Zep & Graphiti

https://www.getzep.com/

Bi-temporal knowledge graph (event time + ingestion time). Strong on chronological reasoning and contradiction tracking. Graphiti is the open-source core.

Active · Verified 2026-10-22 · fresh as of 2026-10-22 · 82 cited facts, 6 with a third-party source · 1 recorded change · Suggest a correction

At a glance

Tier
T1
Created
2024-08 vendor fix
License
Apache-2.0 repo fix
Freshness
2026-10-22 fix
Layer
agent-infra repo fix
Licensing
open-core vendor fix
Deployment locus
hybrid repo fix
Platform vs product
platform vendor fix
Accelerator
yc-w24 third-party fix
SDK languages
go, python, typescript repo fix
Protocols
mcp-server vendor fix
Compliance
hipaa, soc2-type2 vendor fix

Memory taxonomy

storage
graph
retrieval
graph-traversal
persistence
long-term
update
append-only
unit
episode
governance
auditable
conflict
bi-temporal

When to use

Optimised for: memory operation tracing + drift / poisoning detection

Anti-fit: not for use cases that don't run agent workloads in production

Pros & cons

Pros

Bi-temporal graph captures event time + ingestion time, making contradiction tracking and chronological reasoning correct by construction.

Cons

KG storage is heavier than vector for the same data volume; smaller funding base than Mem0 ($2.3M vs $24M).

Claims & capabilities

Graphiti is its open-source graph engine. Published counter-analysis disputing Mem0's LOCOMO results. $2.3M raised Apr 2024.

Technical surface

API surface
REST, SDK: Python, JS/TS, Go
Backend storage
Postgres + Neo4j (Graphiti)
Deployment
Both — Zep Cloud managed; Graphiti OSS self-hosted (Neo4j/FalkorDB)
Embedding model
multiple supported
Multi-tenancy
Logical namespace per user/session; AWS VPC self-hosted option for full data residency; HIPAA BAA on Enterprise plan
MCP
native (first-party) — Graphiti MCP server
A2A
not documented publicly
OpenTelemetry
not documented publicly

Compare Zep & Graphiti with…

Similar systems

Other dedicated memory layers in the catalog, ranked by inbound references.

  • Mem0 T1

    Universal memory layer for AI agents. Three concurrent stores (vector + graph + KV); LLM-extracted facts; concurrent retrieval via ThreadPoolExecutor.

  • Cognee T1

    "Extract–Cognify–Load" pipeline that turns raw input into a typed, queryable knowledge graph for agent recall.

  • Hindsight (Vectorize) T1

    Standalone memory service from Vectorize. Open source. Biomimetic four-network design (World, Bank, Observation, Opinion). Ships an MCP memory server.

  • Letta / MemGPT T1

    Originated as MemGPT (UC Berkeley), where the model pages its own memory between context, recall and archival tiers. The product now centres on Letta Code, a stateful agent harness whose agents rewrite their own memory, skills and prompts over time.

  • Memori T2

    Structured, persistent memory layer for AI agents. Open source.

  • Memvid T2

    Single-file memory layer (one .mv2 file). No DB, no server. Append-only sequence of immutable Smart Frames with timestamps + checksums. Native Rust core (rewritten from Python).

Sources (81 cited facts, 6 third-party)

Each fact links to the page it came from; the badge says who published it (how to read sources).

What changed

Changes to this record's lifecycle, licence, release, pricing and hosting facts, from the catalog's git history. Subscribe (Atom)

  1. 2026-10-22
    • Latest release “v0.29.0 2026-04-27” → “v0.30.0 (2026-09-01) (graphiti-core; MCP server mcp-v1.1.0 same day)” source
    • Pricing “Free + paid” → “Free 10k credits/mo; Flex $125/mo ($104 annual) 50k credits; Flex Plus $375/mo ($312 annual) 200k credits; Enterprise custom” source
    • Deployment “Managed-only” → “Both — Zep Cloud managed; Graphiti OSS self-hosted (Neo4j/FalkorDB)” source
    #195

Related systems

References (20)

