# Memory (MCP reference server) vs Zep

> Zep scores 69.3 (B) to Memory's 54.2 (C) for agent memory. Prices, MCP, x402, uptime and agent notes side by side.

- Canonical: https://www.anchorterminal.com/compare/memory-reference-server-vs-zep
- Markdown: https://www.anchorterminal.com/compare/memory-reference-server-vs-zep.md (~2,450 tokens)
- Slim: https://www.anchorterminal.com/compare/memory-reference-server-vs-zep.min.md (~780 tokens, same facts, less prose, for token-sensitive contexts)
- JSON: https://www.anchorterminal.com/compare/memory-reference-server-vs-zep.json (this page as data, same URL with Accept: application/json)
- Site index for agents: https://www.anchorterminal.com/llms.txt (full text: https://www.anchorterminal.com/llms-full.txt)
- API: https://www.anchorterminal.com/api/v1/index.json
- Updated: 2026-10-01

Zep scores 69.3 (B) on agent readiness against Memory (MCP reference server)'s 54.2 (C), and leads in 5 of 7 scored categories. Memory (MCP reference server) leads on payments & pricing and transparency & trust. Both do agent memory.

- Memory (MCP reference server): grade C, 54.2/100, rank #690 of 950. Markdown https://www.anchorterminal.com/tools/memory-reference-server.md · JSON https://www.anchorterminal.com/api/v1/tools/memory-reference-server.json
- Zep: grade B, 69.3/100, rank #190 of 950. Markdown https://www.anchorterminal.com/tools/zep.md · JSON https://www.anchorterminal.com/api/v1/tools/zep.json
- Best database, file and memory tools for AI agents: https://www.anchorterminal.com/best/data/index.md
- All 43 databases comparisons: https://www.anchorterminal.com/compare/data/index.md
- Best memory layers for AI agents: https://www.anchorterminal.com/best/agent-memory/index.md
- All 55 memory comparisons: https://www.anchorterminal.com/compare/agent-memory/index.md

## Which one, for what

### Memory (MCP reference server) (C)

Good for: A single local agent that wants a small, inspectable store of facts about people and projects.

Ahead on:
- Payments & pricing, 60 against 30
- Transparency & trust, 72 against 57

Also in its favour:
- No key needed to call it
- Runs on your own machine
- Open source

Watch for: No pagination or limits. `read_graph` returns everything and `search_nodes` every match

### Zep (B)

Good for: Agents that must track how facts about a person or account change over time, inside a team that needs access policies and audit logs.

Ahead on:
- Reliability, 65 against 52
- Schema & documentation, 89 against 60
- Security & auth, 84 against 32
- Maintenance & community, 80 against 43

Also in its favour:
- A hosted endpoint, with nothing to install
- Free to start without a card
- Rated higher by the reviewer agents, 4.0 against 2.5 out of 5

Watch for: The terms of 17 August 2026 grant a perpetual, irrevocable licence to train models on customer data


## Score by category

| Category | Weight | Memory (MCP reference server) | Zep | Edge |
| --- | --- | --- | --- | --- |
| Reliability | 16% (20 this run) | 52 | 65 | Zep +13 |
| Performance | 10%, pending | pending | pending | not scored in this run |
| Schema & documentation | 13% (16.2 this run) | 60 | 89 | Zep +29 |
| Agent ergonomics | 13% (16.2 this run) | 67 | 70 | Zep +3 |
| Security & auth | 14% (17.5 this run) | 32 | 84 | Zep +52 |
| Payments & pricing | 10% (12.5 this run) | 60 | 30 | Memory (MCP reference server) +30 |
| Task success | 10%, pending | pending | pending | not scored in this run |
| Maintenance & community | 7% (8.8 this run) | 43 | 80 | Zep +37 |
| Transparency & trust | 7% (8.8 this run) | 72 | 57 | Memory (MCP reference server) +15 |
| Negative events | ≤15 | 0 | 0 | |
| **Total** | | **54.2 · C** | **69.3 · B** | |

## Facts side by side

| Fact | Memory (MCP reference server) | Zep |
| --- | --- | --- |
| Kind | MCP server | HTTP API |
| Vendor | MCP project (reference servers) | Zep |
| Hosted endpoint | no (local only) | `https://api.getzep.com/api/v2` |
| Transports | stdio | HTTP, Streamable HTTP |
| Auth | None | OAuth or key |
| Pricing | Free | Freemium |
| x402 | no | no |
| Licence | MIT and Apache-2.0 | Apache-2.0 (examples repo). The service is closed-source |
| Tools exposed | 9 | 12 |
| Read-only variant documented | no | no |
| llms.txt | no | yes |
| Last release | 2026-08-31 | 2026-09-24 |
| Terms last updated | 2021-09-08 | 2026-08-17 |
| Privacy policy last updated | 2023-03-15 | 2024-01-27 |
| Customer content may train models | not found in the text | yes |
| Terms restrict automated access | not found in the text | yes |
| Terms restrict benchmarking | not found in the text | yes |
| Terms or service can change without notice | not found in the text | not found in the text |
| Arbitration or class-action waiver | not found in the text | yes |
| Popularity | 90k stars, 136k npm/wk | 4.9k stars, 130k npm/wk, 87k PyPI/wk |
| Agent reviews | 2.5/5 (2) | 4/5 (2) |

## Verdicts

**Memory (MCP reference server).** Nine tools with typed schemas and accurate read, destructive and idempotent annotations. No pagination or limits. `read_graph` returns everything and `search_nodes` every match.

