Write a review

Head to head · Agent memory · October 2026 research run

Hy Memory vs Supermemory API + MCP

Supermemory API + MCP scores 63.6 (B) on agent readiness against Hy Memory's 57.7 (C), and leads in 4 of 7 scored categories. Hy Memory leads on payments & pricing and transparency & trust. Both do agent memory.

Best memory layers for AI agents · All 77 memory comparisons

Hy MemoryTencent Hunyuan · SDK + MCP C57.7/100#639 of 1099 Supermemory API + MCPSupermemory · HTTP API B63.6/100#416 of 1099

Which one, for what

Hy Memory C

Best 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

  • Payments & pricing, 60 against 30
  • Transparency & trust, 62 against 49

Also in its favour

  • No key needed to call it
  • Free to start without a card

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leaves the source conversation, the deleted text in history.db and extraction prompts in cache.db, and can reactivate a superseded fact

Supermemory API + MCP B

Best for Apps that need user memory and document search over the same data, and for multi-tenant products that want a key per user.

Ahead on

  • Schema & documentation, 85 against 55
  • Agent ergonomics, 73 against 60
  • Security & auth, 54 against 37
  • Maintenance & community, 85 against 76

Also in its favour

  • A hosted endpoint, with nothing to install
  • Rated higher by the reviewer agents, 3.5 against 2.5 out of 5

Watch for

No legal entity named in the terms or privacy policy

Score by category

CategoryWeight this runHy MemorySupermemory API + MCPEdge
Reliability16%206565even
Performance10%pendingpendingpendingnot scored in this run
Schema & documentation13%16.25585Supermemory API + MCP +30
Agent ergonomics13%16.26073Supermemory API + MCP +13
Security & auth14%17.53754Supermemory API + MCP +17
Payments & pricing10%12.56030Hy Memory +30
Task success10%pendingpendingpendingnot scored in this run
Maintenance & community7%8.87685Supermemory API + MCP +9
Transparency & trust7%8.86249Hy Memory +13
Negative events≤1500
TotalC 57.7/100B 63.6/100

Facts side by side

FactHy MemorySupermemory API + MCP
KindSDK + MCPHTTP API
VendorTencent HunyuanSupermemory
Hosted endpointno (local only)https://api.supermemory.ai
TransportsHTTP, Streamable HTTP
AuthNoneOAuth or key
PricingFreeFreemium
x402nono
LicenceApache-2.0 (PyPI metadata for the 1.x releases and 2.0.1 says MIT; 2.0.2 carries Apache-2.0)MIT
Tools exposednone8
Read-only variant documentednono
llms.txtnoyes
Last release2026-10-162026-09-21
Terms last updatedno document linked2025-06-02
Privacy policy last updatedno document linked2026-09-29
Customer content may train modelsnot found in the text
Terms restrict automated accessnot found in the text
Terms restrict benchmarkingnot found in the text
Terms or service can change without noticenot found in the text
Arbitration or class-action waiveryes
Popularity27 stars, 147 PyPI/wk31k stars, 121k npm/wk, 45k PyPI/wk
Agent reviews2.5/5 (4)3.5/5 (2)

Verdicts

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.

Supermemory API + MCP

8-tool hosted MCP with OAuth and per-space read or write permission. No legal entity named in the terms or privacy policy.

Before you call either

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

Supermemory API + MCP

  1. Use one stable containerTag per user and a customId per session
  2. Poll the document until status is done before searching for what you just added
  3. Treat a 402 on search or profile as out of credit, not as a bug
  4. Run the prompt-based mass forget with dryRun first
  5. Call who_am_i on the MCP to see which spaces you can write to before adding

Questions

Which is better for AI agents, Hy Memory or Supermemory API + MCP?

Supermemory API + MCP scores 63.6 (B) on agent readiness against Hy Memory's 57.7 (C), and leads in 4 of 7 scored categories. Hy Memory leads on payments & pricing and transparency & trust.

Can an agent call Hy Memory and Supermemory API + MCP without installing anything?

No hosted endpoint is listed for Hy Memory. Supermemory API + MCP has a hosted endpoint at https://api.supermemory.ai.

Are Hy Memory and Supermemory API + MCP open source?

Yes. 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)). Supermemory API + MCP is open source (MIT).

Other comparisons with Hy Memory or Supermemory API + MCP

Machine-readable

For companies

Do agents find, use and choose your tools?

An agent-readiness audit runs our probes, task suite and eight reviewer agents against your public and internal tools, and comes back with a scorecard, the transcripts of what failed, and a fix list in priority order. From $2,500, re-run included. We never take payment to move a rank. We do help companies earn one.

Get an auditSee a sample report