Novyx vs Zep
Both provide persistent memory for AI agents. Here's a detailed comparison to help you choose.
TL;DR
Novyx focuses on memory safety with rollback, Replay debugging, Cortex maintenance, cross-tenant threat intelligence, auto defense, and a 107-tool MCP server. Every Novyx customer makes every other customer safer. Zep is a cloud-only service providing conversation memory with classification, user management, and the Graphiti knowledge graph. Zep's Community Edition has been deprecated.
| Feature | Novyx | Zep |
|---|---|---|
| Persistent memory | ✓ | ✓ |
| Semantic search | ✓ | ✓ |
| Point-in-time rollback | ✓ (Magic Rollback) | — |
| Cryptographic audit trail | ✓ (SHA-256 + RSA) | — |
| Replay (time-travel debugging) | ✓ | — |
| Cortex (autonomous maintenance) | ✓ | — |
| Knowledge graph | ✓ | ✓ (Graphiti) |
| MCP server | 107 tools | — |
| Threat intelligence | ✓ (cross-tenant) | — |
| Auto defense | ✓ (self-tuning) | — |
| Attack correlation | ✓ | — |
| Conversation classification | — | ✓ |
| User/session management | Sessions + Spaces | Built-in |
| Circuit breaker | ✓ (free) | — |
| Python SDK | ✓ | ✓ |
| JS/TS SDK | ✓ | ✓ |
| Free tier | 5,000 memories | Limited free tier |
| Eval & CI/CD gate | ✓ | — |
| Self-hosted | Local SQLite mode | ✗ (CE deprecated) |
| Open source | — | ✗ (CE deprecated) |
The Rollback Differentiator
Zep is built around conversation memory — classifying sessions, extracting facts from dialogue, and managing user context. But it has no mechanism for undoing agent mistakes. When a Zep-powered agent extracts an incorrect fact from a conversation, that bad data persists in your memory store indefinitely.
Novyx's Magic Rollback changes this equation entirely. Every memory operation — store, update, delete — is recorded in a SHA-256 hash chain. When something goes wrong, you revert to any point in time with a single API call. The cryptographic audit trail proves the rollback was complete: no orphaned data, no partial reverts, no guessing.
This is especially critical for conversational agents. A single misclassified conversation can cascade into dozens of incorrect memory extractions. With Novyx, you roll back to before the bad conversation was processed. With Zep, you're hunting through individual facts trying to find and delete each one.
Architecture: Composable API vs Conversation Engine
Zep is designed around conversations. It expects chat-style message arrays, classifies them into categories, and extracts facts automatically. This works well if your agent fits that pattern, but becomes limiting when you need to store structured data, non-conversational observations, or memories from multiple sources.
Novyx is a composable memory API. You store whatever you want — conversations, observations, structured data, relationships — and query it with semantic search. It plugs into LangChain, CrewAI, LlamaIndex, and any custom code. Zep's integrations are more tightly coupled to its conversation-first model.
The practical difference: Novyx adapts to your architecture, while Zep asks you to adapt to its conversation model.
Knowledge Graphs: Built-in vs External
Both platforms offer knowledge graph capabilities. Zep uses Graphiti, a temporal knowledge graph focused on episode-based relationships from conversations. Novyx has a built-in knowledge graph with triple storage (subject-predicate-object) that works with any data source, not just conversations.
Novyx also combines its knowledge graph with rollback — you can revert graph relationships alongside memory state, keeping your entire data layer consistent. Graphiti operates independently from Zep's memory, so rolling back graph changes requires separate manual intervention.
When to Choose Novyx
- ✓You need rollback and time-travel debugging for memory
- ✓You want autonomous memory maintenance with Cortex
- ✓You use Cursor or Claude Code and want MCP integration
- ✓You need a cryptographic audit trail for compliance
- ✓You want drop-in integrations for LangChain, CrewAI, and LlamaIndex
When to Choose Zep
- ✓You need conversation classification and structured user management
- ✓You want a managed cloud service with no infrastructure to maintain
- ✓You need Graphiti for temporal knowledge graphs
Code Comparison
from novyx import Novyx
nx = Novyx(api_key="YOUR_API_KEY")
# Store
nx.remember("User prefers dark mode", tags=["prefs"])
# Search
results = nx.recall("user preferences")
# Rollback (Novyx-only)
nx.rollback(target="2026-01-15T10:00:00Z")
# Audit trail (Novyx-only)
audit = nx.audit(limit=10)Start Building with Persistent Memory
5,000 memories free. No credit card required.