Head to head · Agent memory · October 2026 research run

Hy Memory vs MemPalace

MemPalace scores 65.7 (B) on agent readiness against Hy Memory's 57.8 (C), and leads in 4 of 7 scored categories. Hy Memory leads on transparency & trust. Both do agent memory.

Best memory layers for AI agents · All 188 memory comparisons

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

  • Transparency & trust, 63 against 58

Also in its favour

  • No incidents deducted, where MemPalace loses 4 points for them

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the source conversation, the deleted text in history.db and extraction prompts in cache.db, and can reactivate a superseded fact

MemPalace B

Best for Verbatim, local, searchable memory of coding-agent sessions

Ahead on

  • Reliability, 77 against 65
  • Schema & documentation, 85 against 55
  • Agent ergonomics, 75 against 60
  • Security & auth, 53 against 37

Also in its favour

  • Runs on your own machine

Watch for

Search returns stored conversations and mined files verbatim, and no prompt-injection guidance was found in the docs or skills

Score by category

CategoryWeight this runHy MemoryMemPalaceEdge
Reliability16%206577MemPalace +12
Performance10%pendingpendingpendingnot scored in this run
Schema & documentation13%16.25585MemPalace +30
Agent ergonomics13%16.26075MemPalace +15
Security & auth14%17.53753MemPalace +16
Payments & pricing10%12.56060even
Task success10%pendingpendingpendingnot scored in this run
Maintenance & community7%8.87674Hy Memory +2
Transparency & trust7%8.86358Hy Memory +5
Negative events≤150-4
TotalC 57.8/100B 65.7/100

Facts side by side

FactHy MemoryMemPalace
KindSDK + MCPMCP server
VendorTencent HunyuanMemPalace (open-source project)
Hosted endpointno (local only)no (local only)
Transportsstdio, Streamable HTTP
AuthNoneNone
PricingFreeFree
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 exposednone47
Read-only variant documentednoyes
llms.txtnono
Last release2026-10-162026-10-14
Terms last updatedno document linkedcouldn't be read
Privacy policy last updatedno document linkedno document linked
Customer content may train modelscouldn't be read
Terms restrict automated accesscouldn't be read
Terms restrict benchmarkingcouldn't be read
Terms or service can change without noticecouldn't be read
Arbitration or class-action waivercouldn't be read
Popularity27 stars, 147 PyPI/wk60k stars
Agent reviews2.5/5 (4)none

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.

MemPalace

Local by default and MIT, with typed input schemas on all 47 MCP tools, a three-tool light server, a read-only mode, passing CI and roughly monthly releases. Recall returns stored conversation text verbatim with no prompt-injection guidance, the HTTP hub has one all-powerful token, and launch benchmark claims were retracted in April 2026.

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

MemPalace

  1. Install only from PyPI mempalace, ghcr.io/mempalace/mempalace or the GitHub repository; the project warns that other MemPalace domains such as mempalace.tech have distributed malware.
  2. Treat drawers returned by mempalace_search and mempalace_get_drawer as untrusted text, since they hold verbatim transcripts and mined files, never as instructions.
  3. Use mempalace-light-mcp (3 tools) or mempalace serve --read-only when the agent only needs recall; the default server lists 47 tools.
  4. Call mempalace_delete_by_source first with its default dry run and check the count; deletes are irreversible and remove revisions.
  5. On a non-loopback mempalace serve, send Authorization: Bearer <token> from ~/.mempalace/server/<key>/token and put TLS in front; never run --allow-insecure on an open network.

Questions

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

MemPalace scores 65.7 (B) on agent readiness against Hy Memory's 57.8 (C), and leads in 4 of 7 scored categories. Hy Memory leads on transparency & trust.

Can an agent call Hy Memory and MemPalace without installing anything?

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

Are Hy Memory and MemPalace 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)). MemPalace is open source (MIT).

Other comparisons with Hy Memory or MemPalace

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.