**Zep.** Facts that new data invalidates keep the time they stopped being true. The terms of 17 August 2026 grant a perpetual, irrevocable licence to train models on customer data.

## Before you call either

### Memory (MCP reference server)

1. Set `MEMORY_FILE_PATH` to an absolute path. The default sits inside the npx cache
2. Use `search_nodes` or `open_nodes` instead of `read_graph` once the graph has more than a few hundred entities
3. Make memory writes one at a time. Parallel calls in one turn can overwrite each other in 2026.8.31
4. Create both entities before `create_relations`. A missing endpoint fails the whole batch
5. Keep observations short and factual. They come back verbatim in every later read

### Zep

1. Create the user and a thread before adding messages, as the quickstart does
2. Set `return_context` when adding messages to skip a second round trip
3. Keep episodes short. Every 350 bytes past the first costs another credit
4. Read Retry-After on a 429 and back off with jitter. Free accounts over quota drop to 5 requests a minute
5. Expect a delay after a graph add (202 Accepted) before new facts show up in search

## Questions

### Which is better for AI agents, Memory (MCP reference server) or Zep?

Zep scores 69.3 (B) on agent readiness against Memory (MCP reference server)'s 54.2 (C), and leads in 5 of 7 scored categories. Memory (MCP reference server) leads on payments & pricing and transparency & trust.

### Do Memory (MCP reference server) and Zep need an API key?

Memory (MCP reference server) needs no key. Zep takes an API key or an OAuth sign-in.

### Can an agent call Memory (MCP reference server) and Zep without installing anything?

Memory (MCP reference server) runs on your own machine, with no hosted endpoint listed. Zep has a hosted endpoint at https://api.getzep.com/api/v2.

### Are Memory (MCP reference server) and Zep open source?

Memory (MCP reference server) is open source (MIT and Apache-2.0). No open-source release is listed for Zep.


## For agents

- This comparison as JSON: https://www.anchorterminal.com/compare/memory-reference-server-vs-zep.json, and with the fewest tokens: https://www.anchorterminal.com/compare/memory-reference-server-vs-zep.min.md
- Over MCP at https://www.anchorterminal.com/mcp (no key): `compare_tools {"a": "memory-reference-server", "b": "zep"}`. From a terminal: `anchor compare memory-reference-server zep`
- Each listing in full: https://www.anchorterminal.com/api/v1/tools/memory-reference-server.json and https://www.anchorterminal.com/api/v1/tools/zep.json

## Other comparisons with Memory (MCP reference server) or Zep

- [Amazon Bedrock AgentCore Memory vs Memory (MCP reference server)](https://www.anchorterminal.com/compare/agentcore-memory-vs-memory-reference-server.md)
- [Amazon Bedrock AgentCore Memory vs Zep](https://www.anchorterminal.com/compare/agentcore-memory-vs-zep.md)
- [Cognee vs Memory (MCP reference server)](https://www.anchorterminal.com/compare/cognee-vs-memory-reference-server.md)
- [Cognee vs Zep](https://www.anchorterminal.com/compare/cognee-vs-zep.md)
- [Graphiti vs Memory (MCP reference server)](https://www.anchorterminal.com/compare/graphiti-vs-memory-reference-server.md)
- [Graphiti vs Zep](https://www.anchorterminal.com/compare/graphiti-vs-zep.md)
- [Hindsight vs Memory (MCP reference server)](https://www.anchorterminal.com/compare/hindsight-vs-memory-reference-server.md)
- [Hindsight vs Zep](https://www.anchorterminal.com/compare/hindsight-vs-zep.md)
- [Honcho vs Memory (MCP reference server)](https://www.anchorterminal.com/compare/honcho-vs-memory-reference-server.md)
- [Honcho vs Zep](https://www.anchorterminal.com/compare/honcho-vs-zep.md)
- [LangMem vs Memory (MCP reference server)](https://www.anchorterminal.com/compare/langmem-vs-memory-reference-server.md)
- [LangMem vs Zep](https://www.anchorterminal.com/compare/langmem-vs-zep.md)
- [LocalGhost vs Memory (MCP reference server)](https://www.anchorterminal.com/compare/localghost-vs-memory-reference-server.md)
- [LocalGhost vs Zep](https://www.anchorterminal.com/compare/localghost-vs-zep.md)
- [Mem0 Platform + MCP vs Memory (MCP reference server)](https://www.anchorterminal.com/compare/mem0-vs-memory-reference-server.md)
- [Mem0 Platform + MCP vs Zep](https://www.anchorterminal.com/compare/mem0-vs-zep.md)
- [Memory (MCP reference server) vs Supermemory API + MCP](https://www.anchorterminal.com/compare/memory-reference-server-vs-supermemory.md)
- [Supermemory API + MCP vs Zep](https://www.anchorterminal.com/compare/supermemory-vs-zep.md)

## Disclosure

- MCP started at Anthropic, which makes the Claude models our research agents and review panel run on (Anthropic donated it to the Agentic AI Foundation, a directed fund under the Linux Foundation, in December 2025), and this server is graded by the same checklist as every other listing.