Mem0 Migration | Zep Documentation

Zep is a memory layer for AI agents that unifies chat and business data into a dynamic temporal knowledge graph for each user. It tracks entities, relationships, and facts as they evolve, enabling you to build prompts with only the most relevant information—reducing hallucinations, improving recall, and lowering LLM costs.

Zep provides high-level APIs like memory.get and deep search with graph.search, supports custom entity/edge types, fact ratings, hybrid search, and granular graph updates. Mem0, by comparison, offers basic add/get/search APIs and an optional graph, but lacks built-in data unification, ontology customization, temporal fact management, fact ratings, and fine-grained graph control.

Got lots of data to migrate? Contact us for a discount and increased API limits.

Zep’s memory model in one minute

Unified customer record

Messages sent via memory.add go straight into the user’s knowledge graph; business objects (JSON, docs, e-mails, CRM rows) flow in through graph.add. Zep automatically deduplicates entities and keeps every fact’s valid and invalid dates so you always see the latest truth.

Domain-depth ontology

You can define Pydantic-style custom entity and edge classes so the graph speaks your business language (Accounts, Policies, Devices, etc.).

Temporal facts & ratings

Every edge stores when a fact was created, became valid, was invalidated, and (optionally) expired; fact_ratings let you auto-label facts (e.g., “high-confidence KYC data”) and filter on retrieval.

Hybrid & granular search

graph.search supports hybrid BM25 + semantic queries, graph search, with pluggable rerankers (RRF, MMR, cross-encoder) and can target nodes, edges, episodes, or everything at once.

How Zep differs from Mem0

Capability	Zep	Mem0
Business-data ingestion	Native via `graph.add` (JSON or text); business facts merge with user graph	No direct ingestion API; business data must be rewritten as “memories” or loaded into external graph store
Knowledge-graph storage	Built-in temporal graph; zero infra for developers	Optional “Graph Memory” layer that requires Neo4j/Memgraph and extra config
Custom ontology	First-class entity/edge type system	Not exposed; relies on generic nodes/relationships
Fact life-cycle (valid/invalid)	Automatic and queryable	Not documented / not supported
Fact ratings & filtering	Yes (`fact_ratings` API)	Not available
Search	Hybrid vector + graph search with multiple rerankers	Vector search with filters; basic Cypher queries if graph layer enabled
Graph CRUD	Full node/edge CRUD & bulk episode ingest	Add/Delete memories; no low-level edge ops
Memory context string	Auto-generated, temporal, prompt-ready	You assemble snippets manually from `search` output
LLM integration	Returns ready-made `memory.context`; easily integrates with agentic tools	Returns raw strings you must format

SDK support

Zep offers Python, TypeScript, and Go SDKs. See Installation Instructions for more details.

Migrating your code

Basic flows

What you do in Mem0	Do this in Zep
`client.add(messages, user_id=ID)` → stores conversation snippets	`zep.memory.add(session_id, messages=[...])` – keeps chat sequence and updates graph
`client.add("json...", user_id=ID)` (not really supported)	`zep.graph.add(user_id, data=<JSON>)` – drop raw business records right in
`client.search(query, user_id=ID)` – vector+filter search	Easy path: `zep.memory.get(session_id)` returns the `memory.context` + recent messages Deep path: `zep.graph.search(user_id, query, reranker="rrf")`
`client.get_all(user_id=ID)` – list memories	`zep.graph.search(user_id, '')` or iterate `graph.get_nodes/edges` for full dump
`client.update(memory_id, ...)` / `delete`	`zep.graph.edge.delete(uuid_="edge_uuid")` or `zep.graph.episode.delete(uuid_="episode_uuid")` for granular edits. Facts may not be updated directly; new data automatically invalidates old.

Practical tips

Session mapping: Map Mem0’s user_id → Zep user_id, and create session_id per conversation thread.
Business objects: Convert external records to JSON or text and feed them through graph.add; Zep will handle entity linking automatically.
Prompting: Replace your custom “summary builder” with the memory.context string; it already embeds temporal ranges and entity summaries.
Quality filters: Use Fact Ratings and apply min_fact_rating when calling memory.get to exclude low-confidence facts instead of manual post-processing.
Search tuning: Start with the default rrf reranker; switch to mmr, node_distance, cross_encoder, or episode_mentions when you need speed or precision tweaks.

Side-by-side SDK cheat-sheet

Operation	Mem0 Method (Python)	Zep Method (Python)	Notes
Add chat messages	`m.add(messages, user_id=...)`	`zep.memory.add(session_id, messages)`	Zep expects ordered AI + user msgs per turn
Add business record	n/a (work-around)	`zep.graph.add(user_id, data)`	Direct ingestion of JSON/text
Retrieve context	`m.search(query,... )`	`zep.memory.get(session_id)`	Zep auto-selects facts; no prompt assembly
Semantic / hybrid search	`m.search(query, ...)`	`zep.graph.search(..., reranker=...)`	Multiple rerankers, node/edge scopes
List memories	`m.get_all(user_id)`	`zep.graph.search(user_id, '')`	Empty query lists entire graph
Update fact	`m.update(id, ...)`	Not directly supported - add new data to supersede	Facts are temporal; new data invalidates old
Delete fact	`m.delete(id)`	`zep.graph.edge.delete(uuid_="edge_uuid")`	Episode deletion removes associated edges
Rate / filter facts	not supported	`min_fact_rating` param on `memory.get`	—

Where to dig deeper

Quickstart
Graph Search guide
Entity / Edge customization
Fact ratings
Graph CRUD: Reading from the Graph | Adding to the Graph | Deleting from the Graph

For any questions, ping the Zep Discord or contact your account manager. Happy migrating!