  • Amazon Neptune Analytics integrates with — Graphiti README lists Amazon Neptune Database or Neptune Analytics as a supported graph backend (graphiti-core[neptune]). (verified 2026-10-29)
  • Anthropic Claude (foundation models) integrates with — Graphiti README lists Anthropic as a supported LLM provider (graphiti-core[anthropic]). (verified 2026-10-29)
  • AutoGen / AG2 integrates with — Zep docs have an AG2 integration page (zep-ag2 package). (verified 2026-10-29)
  • AutoGen Memory integrates with — Zep docs have a Microsoft AutoGen integration page (zep-autogen package). (verified 2026-10-29)
  • CrewAI integrates with — Zep docs have a CrewAI integration page (zep-crewai package). (verified 2026-10-29)
  • FalkorDB integrates with — Graphiti README lists FalkorDB as a supported graph database backend (graphiti-core[falkordb]). (verified 2026-10-29)
  • Google Agent Development Kit (ADK) integrates with — Zep docs have a Google ADK integration page (zep-adk package). (verified 2026-10-29)
  • Google Gemini 3 family integrates with — Graphiti README lists Google Gemini as a supported LLM provider (graphiti-core[google-genai]). (verified 2026-10-29)
  • Kuzu integrates with — Graphiti README lists Kuzu as a graph backend, now marked deprecated but still shipped. (verified 2026-10-29)
  • LangGraph (orchestration) integrates with — Zep docs have a LangGraph integration page (zep-langgraph package). (verified 2026-10-29)
  • LiveKit Agents integrates with — Zep docs have a LiveKit Agents integration page (zep-livekit package). (verified 2026-10-29)
  • Mastra integrates with — Zep docs have a Mastra integration page (@getzep/zep-mastra package). (verified 2026-10-29)
  • Microsoft Agent Framework integrates with — Zep docs have a Microsoft Agent Framework integration page for adding Zep long-term memory. (verified 2026-10-29)
  • Neo4j integrates with · depends on at runtime — Graphiti README lists Neo4j as a supported graph database backend. (verified 2026-10-29)
  • OpenAI GPT family (GPT-5 / GPT-4o / o3 / o4) integrates with — Graphiti README names OpenAI as the default LLM provider. (verified 2026-10-29)
  • OpenSearch integrates with — Graphiti README says the Neptune backend uses an Amazon OpenSearch Serverless collection for full-text search. (verified 2026-10-29)
  • Pydantic-AI integrates with — Zep docs have a Pydantic AI integration page for adding Zep long-term memory. (verified 2026-10-29)
  • Strands Agents (AWS) integrates with — Zep docs have a Strands Agents integration page for adding Zep long-term memory. (verified 2026-10-29)
  • Vercel AI SDK integrates with — Zep docs have a Vercel AI SDK integration page (@getzep/zep-vercel-ai package). (verified 2026-10-29)
  • Voyage AI (MongoDB) integrates with — Graphiti README lists Voyage among supported embedder providers. (verified 2026-10-29)

Referenced by (13)

  • AutoGen Memory integrates with — Integrates with Mem0/Zep rather than building deep memory natively.
  • CrewAI Enterprise (now CrewAI AMP) depends on at runtime — adjacent-infrastructure cell: OSS CrewAI (already in catalog); typically paired with Mem0 / Zep for memory + Langfuse / LangSmith for observability
  • EverMemOS cites — S2 isInfluential citation
  • FalkorDB integrates with · depends on at runtime — MCP server via Graphiti integration
  • Flowise Memory integrates with — Flowise LangChain Memory nodes include Zep Memory. (verified 2026-10-29)
  • Graphiti MCP Server (Zep) builds on — Graphiti is the open-source core; MCP exposure of Graphiti's bi-temporal KG
  • LlamaIndex (framework) integrates with — LlamaIndex has an official vector store integration package llama-index-vector-stores-zep in its repo. (verified 2026-10-29)
  • MAGMA cites — S2 isInfluential citation
  • MemR³ cites — S2 isInfluential citation
  • n8n (AI agent flows) integrates with — n8n built-in AI cluster node: Zep Vector Store node. (verified 2026-10-29)
  • n8n AI Agent Memory integrates with — n8n built-in memory sub-node: Zep memory node. (verified 2026-10-29)
  • Phidata (now Agno) integrates with — Agno ships a zep toolkit (agno.tools.zep). (verified 2026-10-29)
  • RGMem cites — S2 isInfluential citation