Zep and Graphiti

Graphiti (open source, Apache-2.0, 32,885 stars on 2026-11-17) is a Python framework for temporal context graphs. Zep is the commercial “unified context layer for enterprises” built on it — managed or in your own cloud (BYOC), with its own graph store (“Konig”), ingestion, governance and serving. Graphiti is self-hosted only and you bring your own graph database. Paper: arXiv 2501.13956.

Design

  • Facts are edges with validity windows; changed facts are invalidated, not deleted, so history is kept.
  • Every entity/fact traces back to source episodes (provenance).
  • Ontology via Pydantic models, learned, or both; incremental updates, no batch recompute.
  • Retrieval: embeddings + BM25 + graph traversal.
  • Backends: Neo4j 5.26, FalkorDB (incl. embedded Lite), Amazon Neptune + OpenSearch. See Neo4j.
  • Reference MCP and REST servers exist but have no auth or prompt-injection protection — not production.
  • Telemetry (PostHog) on by default; disable with GRAPHITI_TELEMETRY_ENABLED=false.

Repository snapshot (checked 2026-11-17)

ItemDetail
Repogetzep/graphiti, Python, Apache-2.0
Created2024-08-08
Activitylast push 2026-11-15; latest release v0.31.2 (2026-10-20, a certifi update)
Size32,885 stars, 3,383 forks
Packagegraphiti-core on PyPI, with extras falkordb, falkordblite (Python 3.12+), neptune, anthropic, groq, google-genai
Docshttps://help.getzep.com/graphiti

What a context graph holds

ComponentStores
Entities (nodes)People, products, policies and concepts, with summaries that evolve
Facts (edges)Entity, relationship, entity triplets with a validity window
EpisodesThe raw ingested data; every derived fact traces back to one
Custom typesDeveloper-defined entity and edge types as Pydantic models

Requirements and setup

  • Python 3.10 or higher.
  • A graph database: Neo4j 5.26, FalkorDB 1.1.2, or Amazon Neptune plus an Amazon OpenSearch Serverless collection for full-text search.
  • An LLM and an embedder. OpenAI is the default and needs OPENAI_API_KEY. Anthropic, Gemini and Groq are supported, and Azure OpenAI works through Azure’s v1 API. Any OpenAI-compatible endpoint (DeepSeek, Together, OpenRouter, Ollama, vLLM, llama.cpp, LM Studio) works through OpenAIGenericClient.
  • Structured output is required for extraction and deduplication. The README warns that small or local models often emit JSON that fails the schema, and offers a structured_output_mode of json_schema (default) or json_object.
  • Concurrency is capped by SEMAPHORE_LIMIT, default 10, to avoid provider 429 errors. Raise it for speed, lower it if rate-limited.
  • Docker Compose starts Neo4j, or FalkorDB with --profile falkordb.

Features worth knowing

  • identity_properties match entities by chosen fields (for example a Person by email) before node resolution; supported on Neo4j and FalkorDB.
  • Prompt builders can be overridden per instance, and an opt-in llm_runtime routes individual prompts to different models and providers. Response schemas stay fixed.
  • Reference servers: mcp_server (episode, entity and search tools over MCP) and server (FastAPI REST). The README says they are not production deployments. For production, use graphiti-core in your own service, which must supply authentication, tenant isolation and input controls, or use Zep.

Zep versus Graphiti (from the README)

AspectZepGraphiti
What it isEnterprise context layer, managed or in your cloud (BYOC)Open-source framework, self-hosted only
Graph databaseKonig, Zep’s own serviceBring your own: Neo4j, FalkorDB or Neptune
Users, threads, ingestionBuilt inBuild your own
RetrievalPre-configured; the README claims sub-200ms at scaleCustom; depends on your setup
ToolingDashboard, CLI, SDKs for Python, TypeScript and GoBuild your own

Graphiti versus GraphRAG (the vendor’s comparison)

The README contrasts Graphiti’s continuous incremental updates, explicit bi-temporal tracking with automatic fact invalidation, and hybrid retrieval with GraphRAG’s batch processing, community summaries and sequential LLM summarization. It rates Graphiti as typically sub-second and GraphRAG as seconds to tens of seconds. These are the authors’ claims, not measured here. See graphrag.

Benchmarks

Published scores for Graphiti and Zep differ by source, test harness and judge model, so no single figure is quoted here. The comparison across memory systems is in agent-memory-benchmarks.

Take

Its distinguishing feature is facts with validity windows, so it can answer “what was true when”. The cost is heavier operation: you run a graph database, an LLM and an embedder, and build the service around it. Compare mem0, graphrag, cognee; landscape in agent-memory-systems.