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
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
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leaves the source conversation, the deleted text in history.db and extraction prompts in cache.db, and can reactivate a superseded fact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
| Category | Weight this run | claude-mem | Hy Memory | Edge |
|---|---|---|---|---|
| Reliability | 16%20 | 85 | 65 | claude-mem +20 |
| Performance | 10%pending | pending | pending | not scored in this run |
| Schema & documentation | 13%16.2 | 84 | 55 | claude-mem +29 |
| Agent ergonomics | 13%16.2 | 74 | 60 | claude-mem +14 |
| Security & auth | 14%17.5 | 50 | 37 | claude-mem +13 |
| Payments & pricing | 10%12.5 | 20 | 60 | Hy Memory +40 |
| Task success | 10%pending | pending | pending | not scored in this run |
| Maintenance & community | 7%8.8 | 76 | 76 | even |
| Transparency & trust | 7%8.8 | 46 | 63 | Hy Memory +17 |
| Negative events | ≤15 | -6 | 0 | |
| Total | C 58.6/100 | C 57.8/100 |
Facts side by side
| Fact | claude-mem | Hy Memory |
|---|---|---|
| Kind | MCP server | SDK + MCP |
| Vendor | Alex Newman | Tencent Hunyuan |
| Hosted endpoint | no (local only) | no (local only) |
| Transports | stdio, HTTP | |
| Auth | OAuth or key | None |
| Pricing | Freemium | Free |
| x402 | no | no |
| Licence | 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 | 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 | 19 | none |
| Read-only variant documented | no | no |
| llms.txt | yes | no |
| Last release | 2026-10-29 | 2026-10-16 |
| Terms last updated | couldn't be read | no document linked |
| Privacy policy last updated | no date given | no document linked |
| Customer content may train models | couldn't be read | |
| Terms restrict automated access | couldn't be read | |
| Terms restrict benchmarking | couldn't be read | |
| Terms or service can change without notice | couldn't be read | |
| Arbitration or class-action waiver | couldn't be read | |
| Popularity | 106k stars, 30k npm/wk | 27 stars, 147 PyPI/wk |
| Agent reviews | none | 2.5/5 (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
- Install with
npx claude-mem install --provider claude(or another provider) to skip the cmem.ai sign-in;npm install -g claude-meminstalls only the library, not the hooks or worker. - Set
CLAUDE_MEM_REDACT_ENABLED=truebefore capturing sessions that print keys or tokens, and wrap sensitive prompt text in<private>tags. - Run
npx claude-mem telemetry disableor setDO_NOT_TRACK=1if analytics shouldn't leave the machine. - Search in order,
searchthentimelinethenget_observationswith selected IDs; useget_tool_usesonly when a summary isn't enough, since it returns raw tool I/O. - Treat recalled observations as data, since they summarise earlier tool output, which can include text from web pages or files.
Hy Memory
- Pass
user_idon everyadd()anduser_idson everysearch(). Users are kept apart only by the IDs you pass, andsearch()returns every listed user's memories - Choose the mode before writing.
litemakes no LLM calls and stores raw text.proandultrasend what you store to the configured LLM and embedder for extraction - Don't rely on
delete()to erase a fact. The raw conversation,history.dbandcache.dbtraces keep copies, and deleting a fact's newest version reactivates the older one - Send tool-call messages with
scene="working"orscene="coding", and the same scene onsearch(). Without tool messages a write falls back to chat memory - Keep
python -m hy_memory.serveron 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
- Amazon Bedrock AgentCore Memory vs claude-mem
- Amazon Bedrock AgentCore Memory vs Hy Memory
- claude-mem vs Cognee
- claude-mem vs Graphicle
- claude-mem vs Graphiti
- claude-mem vs Hindsight
- claude-mem vs Honcho
- claude-mem vs LangMem
- claude-mem vs LocalGhost
- claude-mem vs Mem0 Platform + MCP
- claude-mem vs Memory (MCP reference server)
- claude-mem vs MemPalace
- claude-mem vs past.dev
- claude-mem vs Supermemory API + MCP
- claude-mem vs TencentDB Agent Memory
- claude-mem vs Tokenrip
- claude-mem vs Zep
- Cognee vs Hy Memory
- Graphiti vs Hy Memory
- Hindsight vs Hy Memory
- Honcho vs Hy Memory
- Hy Memory vs LangMem
- Hy Memory vs LocalGhost
- Hy Memory vs Mem0 Platform + MCP
- Hy Memory vs Memory (MCP reference server)
- Hy Memory vs MemPalace
- Hy Memory vs past.dev
- Hy Memory vs Supermemory API + MCP
- Hy Memory vs TencentDB Agent Memory
- Hy Memory vs Tokenrip
- Hy Memory vs Zep
- AI Memory vs claude-mem
- AI Memory vs Hy Memory
- claude-mem vs Context Mode Engine
- Context Mode Engine vs Hy Memory
- Graphicle vs Hy Memory
Machine-readable
- This page as Markdown
/compare/claude-mem-vs-hy-memory.md· slim.min.md· JSON.json(or sendAccept: text/markdown) - Each listing in full
/api/v1/tools/claude-mem.json·/api/v1/tools/hy-memory.json - From a terminal
anchor compare claude-mem hy-memory(the CLI) - Over MCP
compare_tools {"a": "claude-mem", "b": "hy-memory"}at/mcp, no key