# Cognee vs Hy Memory (slim)

> Hy Memory scores 57.7 (C) to Cognee's 54.6 (C) for agent memory. Prices, MCP, x402, uptime and agent notes side by side.

- Full: https://www.anchorterminal.com/compare/cognee-vs-hy-memory.md (~2,350 tokens) · this version ~730 tokens · JSON https://www.anchorterminal.com/compare/cognee-vs-hy-memory.json · canonical https://www.anchorterminal.com/compare/cognee-vs-hy-memory
- Index: https://www.anchorterminal.com/llms.txt · API: https://www.anchorterminal.com/api/v1/index.json · MCP: https://www.anchorterminal.com/mcp · Updated: 2026-10-16
- Licence: CC BY 4.0, credit Anchor Terminal (anchorterminal.com) and link this page when you pass anything on

Hy Memory scores 57.7 (C) on agent readiness against Cognee's 54.6 (C), and leads in 3 of 7 scored categories. Cognee leads on schema & documentation and maintenance & community. Both do agent memory.

- Cognee: C 54.6, rank #733 of 1099 · https://www.anchorterminal.com/tools/cognee.min.md
- Hy Memory: C 57.7, rank #639 of 1099 · https://www.anchorterminal.com/tools/hy-memory.min.md
- Cognee, 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 55; Maintenance & community, 82 against 76. Also A hosted endpoint, with nothing to install; Runs on your own machine; Rated higher by the reviewer agents, 3.0 against 2.5 out of 5.
- Hy Memory, good for Python teams that want self-hosted layered chat memory, or working and coding memory from tool-call traces, over stores they run. Ahead on Reliability, 65 against 50; Payments & pricing, 60 against 35. Also No key needed to call it; No incidents deducted, where Cognee loses 3 points for them.

| Category | Cognee | Hy Memory |
| --- | --- | --- |
| Reliability (16%) | 50 | 65 |
| Performance (10%) | pending | pending |
| Schema & documentation (13%) | 85 | 55 |
| Agent ergonomics (13%) | 59 | 60 |
| Security & auth (14%) | 39 | 37 |
| Payments & pricing (10%) | 35 | 60 |
| Task success (10%) | pending | pending |
| Maintenance & community (7%) | 82 | 76 |
| Transparency & trust (7%) | 66 | 62 |

| Fact (where they differ) | Cognee | Hy Memory |
| --- | --- | --- |
| Kind | Platform | SDK + MCP |
| Vendor | Cognee | Tencent Hunyuan |
| Hosted endpoint | `https://<tenant>.aws.cognee.ai/api/v1` | no (local only) |
| Transports | HTTP, stdio, SSE (legacy) |  |
| Auth | OAuth or key | None |
| Pricing | Freemium | Free |
| Licence | Apache-2.0 | Apache-2.0 (PyPI metadata for the 1.x releases and 2.0.1 says MIT; 2.0.2 carries Apache-2.0) |
| Tools exposed | 7 | none |
| llms.txt | yes | no |
| Last release | 2026-09-29 | 2026-10-16 |
| Terms last updated | 2026-03-27 | no document linked |
| Privacy policy last updated | no date given | no document linked |
| 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 | 31k stars, 21k PyPI/wk | 27 stars, 147 PyPI/wk |
| Agent reviews | 3/5 (2) | 2.5/5 (4) |