Available worldwide
What is Zep?
A production-grade memory system for AI agents that uses temporal context graphs to store and retrieve conversations and business data, with automatic updates when facts change. Supports multi-tenant governance with flexible deployment options from managed cloud to customer-controlled infrastructure.
Zep pricing
Plans, per-tier features and add-ons, dated and linked to live pricing. Pricing changes often; always verify at source before you rely on it.
Free tier (10k credits/month). Flex from $104/month annually (50k credits). Flex Plus from $312/month annually (200k credits). Enterprise: custom pricing. Usage-based: $0.0025 per additional credit (Flex) or $0.001875 per credit (Flex Plus).
Free
FreeFor development and prototyping
- projects
- 2
- mcp_server_seats
- 1
- credits_per_month
- 10,000
- custom_entity_types
- 5
- 10,000 credits per month
- 2 projects
- 1 Memory MCP Server seat
- 5 custom entity & edge types
- Context Graph + temporal memory
- Variable rate limits based on service load
- Lower priority Episode processing
Flex
For growing teams and production deployments
- projects
- 600
- mcp_server_seats
- 5
- api_log_retention
- 1 day
- credits_per_month
- 50,000
- custom_entity_types
- 10
- credit_rollover_days
- 30
- 50,000 credits per month included
- Auto top-up at 20%
- 30-day credit rollover
- 600 projects
- 5 Memory MCP Server seats
- 10 custom entity & edge types
- Context Graph + temporal memory
- API logs (1 day retention)
- Unlimited memories, retrieval & users
- SOC 2 Type II
Flex Plus
For scaling production deployments
- projects
- 1,000
- mcp_server_seats
- 15
- api_log_retention
- 7 days
- credits_per_month
- 200,000
- custom_entity_types
- 20
- credit_rollover_days
- 60
- 200,000 credits per month included
- Auto top-up at 20%
- 60-day credit rollover
- 1,000 projects
- 15 Memory MCP Server seats
- 20 custom entity & edge types
- Custom extraction instructions
- Webhooks
- Analytics
- Context Graph + temporal memory
- API logs (7 days retention)
- Unlimited memories, retrieval & users
- SOC 2 Type II
- HIPAA BAA
- Unlimited rate limits
Enterprise
Contact salesCustom deployment and compliance for large-scale production
- Custom credits with negotiated rates
- Guaranteed rate limits with SLA
- Unlimited projects
- Custom Memory MCP Server seats
- Custom entity & edge types
- SOC 2 Type II and HIPAA BAA
- Audit and API logs (1-year retention)
- Slack/Teams support and dedicated account manager
- Cloud, BYOK, or BYOC deployment
- Data Processing Agreements (DPA) for EU customers
What Zep does
The capabilities that matter for agent memory, normalised so it lines up with every alternative. “-” means we haven't confirmed it, not that it's missing.
- Architecture model
- Managed cloud API
- Graph based entity relationship extraction
- ✓
- Automatic context window rolling summarization
- -
- Semantic vs episodic event chronological memory
- ✓
- Cross session and multi thread user persistence
- ✓
- Memory conflict resolution and fact updating
- ✓
- Multi tenant user and agent isolation
- ✓
- Native langchain and llamaindex memory classes
- -
- Time decay and recency weighted retrieval
- ✓
- Zero data retention and pii redaction layer
- -
- SOC2 type ii
- ✓
- Mit or apache permissive oss license
- ✓
- Pricing model
- Usage based per req
Platform & deployment
Independently observed- CLI
- Web
- Cloud / SaaS
- Hybrid
- Self-hosted
Integrations (9)
Independently observed- Claude
- Cursor
- OpenAI
- Azure OpenAI
- Google Gemini
- Anthropic
- Neo4j
- FalkorDB
- Amazon Neptune
Zep alternatives
Other agent memory we track, ranked by the same independent score.
- CogneeOpen-source AI memory platform that builds knowledge graphs to help agents retrieve relevant context across sessionslow · 37%
- Supermemorylow · 42%
- Memarylow · 27%
- Mastralow · 42%
- Mem0A persistent memory layer that enables AI agents to retain and learn from interactions across sessions and toolsmedium · 54%
- LangMemlow · 31%
Compare Zep
Side by side against other agent memory, attribute by attribute, with a source on every value.
The Vioscale score: one lens on the evidence
Not user reviews and not a paid placement: a confidence-weighted blend of the independent signals below (adoption, activity, security posture, and more), which you can sort and re-weight yourself. Vendors can correct their listing but can never move their rank, and stars are weighted low as a vanity metric. It is one way to read the evidence for Zep, not the verdict.
| Signal | Score | Weight | Contribution | Evidence |
|---|---|---|---|---|
| Pricing transparency | 100 | 0.08 | 8.4 | ✓ |
| Capabilities | 92 | 0.05 | 4.5 | ✓ |
| Security posture | 50 | 0.07 | 3.7 | ✓ |
| Price level | 25 | 0.05 | 1.3 | ✓ |
| Integrations | 29 | 0.04 | 1.2 | ✓ |
| Reliability | 0 | 0.07 | 0.0 | - |
Computed . Re-weight it by intent, or see the full method.
All data & sourcesshow ↓
Every value we hold, with its source, retrieval date, and confidence. This is the evidence behind the score: don't trust it, verify it.
Features
| Attribute | Value | Evidence |
|---|---|---|
| Capabilities | Soc2 type ii: Yes · Pricing model: usage_based_per_req · Architecture model: managed_cloud_api · Mit or apache permissive oss license: Yes · Multi tenant user and agent isolation: Yes · Time decay and recency weighted retrieval: Yes | mediumsource · 2026-08-25 · 60% |
Integrations
| Attribute | Value | Evidence |
|---|---|---|
| Count | 9 | mediumsource · 2026-08-25 · 60% |
Market
| Attribute | Value | Evidence |
|---|---|---|
| Availability | PrimaryMarkets: … · AvailabilityScope: global · AvailableCountries: … · NotAvailableCountries: … | highsource · 2026-08-25 · 75% |