# Zep

> Context and memory engineering for AI agents.

Zep has a SharkScore of 68.1/100, ranked #39 of 671 in Frameworks & SDKs (updated 2026-11-19).

- Website: https://www.getzep.com (getzep.com)
- Kind: Tool · Pricing: Freemium · from $125/mo
- Maker: Zep
- Repository: https://github.com/getzep/graphiti
- Categories: Frameworks & SDKs
- Verified by the maker: no

## Why it scores 68.1

| Part | Score (0–100) | Weight |
|---|---|---|
| Adoption | 47 | 30% |
| User reviews | no data | 25% |
| Maintenance | 100 | 20% |
| Trust & transparency | 80 | 15% |
| Momentum | no data | 10% |

Evidence covers 87% of the score's weight. Compared with other listings in Frameworks & SDKs.

## Evidence

| Signal | Value |
|---|---|
| Traffic rank (Tranco) | #258.4K |
| GitHub stars | 32.9K |
| Stars, last 90 days | — |
| Downloads, 30 days | 301.8K |
| Reviews | none yet |
| Last update | 0 days ago |
| Uptime, 30 days | 100.0% |
| Public pricing / Free tier / API / MCP | yes / yes / yes / yes |

## RankShark review

Automated evaluation by RankShark · 2026-11-18 · method review-1.0 · https://rankshark.pro/how-we-review
We were not paid for this review.

As of 2026-11-18, Zep provides governed context graphs and agent skills for AI agents; paid self-serve plans start at $125/month, and its free plan includes 10,000 credits per month. [E1, E2]

Zep is a context service for agents that combines business data, documents, and conversations into temporal context graphs. The vendor says agents can retrieve this context through MCP or Zep SDKs. [E1, E3]

### Pros

- The free plan includes 10,000 credits per month and unlimited memories, retrieval, and users.
- The vendor lists Python, TypeScript, and Go SDKs.
- The vendor offers managed cloud, customer-key cloud, and VPC deployment options.

### Cons

- Free-plan rate limits vary with service-wide load, and the page says Episode processing has lower priority.
- The privacy policy provided is dated January 27, 2024, and does not state customer-data retention periods or data regions.
- Whether customer data is used for model training is not stated on the pages we checked.

### Pricing

| Plan | Price | Limits |
|---|---|---|
| Free | Free | 10,000 credits per month; no rollover or auto-top-up; 2 projects; 1 Context MCP Server seat; 5 custom entity & edge types; variable rate limits; lower priority Episode processing. |
| Flex | $125 / month billed monthly | 50,000 credits per month; then $25 / 10,000 credits; 600 requests per minute; 5 projects; 5 Context MCP Server seats; 10 custom entity & edge types; API logs kept for 1 day. |
| Flex Plus | $375 / month billed monthly | 200,000 credits per month; then $75 / 40,000 credits; 1,000 requests per minute; 10 projects; 15 Context MCP Server seats; 20 custom entity & edge types; API logs kept for 7 days. |
| Enterprise | Custom | Custom credits and negotiated rates; unlimited projects; custom rate limits with a guaranteed SLA; deployment options include Zep Cloud, cloud with customer keys, or VPC; API logs kept for 1 year. |

Checked 2026-11-18 · https://www.getzep.com/pricing/

### Sources

- https://www.getzep.com/ (fetched 2026-11-18)
- https://www.getzep.com/pricing/ (fetched 2026-11-18)
- https://help.getzep.com/overview (fetched 2026-11-18)
- https://www.getzep.com/legal/privacy/ (fetched 2026-11-18)
- https://www.getzep.com/legal/privacy/ (fetched 2026-11-18)
- https://trust.getzep.com/ (fetched 2026-11-18)

## Top alternatives

1. [Model Context Protocol](https://rankshark.pro/tools/model-context-protocol) — SharkScore 81.7. Open protocol and SDKs that connect AI apps to tools and data.
2. [AI SDK](https://rankshark.pro/tools/ai-sdk) — SharkScore 77.7. TypeScript toolkit for building AI apps and agents.
3. [LangChain](https://rankshark.pro/tools/langchain) — SharkScore 77.7. Build agents and LLM apps in Python and TypeScript.
4. [LangSmith](https://rankshark.pro/tools/langsmith) — SharkScore 76.9. Tracing, evaluation and monitoring for LLM apps.
5. [Transformers](https://rankshark.pro/tools/transformers) — SharkScore 76.9. Hugging Face's library of pretrained models for text, vision and audio.

---
Source: https://rankshark.pro/tools/zep · Method v2026-11-18.2: https://rankshark.pro/how-ranking-works · Payment never changes a rank.
