Skip to content

Latest commit

 

History

4,101 Commits

Folders and files

NameName
Last commit message
Last commit date
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 

Repository files navigation

Epistemic Graph

Epistemic Graph logo

A durable graph database and reasoning engine for connected, evidence-rich data.
Property graph · SQL · RDF/OWL · vectors · time · provenance · multimodal records

PyPI - Version Documentation GitHub license Version Build GitHub Repo stars GitHub forks GitHub contributors GitHub last commit (by committer) GitHub pull requests GitHub closed pull requests GitHub issues GitHub top language GitHub language count GitHub repo size GitHub repo file count (file type) PyPI - Downloads PyPI - License PyPI - Wheel PyPI - Implementation

Documentation · Capabilities · Interfaces · Status

Overview

Epistemic Graph is a Rust-native database and compute engine for teams building knowledge systems, evidence-led applications, analytics, and agent memory. It stores and queries connected graph records, relational data, RDF/OWL knowledge, vectors, time-series, events, documents, and media through one engine.

Claims can retain their evidence, provenance, confidence, and time of validity, so applications can inspect why information is present and how it changes. Use Epistemic Graph directly through its clients and query interfaces, or as the durable knowledge layer beneath Graph OS and Agent Utilities. Epistemic Graph is the database; agent execution and connector runtimes live in their respective ecosystem projects.

Key capabilities

Capability What it provides
One multi-model engine Property graph, relational tables, RDF, vectors, time-series, events, blobs, and media
Query across interfaces UQL, SQL, SPARQL, Cypher/Bolt, GraphQL, and typed native clients
Semantic constraints OWL reasoning, SHACL validation, and ShEx shape validation
Evidence-aware knowledge Claims, provenance, confidence, contradiction handling, and bitemporal validity
Durable operation Commit-before-ack persistence, audit, change data capture, tenant isolation, and observability
Distributed deployment Single-node operation and an optional cluster build with replication and coordinated placement

Check the capability matrix and generated method ledger for the current behavior of each operation.

Documentation

  • Start here for a guided engine tour.
  • Interfaces explains UQL, SQL, SPARQL, Cypher, GraphQL, vectors, time-series, and clients.
  • Architecture covers query execution, reasoning, storage, and distribution.
  • Deploy Epistemic Graph covers durable server, TLS, containers, and clusters.
  • Operations covers day-two procedures and recovery.

Architecture

People enter through Agent Web UI, Agent Terminal UI over REST, Geniusbot, or messaging services hosted by Graph OS. MCP, REST, and A2A clients also connect to Graph OS, which routes to Agent Utilities and Epistemic Graph. Source systems connect to Epistemic Graph through Agent Connector SDK.

Epistemic Graph architecture: authenticated interfaces feed a unified planner, which composes graph, semantic, analytical, temporal, and multimodal engines over one durable store.

People use the Agent Web UI, Agent Terminal UI (through the Graph OS REST API), Geniusbot, or the messaging services hosted by Graph OS. External applications and agents connect through Graph OS using MCP, REST, or A2A. Graph OS governs the runtime boundary, Agent Utilities coordinates agents and workflows, and Epistemic Graph stores and reasons over their durable knowledge. Source systems enter through Agent Connector SDK, which commits typed source data to the graph.

This repository owns Ecosystem projects own
Durable graph and multimodal state, query planning, semantic reasoning, transaction behavior, and engine authorization Graph OS owns MCP/REST/A2A entrypoints, runtime policy, messaging services, and frontend hosting
Generated engine contracts and capability truth Agent Utilities owns agents, workflows, skills, evaluation, and the agent control plane
Source-ingestion admission, schema validation, evidence, and provenance commits Agent Connector SDK owns connector execution and source-system adapters
Database and compute execution Agent Web UI, Agent Terminal UI, and Geniusbot provide user-facing clients

Quick start

Install the release wheel and open an in-process graph. This mode is explicit, ephemeral, and needs no server or TLS configuration.

python -m pip install epistemic-graph
python -m epistemic_graph.cli status  # no server is expected in embedded mode
python - <<'PY'
import msgpack
from epistemic_graph.engine import Engine

engine = Engine(persist_dir=":memory:")
engine.create_graph("demo")
engine.add_node(
    "demo",
    "node:hello",
    msgpack.packb({"kind": "Greeting"}, use_bin_type=True),
)
print(engine.has_node("demo", "node:hello"), engine.node_count("demo"))
PY

Expected output:

Status: NOT RUNNING (no PID file)
True 1

For durable storage, authenticated clients, containers, TLS, or clustering, continue with Deploy Epistemic Graph.

Contributing

Issues and pull requests are welcome. See CONTRIBUTING.md for development setup and review gates. Architecture and implementation guidance for coding agents lives in AGENTS.md.

License

Licensed under the MIT License.

About

A multi-modal agent memory, context, inferencing, analytics engine and database.

Resources

Contributing

Stars

11 stars

Watchers

1 watching

Forks

Releases

Packages

Contributors

Languages