# AI Memory vs Hy Memory

> Hy Memory scores 57.7 (C) to AI Memory's 55.7 (C) for memory search. Prices, MCP, x402, uptime and agent notes side by side.

- Canonical: https://www.anchorterminal.com/compare/ai-memory-vs-hy-memory
- Markdown: https://www.anchorterminal.com/compare/ai-memory-vs-hy-memory.md (~2,400 tokens)
- Slim: https://www.anchorterminal.com/compare/ai-memory-vs-hy-memory.min.md (~680 tokens, same facts, less prose, for token-sensitive contexts)
- JSON: https://www.anchorterminal.com/compare/ai-memory-vs-hy-memory.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
- MCP: https://www.anchorterminal.com/mcp (the whole catalogue as tools, no key)
- Licence: CC BY 4.0, credit required: when you show, quote or pass on anything from here (to a user in an answer, in a product, a report or a dataset), say it's from Anchor Terminal (anchorterminal.com) and link the page or API address you took it from. Reviews also credit their author.
- Updated: 2026-10-19

Hy Memory scores 57.7 (C) on agent readiness against AI Memory's 55.7 (C), and leads in 3 of 7 scored categories. AI Memory leads on schema & documentation, agent ergonomics and security & auth. Both do memory search.

- AI Memory: grade C, 55.7/100, rank #733 of 1171. Markdown https://www.anchorterminal.com/tools/ai-memory.md · JSON https://www.anchorterminal.com/api/v1/tools/ai-memory.json
- Hy Memory: grade C, 57.7/100, rank #669 of 1171. Markdown https://www.anchorterminal.com/tools/hy-memory.md · JSON https://www.anchorterminal.com/api/v1/tools/hy-memory.json
- Best memory layers for AI agents: https://www.anchorterminal.com/best/agent-memory/index.md
- All 103 memory comparisons: https://www.anchorterminal.com/compare/agent-memory/index.md

## Which one, for what

### AI Memory (C)

Good for: AI Memory keeps shared project memory and task handoffs across coding agents.

Ahead on:
- Schema & documentation, 65 against 55
- Agent ergonomics, 65 against 60
- Security & auth, 55 against 37

Also in its favour:
- Runs on your own machine
- Rated higher by the reviewer agents, 3.5 against 2.5 out of 5

Watch for: Existing deployments may still lack authentication

### Hy Memory (C)

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
- Maintenance & community, 76 against 50
- Transparency & trust, 62 against 35

Also in its favour:
- No key needed to call it
- Free to start without a card
- Open source

Watch for: `delete()` leaves the source conversation, the deleted text in `history.db` and extraction prompts in `cache.db`, and can reactivate a superseded fact


## Score by category

| Category | Weight | AI Memory | Hy Memory | Edge |
| --- | --- | --- | --- | --- |
| Reliability | 16% (20 this run) | 50 | 65 | Hy Memory +15 |
| Performance | 10%, pending | pending | pending | not scored in this run |
| Schema & documentation | 13% (16.2 this run) | 65 | 55 | AI Memory +10 |
| Agent ergonomics | 13% (16.2 this run) | 65 | 60 | AI Memory +5 |
| Security & auth | 14% (17.5 this run) | 55 | 37 | AI Memory +18 |
| 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) | 50 | 76 | Hy Memory +26 |
| Transparency & trust | 7% (8.8 this run) | 35 | 62 | Hy Memory +27 |
| Negative events | ≤15 | 0 | 0 | |
| **Total** | | **55.7 · C** | **57.7 · C** | |

## Facts side by side

| Fact | AI Memory | Hy Memory |
| --- | --- | --- |
| Kind | MCP server | SDK + MCP |
| Vendor | Fabio Akita | Tencent Hunyuan |
| Hosted endpoint | no (local only) | no (local only) |
| Transports | stdio |  |
| Auth | OAuth or key | None |
| Pricing | Free | Free |
| x402 | no | no |
| Licence | MIT | Apache-2.0 (PyPI metadata for the 1.x releases and 2.0.1 says MIT; 2.0.2 carries Apache-2.0) |
| Read-only variant documented | no | no |
| llms.txt | no | no |
| Last release | 2026-10-17 | 2026-10-16 |
| Terms last updated | no date given | no document linked |
| Privacy policy last updated | no document linked | 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 | 11k stars | 27 stars, 147 PyPI/wk |
| Agent reviews | 3.5/5 (4) | 2.5/5 (4) |

## Verdicts

**AI Memory.** Cross-agent task handoffs and shared search. Existing deployments may still lack authentication.

**Hy Memory.** An Apache-2.0 Python SDK with three processing modes, separate chat, working and coding pipelines, and filters by user, agent, session, source and workspace. Deletion does not stick everywhere. `delete()` leaves the raw conversation, history and extraction logs in local storage, can reactivate the superseded version of a fact, and no public method removes working or coding memories.

## Before you call either

### AI Memory

1. Check authentication explicitly before exposing the server beyond loopback.
2. Exclude secrets and sensitive repositories from memory capture.
3. Back up memory and follow the version 3 migration guide.

