"
- examples/hybrid-vector.md: "Combine Hypabase relationship queries with vector similarity search for hybrid retrieval"
Comparisons:
- comparisons/vs-neo4j.md: "Architectural differences between Hypabase and Neo4j for n-ary relationships"
- comparisons/vs-vector-dbs.md: "How Hypabase and vector databases complement each other"
- comparisons/vs-mem0.md: "Architectural differences between Hypabase and Mem0 for agent memory"
API Reference:
- reference/client.md: "Complete Hypabase client API — every method with parameters, return types, and examples"
- reference/models.md: "Pydantic models for nodes, edges, incidences, stats, and validation results"
- reference/cli.md: "CLI command reference — init, node, edge, query, stats with all flags and options"
extra:
version:
provider: mike
extra_css:
- stylesheets/extra.css
markdown_extensions:
- admonition
- pymdownx.details
- pymdownx.superfences
- pymdownx.tabbed:
alternate_style: true
- pymdownx.highlight:
anchor_linenums: true
- pymdownx.inlinehilite
- pymdownx.snippets
- attr_list
- md_in_html
- toc:
permalink: true
nav:
- Home: index.md
- Getting Started: getting-started.md
- Concepts: concepts.md
- Guides:
- Traversal: guides/traversal.md
- Provenance: guides/provenance.md
- Batch Operations: guides/batch-operations.md
- CLI Quickstart: guides/cli.md
- HIF Import/Export: guides/hif.md
- MCP Server: guides/mcp.md
- Examples:
- Medical Knowledge Graph: examples/medical-kg.md
- RAG Extraction Pipeline: examples/rag-extraction.md
- Agent Memory: examples/agent-memory.md
- Hybrid Vector Pattern: examples/hybrid-vector.md
- Comparisons:
- vs Neo4j: comparisons/vs-neo4j.md
- vs Vector DBs: comparisons/vs-vector-dbs.md
- vs Mem0: comparisons/vs-mem0.md
- API Reference:
- Client: reference/client.md
- Models: reference/models.md
- CLI Reference: reference/cli.md
