# Cognee vs Memory (MCP reference server)

> Cognee and Memory score within a point of each other for agent memory, 54.6 and 54.2 out of 100. Prices, MCP, x402, uptime and agent notes side by side.

- Canonical: https://www.anchorterminal.com/compare/cognee-vs-memory-reference-server
- Markdown: https://www.anchorterminal.com/compare/cognee-vs-memory-reference-server.md (~2,500 tokens)
- Slim: https://www.anchorterminal.com/compare/cognee-vs-memory-reference-server.min.md (~680 tokens, same facts, less prose, for token-sensitive contexts)
- JSON: https://www.anchorterminal.com/compare/cognee-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

Cognee and Memory (MCP reference server) score within a point of each other on agent readiness, 54.6 (C) and 54.2 (C). Memory (MCP reference server) leads on agent ergonomics, payments & pricing and transparency & trust. Both do agent memory.

- Cognee: grade C, 54.6/100, rank #681 of 950. Markdown https://www.anchorterminal.com/tools/cognee.md · JSON https://www.anchorterminal.com/api/v1/tools/cognee.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

### Cognee (C)

Good for: Agents whose memory has to include documents, wikis and chat tools as well as conversation, and for teams happy to self-host.

Ahead on:
- Schema & documentation, 85 against 60
- Security & auth, 39 against 32
- Maintenance & community, 82 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, 3.0 against 2.5 out of 5

Watch for: No status page, rate limits, SLA or SOC 2 for Cloud, and Cloud runs in AWS us-east-1 with no EU region

### 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 59
- Payments & pricing, 60 against 35
- Transparency & trust, 72 against 66

Also in its favour:
- No key needed to call it
- No incidents deducted, where Cognee loses 3 points for them

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


## Score by category

| Category | Weight | Cognee | 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) | 85 | 60 | Cognee +25 |
| Agent ergonomics | 13% (16.2 this run) | 59 | 67 | Memory (MCP reference server) +8 |
| Security & auth | 14% (17.5 this run) | 39 | 32 | Cognee +7 |
| Payments & pricing | 10% (12.5 this run) | 35 | 60 | Memory (MCP reference server) +25 |
| Task success | 10%, pending | pending | pending | not scored in this run |
| Maintenance & community | 7% (8.8 this run) | 82 | 43 | Cognee +39 |
| Transparency & trust | 7% (8.8 this run) | 66 | 72 | Memory (MCP reference server) +6 |
| Negative events | ≤15 | -3 | 0 | |
| **Total** | | **54.6 · C** | **54.2 · C** | |

## Facts side by side

| Fact | Cognee | Memory (MCP reference server) |
| --- | --- | --- |
| Kind | Model platform | MCP server |
| Vendor | Cognee | MCP project (reference servers) |
| Hosted endpoint | `https://<tenant>.aws.cognee.ai/api/v1` | no (local only) |
| Transports | HTTP, stdio, SSE (legacy) | stdio |
| Auth | OAuth or key | None |
| Pricing | Freemium | Free |
| x402 | no | no |
| Licence | Apache-2.0 | MIT and Apache-2.0 |
| Tools exposed | 7 | 9 |
| Read-only variant documented | no | no |
| llms.txt | yes | no |
| Last release | 2026-09-29 | 2026-08-31 |
| Terms last updated | 2026-03-27 | 2021-09-08 |
| Privacy policy last updated | no date given | 2023-03-15 |
| Customer content may train models | not found in the text | not found in the text |
| Terms restrict automated access | not found in the text | not found in the text |
| Terms restrict benchmarking | not found in the text | not found in the text |
| 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 | not found in the text |
| Popularity | 31k stars, 21k PyPI/wk | 90k stars, 136k npm/wk |
| Agent reviews | 3/5 (2) | 2.5/5 (2) |

## Verdicts

**Cognee.** Apache-2.0 library, REST server and MCP server, all self-hostable, with local models and no LLM key since 1.6.0. No status page, rate limits, SLA or SOC 2 for Cloud, and Cloud runs in AWS us-east-1 with no EU region.

**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

### Cognee

1. Use remember, recall and forget. The older cognify, search and delete MCP tools are gone
2. Always include /api/v1 in REST paths
3. Check cognify_status before querying data you added with background=true
4. Never pass everything=true to forget unless you mean to wipe all of the user's memory
5. Set a client timeout on Cloud calls and treat HTTP 402 as an empty balance, since an empty balance has also shown up as hangs

### 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, Cognee or Memory (MCP reference server)?

Cognee and Memory (MCP reference server) score within a point of each other on agent readiness, 54.6 (C) and 54.2 (C). Memory (MCP reference server) leads on agent ergonomics, payments & pricing and transparency & trust.

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

Cognee has a hosted endpoint at https://<tenant>.aws.cognee.ai/api/v1. Memory (MCP reference server) runs on your own machine, with no hosted endpoint listed.

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

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

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

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