Compare
Mnemix vs Zep
The research-cited choice. Bi-temporal knowledge graph (Graphiti), BYOC. Voice is a community demo only.
Animation paused for reduced motion
Zep's bi-temporal graph is the strongest research-cited memory architecture for chat agents and Graphiti is genuinely impressive engineering. But voice is a community demo, not a first-class integration, and claimed/unverified memory benchmark figures include a 63.8% Mem0-paper measurement and a 71.2% self-reported score. Choose Mnemix if you're building voice.
Side-by-side
| Dimension | Zep | Mnemix |
|---|---|---|
| GitHub stars | claimed/unverified snapshot: 25,463 (graphiti) + 4,495 (zep) | n/a |
| Bi-temporal | ✅ (4 timestamps in graphiti_core/edges.py) | ✅ (session-scoped) |
| Voice integrations | 🟡 community demo only | ✅ Twilio, Vapi, Retell, Bland |
| Caller-ID enrichment | ❌ | ✅ Twilio Lookup + Trestle + Baylio |
| Edge runtime | ❌ Python on AWS | ✅ Cloudflare Workers |
| Claimed P95 retrieval | claimed/unverified: <200ms | designed for sub-300ms voice recall |
| LongMemEval (self) | claimed/unverified: 71.2% | Published once measured |
| LongMemEval (independent) | claimed/unverified: 63.8% (Mem0 paper) | Published once measured |
| Starter price | $25 to $125 (5x) | Hobby $0; Starter+ contact sales |
When you'd pick Zep
When you'd pick Zep: you're building a chat agent that needs deep graph queries over conversation history, you have AWS BYOC requirements, and your latency budget is generous enough for a non-voice-first stack.
When you'd pick Mnemix
When you'd pick Mnemix: voice is the channel. You need the same bi-temporal model Zep has, but at Cloudflare edge latency, with caller identity bundled in, and integration kits maintained for Vapi, Retell, Bland, and LiveKit on day one.
FAQ
- Zep's bi-temporal graph is research-grade. What does Mnemix have?
- Mnemix also stores four timestamps per fact (valid_from, valid_to, observed_at, ingested_at) — the same bi-temporal model. The difference is operational: Zep runs Python on AWS, Mnemix runs on Cloudflare Workers, and Mnemix bundles caller-ID resolution. For a chat-only agent with deep graph queries, Zep is excellent. For voice, the latency budget pushes you to the edge.
- Will Zep ship first-class voice eventually?
- They might — and if they do, the comparison shifts. Today, Zep's voice support is community examples and demos rather than maintained integration kits with Vapi/Retell/Bland. Mnemix shipped with voice as the only target.
- What about Zep's independent LOCOMO score?
- Claimed/unverified Zep memory benchmark figures include a 71.2% self-reported score and a 63.8% Mem0-paper measurement. We're not litigating which is correct — but it's why Mnemix will publish methodology + harness alongside its first public score, so independent replication is one command away.
- Can I run both Zep and Mnemix together?
- Yes. We've seen teams use Zep for chat history + graph queries and Mnemix for the voice channel + caller identity. The two share well at the application layer, and we can help you consolidate later.
Ship Mnemix in 5 minutes
Free Hobby tier — $0/month, no credit card.
Last updated: .