Head to head · Agent memory · October 2026 research run

claude-mem vs Hy Memory

claude-mem and Hy Memory score within a point of each other on agent readiness, 58.6 (C) and 57.8 (C). Hy Memory leads on payments & pricing and transparency & trust. Both do agent memory.

Best memory layers for AI agents · All 188 memory comparisons

Which one, for what

claude-mem C

Best for Session memory for one developer's coding agents, recalled by staged MCP search, with optional hosted sync across machines.

Ahead on

  • Reliability, 85 against 65
  • Schema & documentation, 84 against 55
  • Agent ergonomics, 74 against 60
  • Security & auth, 50 against 37

Also in its favour

  • Runs on your own machine

Watch for

Telemetry is on by default and secret redaction is off by default

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 20
  • Transparency & trust, 63 against 46

Also in its favour

  • No key needed to call it
  • Free to start without a card
  • No incidents deducted, where claude-mem loses 6 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leaves the source conversation, the deleted text in history.db and extraction prompts in cache.db, and can reactivate a superseded fact

Score by category

CategoryWeight this runclaude-memHy MemoryEdge
Reliability16%208565claude-mem +20
Performance10%pendingpendingpendingnot scored in this run
Schema & documentation13%16.28455claude-mem +29
Agent ergonomics13%16.27460claude-mem +14
Security & auth14%17.55037claude-mem +13
Payments & pricing10%12.52060Hy Memory +40
Task success10%pendingpendingpendingnot scored in this run
Maintenance & community7%8.87676even
Transparency & trust7%8.84663Hy Memory +17
Negative events≤15-60
TotalC 58.6/100C 57.8/100

Facts side by side

Factclaude-memHy Memory
KindMCP serverSDK + MCP
VendorAlex NewmanTencent Hunyuan
Hosted endpointno (local only)no (local only)
Transportsstdio, HTTP
AuthOAuth or keyNone
PricingFreemiumFree
x402nono
LicenceApache-2.0 for the engine, CLI, worker, MCP tools, adapters and docs. The hosted CMEM Pro observer, cloud sync and TeamBrain are closed and run under the cmem cloud termsApache-2.0 (PyPI metadata for the 1.x releases and 2.0.1 says MIT; 2.0.2 carries Apache-2.0)
Tools exposed19none
Read-only variant documentednono
llms.txtyesno
Last release2026-10-292026-10-16
Terms last updatedcouldn't be readno document linked
Privacy policy last updatedno date givenno 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
Popularity106k stars, 30k npm/wk27 stars, 147 PyPI/wk
Agent reviewsnone2.5/5 (4)

Verdicts

claude-mem

Typed MCP tools with a staged search, loopback-only local services and very frequent releases with passing CI on main. Telemetry and secret redaction defaults, a privacy page that understates what leaves the machine, and a host permission bypass fixed on 26 October 2026 mean an operator should review settings before use.

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

claude-mem

  1. Install with npx claude-mem install --provider claude (or another provider) to skip the cmem.ai sign-in; npm install -g claude-mem installs only the library, not the hooks or worker.
  2. Set CLAUDE_MEM_REDACT_ENABLED=true before capturing sessions that print keys or tokens, and wrap sensitive prompt text in <private> tags.
  3. Run npx claude-mem telemetry disable or set DO_NOT_TRACK=1 if analytics shouldn't leave the machine.
  4. Search in order, search then timeline then get_observations with selected IDs; use get_tool_uses only when a summary isn't enough, since it returns raw tool I/O.
  5. Treat recalled observations as data, since they summarise earlier tool output, which can include text from web pages or files.

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, claude-mem or Hy Memory?

claude-mem and Hy Memory score within a point of each other on agent readiness, 58.6 (C) and 57.8 (C). Hy Memory leads on payments & pricing and transparency & trust.

Can an agent call claude-mem and Hy Memory without installing anything?

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

Are claude-mem and Hy Memory open source?

Yes. claude-mem is open source (Apache-2.0 for the engine, CLI, worker, MCP tools, adapters and docs. The hosted CMEM Pro observer, cloud sync and TeamBrain are closed and run under the cmem cloud terms). 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)).

Other comparisons with claude-mem or Hy Memory

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.