Mem0 vs Zep & Graphiti
Mem0 vs Zep & Graphiti: side-by-side comparison of two dedicated memory layers systems — architecture, taxonomy, license, pricing, MCP/A2A support, and direct edges.
Cost & capability
| Mem0 | Zep & Graphiti | |
|---|---|---|
| Capability band | competent | competent |
| Capability composite | 70 | 68 |
| Cost tier | free | free |
| $/Mtok input | 0 | 0 |
| $/Mtok output | 0 | 0 |
| Use cases | Long Running Session, Memory Augmented Chat, Multi Agent Coordination | Long Running Session, Memory Augmented Chat, Multi Agent Coordination, Analytical Summarization |
Where they differ (15)
Rows where both sides have data and the values disagree — the shortlist of dimensions that actually distinguish these two systems.
| Mem0 | Zep & Graphiti | |
|---|---|---|
| Capability composite | 70 | 68 |
| Use cases | Long Running Session, Memory Augmented Chat, Multi Agent Coordination | Long Running Session, Memory Augmented Chat, Multi Agent Coordination, Analytical Summarization |
| Type | Vector + graph + KV (hybrid) | Bi-temporal knowledge graph |
| Created | 2023-06 | 2024-08 |
| Latest release | openclaw-v1.0.11 2026-04-29 | v0.29.0 2026-04-27 |
| GitHub | 54.9k★ +1.6k/mo Python | 25.7k★ +137/mo Python |
| Funding | $24M total $150M val Series A · 2025-10 | $3M total Seed (additional) · 2024-04 |
| Backend storage | hybrid (vector + graph + KV) | Postgres + Neo4j (Graphiti) |
| Deployment | Both | Managed-only |
| API surface | REST, SDK: Python, Node.js | REST, SDK: Python, JS/TS, Go |
| Multi-tenancy | Logical namespace per (user_id, agent_id, run_id); self-hosted/on-prem deployment available for tenant isolation | Logical namespace per user/session; AWS VPC self-hosted option for full data residency; HIPAA BAA on Enterprise plan |
| MCP | native (first-party) — official mem0-mcp server | native (first-party) — Graphiti MCP server |
| OpenTelemetry | via adapter — AgentOps integration | not documented publicly |
| Optimised for | developer experience + universal memory layer (model-agnostic, multi-store) | memory operation tracing + drift / poisoning detection |
| Anti-fit | no anti-fit explicitly stated | not for use cases that don't run agent workloads in production |
At a glance
| Mem0 | Zep & Graphiti | |
|---|---|---|
| Section | Dedicated memory layers | Dedicated memory layers |
| Tier | T1 | T1 |
| Type | Vector + graph + KV (hybrid) | Bi-temporal knowledge graph |
| Created | 2023-06 | 2024-08 |
| Latest release | openclaw-v1.0.11 2026-04-29 | v0.29.0 2026-04-27 |
| License | Apache-2.0 | Apache-2.0 |
| GitHub | 54.9k★ +1.6k/mo Python | 25.7k★ +137/mo Python |
| Pricing | Free + paid | Free + paid |
| Funding | $24M total $150M val Series A · 2025-10 | $3M total Seed (additional) · 2024-04 |
| Backend storage | hybrid (vector + graph + KV) | Postgres + Neo4j (Graphiti) |
| Deployment | Both | Managed-only |
| API surface | REST, SDK: Python, Node.js | REST, SDK: Python, JS/TS, Go |
| Embedding | multiple supported | multiple supported |
| Multi-tenancy | Logical namespace per (user_id, agent_id, run_id); self-hosted/on-prem deployment available for tenant isolation | Logical namespace per user/session; AWS VPC self-hosted option for full data residency; HIPAA BAA on Enterprise plan |
| MCP | native (first-party) — official mem0-mcp server | native (first-party) — Graphiti MCP server |
| A2A | not documented publicly | not documented publicly |
| OpenTelemetry | via adapter — AgentOps integration | not documented publicly |
| Optimised for | developer experience + universal memory layer (model-agnostic, multi-store) | memory operation tracing + drift / poisoning detection |
| Anti-fit | no anti-fit explicitly stated | not for use cases that don't run agent workloads in production |
Taxonomy
| Axis | Mem0 | Zep & Graphiti |
|---|---|---|
| storage | vector | graph |
| retrieval | similarity | graph-traversal |
| persistence | long-term | long-term |
| update | extraction | append-only |
| unit | fact | episode |
| governance | opaque | auditable |
| conflict | llm-arbitrate | bi-temporal |
Pros & cons
Mem0
Pros: Hybrid (vector + graph + KV) gives the most architectural flexibility of any memory layer; AWS Agent SDK exclusivity and 51k★ make it the field's de-facto reference.
Cons: LOCOMO benchmark numbers were publicly disputed by Zep in counter-analysis; LLM-extraction approach risks dropping facts that don't fit the prompt.
Zep & Graphiti
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).