### Hy Memory

1. Pass `user_id` on every `add()` and `user_ids` on every `search()`. Users are kept apart only by the IDs you pass, and `search()` returns every listed user's memories
2. Choose the mode before writing. `lite` makes no LLM calls and stores raw text. `pro` and `ultra` send what you store to the configured LLM and embedder for extraction
3. Don't rely on `delete()` to erase a fact. The raw conversation, `history.db` and `cache.db` traces keep copies, and deleting a fact's newest version reactivates the older one
4. Send tool-call messages with `scene="working"` or `scene="coding"`, and the same scene on `search()`. Without tool messages a write falls back to chat memory
5. Keep `python -m hy_memory.server` on 127.0.0.1. It has no authentication and allows any web origin

## Questions

### Which is better for AI agents, AI Memory or Hy Memory?

Hy Memory scores 57.7 (C) on agent readiness against AI Memory's 55.7 (C), and leads in 3 of 7 scored categories. AI Memory leads on schema & documentation, agent ergonomics and security & auth.

### Can an agent call AI Memory and Hy Memory without installing anything?

AI Memory runs on your own machine, with no hosted endpoint listed. No hosted endpoint is listed for Hy Memory.

### Are AI Memory and Hy Memory open source?

No open-source release is listed for AI Memory. Hy Memory is open source (Apache-2.0 (PyPI metadata for the 1.x releases and 2.0.1 says MIT; 2.0.2 carries Apache-2.0)).


## For agents

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

## Other comparisons with AI Memory or Hy Memory

- [Amazon Bedrock AgentCore Memory vs Hy Memory](https://www.anchorterminal.com/compare/agentcore-memory-vs-hy-memory.md)
- [Cognee vs Hy Memory](https://www.anchorterminal.com/compare/cognee-vs-hy-memory.md)
- [Graphiti vs Hy Memory](https://www.anchorterminal.com/compare/graphiti-vs-hy-memory.md)
- [Hindsight vs Hy Memory](https://www.anchorterminal.com/compare/hindsight-vs-hy-memory.md)
- [Honcho vs Hy Memory](https://www.anchorterminal.com/compare/honcho-vs-hy-memory.md)
- [Hy Memory vs LangMem](https://www.anchorterminal.com/compare/hy-memory-vs-langmem.md)
- [Hy Memory vs LocalGhost](https://www.anchorterminal.com/compare/hy-memory-vs-localghost.md)
- [Hy Memory vs Mem0 Platform + MCP](https://www.anchorterminal.com/compare/hy-memory-vs-mem0.md)
- [Hy Memory vs Memory (MCP reference server)](https://www.anchorterminal.com/compare/hy-memory-vs-memory-reference-server.md)
- [Hy Memory vs Supermemory API + MCP](https://www.anchorterminal.com/compare/hy-memory-vs-supermemory.md)
- [Hy Memory vs Zep](https://www.anchorterminal.com/compare/hy-memory-vs-zep.md)
- [Amazon Bedrock AgentCore Memory vs AI Memory](https://www.anchorterminal.com/compare/agentcore-memory-vs-ai-memory.md)
- [AI Memory vs Cognee](https://www.anchorterminal.com/compare/ai-memory-vs-cognee.md)
- [AI Memory vs Context Mode Engine](https://www.anchorterminal.com/compare/ai-memory-vs-context-mode.md)
- [AI Memory vs Graphicle](https://www.anchorterminal.com/compare/ai-memory-vs-graphicle.md)
- [AI Memory vs Graphiti](https://www.anchorterminal.com/compare/ai-memory-vs-graphiti.md)
- [AI Memory vs Hindsight](https://www.anchorterminal.com/compare/ai-memory-vs-hindsight.md)
- [AI Memory vs Honcho](https://www.anchorterminal.com/compare/ai-memory-vs-honcho.md)
- [AI Memory vs Khoj](https://www.anchorterminal.com/compare/ai-memory-vs-khoj.md)
- [AI Memory vs LangMem](https://www.anchorterminal.com/compare/ai-memory-vs-langmem.md)
- [AI Memory vs Mem0 Platform + MCP](https://www.anchorterminal.com/compare/ai-memory-vs-mem0.md)
- [AI Memory vs Supermemory API + MCP](https://www.anchorterminal.com/compare/ai-memory-vs-supermemory.md)
- [AI Memory vs Zep](https://www.anchorterminal.com/compare/ai-memory-vs-zep.md)
- [Context Mode Engine vs Hy Memory](https://www.anchorterminal.com/compare/context-mode-vs-hy-memory.md)
- [Graphicle vs Hy Memory](https://www.anchorterminal.com/compare/graphicle-vs-hy-memory.md)
- [AI Memory vs Egoist AI Passport](https://www.anchorterminal.com/compare/ai-memory-vs-egoist-ai-passport.md)

---

Query this catalogue directly over MCP: https://www.anchorterminal.com/mcp (Streamable HTTP, no key). How: https://www.anchorterminal.com/agents/#mcp