Skip to main content
Khora is durable memory for AI agents that need to remember across sessions. It stores what your agent learns (documents, entities, relationships, events, and facts) and retrieves it through hybrid search (vector, knowledge graph, keyword) with cross-encoder reranking and temporal scoring. A scheduled dream phase reorganizes the store offline (dedupes entities, prunes weak edges, recomputes centroids) so retrieval quality holds up as the corpus grows. Khora is a library, not a service. You bring your own database: PostgreSQL with pgvector and Neo4j on the production path, or the embedded SQLite + LanceDB stack for demos and single-user CLIs. Khora handles ingestion, extraction, storage, and retrieval. Your code calls remember() and recall().

​
Highlights

network_intelligence

Hybrid Retrieval

Vector + knowledge graph + keyword, fused per query. Cross-encoder reranking and temporal-bias scoring are first-class.
settings_input_component

Adaptive query routing

Simple lookups go vector-only. Multi-hop questions trigger Cypher graph traversal and RRF fusion, routed automatically per query by the VectorCypher engine.
schedule

Temporal context

Bi-temporal by design. Entities and relationships carry valid_from / valid_until ranges. Queries can window by time, bias toward recency, or ask what was true on a given date.
apartment

Multi-tenant by namespace

Namespaces are the sole tenancy boundary, enforced at the storage layer.

​
Requirements

To use the library:
  • Python 3.13+
  • Docker Compose for running the databases locally
    • PostgreSQL with pgvector
    • Neo4j (required for the VectorCypher engine)
  • uv for dependency management
  • Rust 1.85+ for the optional Rust acceleration

​
Where to next

electric_bolt

Quickstart

Install Khora, run migrations, and complete your first remember / recall in a few minutes.
tune

Configuration

Every KHORA_* environment variable and the KhoraConfig surface.
settings_input_component

Retrieval engine

How VectorCypher fuses vector, graph, and keyword search with query routing and RRF.
extension

Integrations

Drop-in adapters for CrewAI, LangGraph, Google ADK, OpenAI Agents, and LlamaIndex.