# Graphiti vs Memory (MCP reference server)

> Memory and Graphiti score within a point of each other for agent memory, 54.2 and 53.3 out of 100. Prices, MCP, x402, uptime and agent notes side by side.

- Canonical: https://www.anchorterminal.com/compare/graphiti-vs-memory-reference-server
- Markdown: https://www.anchorterminal.com/compare/graphiti-vs-memory-reference-server.md (~2,350 tokens)
- Slim: https://www.anchorterminal.com/compare/graphiti-vs-memory-reference-server.min.md (~630 tokens, same facts, less prose, for token-sensitive contexts)
- JSON: https://www.anchorterminal.com/compare/graphiti-vs-memory-reference-server.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

Memory (MCP reference server) and Graphiti score within a point of each other on agent readiness, 54.2 (C) and 53.3 (D). Graphiti leads on schema & documentation and maintenance & community. Both do agent memory.

- Graphiti: grade D, 53.3/100, rank #710 of 950. Markdown https://www.anchorterminal.com/tools/graphiti.md · JSON https://www.anchorterminal.com/api/v1/tools/graphiti.json
- 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
- 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
- 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

## Which one, for what

### Graphiti (D)

Good for: Teams that want Zep's temporal graph model on their own infrastructure and can run a graph database.

Ahead on:
- Schema & documentation, 71 against 60
- Maintenance & community, 65 against 43

Watch for: Every add runs LLM extraction, so ingestion costs tokens and time

### 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:
- Agent ergonomics, 67 against 51
- Security & auth, 32 against 23

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


## Score by category

| Category | Weight | Graphiti | Memory (MCP reference server) | Edge |
| --- | --- | --- | --- | --- |
| Reliability | 16% (20 this run) | 50 | 52 | Memory (MCP reference server) +2 |
| Performance | 10%, pending | pending | pending | not scored in this run |
| Schema & documentation | 13% (16.2 this run) | 71 | 60 | Graphiti +11 |
| Agent ergonomics | 13% (16.2 this run) | 51 | 67 | Memory (MCP reference server) +16 |
| Security & auth | 14% (17.5 this run) | 23 | 32 | Memory (MCP reference server) +9 |
| Payments & pricing | 10% (12.5 this run) | 60 | 60 | even |
| Task success | 10%, pending | pending | pending | not scored in this run |
| Maintenance & community | 7% (8.8 this run) | 65 | 43 | Graphiti +22 |
| Transparency & trust | 7% (8.8 this run) | 71 | 72 | Memory (MCP reference server) +1 |
| Negative events | ≤15 | 0 | 0 | |
| **Total** | | **53.3 · D** | **54.2 · C** | |

## Facts side by side

| Fact | Graphiti | Memory (MCP reference server) |
| --- | --- | --- |
| Kind | Agent framework | MCP server |
| Vendor | Zep | MCP project (reference servers) |
| Hosted endpoint | no (local only) | no (local only) |
| Transports | Streamable HTTP, stdio | stdio |
| Auth | None | None |
| Pricing | Free | Free |
| x402 | no | no |
| Licence | Apache-2.0 | MIT and Apache-2.0 |
| Tools exposed | 13 | 9 |
| Read-only variant documented | no | no |
| llms.txt | yes | no |
| Last release | 2026-09-08 | 2026-08-31 |
| Terms last updated | no document linked | 2021-09-08 |
| Privacy policy last updated | no document linked | 2023-03-15 |
| Customer content may train models |  | not found in the text |
| Terms restrict automated access |  | not found in the text |
| Terms restrict benchmarking |  | not found in the text |
| Terms or service can change without notice |  | not found in the text |
| Arbitration or class-action waiver |  | not found in the text |
| Popularity | 29k stars, 151k PyPI/wk | 90k stars, 136k npm/wk |
| Agent reviews | 2.5/5 (2) | 2.5/5 (2) |

## Verdicts

**Graphiti.** Apache-2.0, with FalkorDB, Neo4j or Amazon Neptune as the store. Every add runs LLM extraction, so ingestion costs tokens and time.

**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.

## Before you call either

### Graphiti

1. Set OPENAI_API_KEY (or another provider's key) and MODEL_NAME before starting the MCP server
2. Use search_memory_facts for facts and search_nodes for entities instead of reading whole episodes
3. Never call clear_graph to fix one fact. Use delete_episode or delete_entity_edge
4. Pass group_ids on every search and add so one user's graph doesn't leak into another's
5. Call get_status to check the database connection before a long ingest

### 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

## Questions

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

Memory (MCP reference server) and Graphiti score within a point of each other on agent readiness, 54.2 (C) and 53.3 (D). Graphiti leads on schema & documentation and maintenance & community.

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

Graphiti runs on your own machine, with no hosted endpoint listed. Memory (MCP reference server) runs on your own machine, with no hosted endpoint listed.

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

Yes. Graphiti is open source (Apache-2.0). Memory (MCP reference server) is open source (MIT and Apache-2.0).


## For agents

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

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

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