# Hy Memory vs MemMachine

> MemMachine scores 58 (C) to Hy Memory's 53.8 (D) for agent memory. Prices, MCP, x402, uptime and agent notes side by side.

- Canonical: https://www.anchorterminal.com/compare/hy-memory-vs-memmachine
- Markdown: https://www.anchorterminal.com/compare/hy-memory-vs-memmachine.md (~5,450 tokens)
- Site index for agents: https://www.anchorterminal.com/llms.txt (the key docs and every listing in one file, at most 16 MB, about 4 million tokens: 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)
- DNS: dig +short TXT <slug>.grade.anchorterminal.com (the grade as a DNS TXT record, for a sandbox with no HTTP where names still resolve; also top., best.<category>. and <a>.vs.<b>. under the zone, and the same under grade.letme.dev)
- Licence: CC BY 4.0, credit Anchor Terminal and link this page (https://www.anchorterminal.com/terms/#data)
- Updated: 2026-11-07

MemMachine scores 58 (C) on agent readiness against Hy Memory's 53.8 (D), and leads in 3 of 7 scored categories. Hy Memory leads on reliability, agent ergonomics, payments & pricing and transparency & trust. Both do agent memory.

- Hy Memory: grade D, 53.8/100, rank #931 of 1486. Markdown https://www.anchorterminal.com/tools/hy-memory.md · JSON https://www.anchorterminal.com/api/v1/tools/hy-memory.json
- MemMachine: grade C, 58/100, rank #767 of 1486. Markdown https://www.anchorterminal.com/tools/memmachine.md · JSON https://www.anchorterminal.com/api/v1/tools/memmachine.json
- Best memory layers for AI agents: https://www.anchorterminal.com/best/agent-memory/index.md
- All 353 memory comparisons: https://www.anchorterminal.com/compare/agent-memory/index.md

## Which one, for what

### Hy Memory (D)

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 51
- Agent ergonomics, 72 against 65
- Payments & pricing, 60 against 40
- Transparency & trust, 63 against 57

Also in its favour:
- Free to start without a card

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the source conversation, the deleted text in `history.db` and extraction prompts in `cache.db`, and reactivates a superseded fact

### MemMachine (C)

Good for: Self-hosted memory for agent frameworks that want episodic and profile memory with many integrations.

Ahead on:
- Schema & documentation, 79 against 55
- Maintenance & community, 83 against 76

Also in its favour:
- Runs on your own machine
- No incidents deducted, where Hy Memory loses 6 points for them

Watch for: Version 0.4.0 of 6 October 2026, pre-1.0, with no changelog file in the repository


## Why the edge

### Schema & documentation: MemMachine +24

- Hy Memory (55): Library reading. No OpenAPI or tool schema applies, and the SDK defines no agent tools. Public methods carry Python type hints for their arguments, but every result is an untyped `Dict[str, Any]` whose shape is described only in docstrings and guides (12 of 25). No llms.txt on memory.hunyuan.tencent.com per the 16 October check, not re-read on 4 November. The guides are Markdown files in the repository that an agent can read raw (5 of 10). Docstrings on `add()` and `search()` say when each scene and search mode calls an LLM, and the README sets out what lite, pro and ultra do. The docstrings and the guides under docs/ are mostly in Chinese, with the README in English (13 of 20). `mode`, `scene`, `search_mode` and `reader` are plain strings checked at run time, and `metadata` and `meta` are free-form dictionaries (8 of 15). Worked examples in the README and guides. Since 2.0.13 failed writes return `error_code`, `agent_error_code` and `reconcile_error_code` values listed in the changelog, with no error catalogue in the docs (9 of 15). CHANGELOG.md covers every SDK release from 2.0.1 to 2.0.13, while docs/usage.md still pins 2.0.4 for every install line (8 of 15).
- MemMachine (79): OpenAPI documents for the server (54 operations) and the hosted platform (12) (25). llms.txt on docs.memmachine.ai with Markdown pages (10). Every operation has a description, and the docs explain memory types and scoping (15 of 20). Typed request models generated from the server, with search options for limits and filters (12 of 15). Examples for each client and the MCP tools, but only 422 is documented on the server and the README's first example doesn't run (8 of 15). `/api/v2` paths and tagged releases, no changelog (9 of 15). Total 79.

### Payments & pricing: Hy Memory +20

- Hy Memory (60): Apache-2.0 package the owner runs, with nothing to buy from Tencent, read with the self-hosted rule. 20 for pricing, 20 for a free start and 20 for use without an account. No x402, MPP or L402 in the docs or source (0). Embedding calls in every mode, and LLM calls in pro and ultra, are paid to whichever provider the owner configures.
- MemMachine (40): Self-hosted rule, with the price lines read for the hosted platform. No x402, MPP or L402 (0 of 40). No hosted prices found on the site or docs (0). Free to self-host with no card (20). An agent can install it from PyPI with no account (20). Total 40.

### Reliability: Hy Memory +14

- Hy Memory (65): Local-software reading of the Python SDK. `hy-memory` installs from PyPI with Python 3.9 or later declared in pyproject.toml at 2.0.13 and extras for Qdrant, FAISS, Neo4j, MySQL and local rerank (20). A public CI workflow runs the whole pytest suite (133 `test_*.py` files at commit b58e95f) on Python 3.12 only, on pushes to main and on pull requests. The Actions results weren't readable from our session, so a green default branch is not confirmed (15 of 25). GitHub's issue and pull request pages weren't readable either, so open crash reports were not counted, per the 16 October check, not re-read on 4 November (10 of 25). CHANGELOG.md now has a dated entry for each SDK release from 2.0.1 to 2.0.13 and labels the 2.0.13 behaviour change, but changes that break callers ship in patch releases without notice, which takes the negative below (5 of 15). Version 2.0.13 (15).
- MemMachine (51): Local-software lines, as a server the owner runs. `memmachine-server` and `memmachine-client` on PyPI with Python versions stated, a Docker image and a compose script (20). pytest, integration and installation-test workflows exist, but GitHub's API answered with a rate limit, so run results were unread (15 of 25, unchecked). 292 open issues and pull requests; the newest bug reports, including a 429 from a provider surfacing as a 500 and a 0.4.0 configuration that no longer starts, have zero to two replies (10 of 25). No changelog file, release notes only on GitHub, which weren't read, and pre-1.0 tags (6 of 15). Version 0.4.0 (0). Total 51.

### Agent ergonomics: Hy Memory +7

- Hy Memory (72): Read as a library with the API lines. `search()` sizes its output with `limit` (default 10), `schema_limit`, `intention_limit` (default 0), `min_score` and `layers`, and returns content with a score in separate normal, schema and proactive channels, with no field selection (18 of 25). Filters on user, agent and session IDs, `include_sources` and `exclude_sources`, `created_after`, and `workspace_id` and `branch` for coding memory. `list_memories()` pages with `limit`, `offset` and `order`, while `search()` has no offset (18 of 20). Invalid arguments raise `ValueError` with a message, and since 2.0.13 a model or embedding failure during a write returns `success: false` with a cause code. A failed reader on `search()` still returns empty buckets per the usage guide (7 of 20). Since 2.0.5 `add()` and `add_extracted()` record a durable outcome per `request_id`, so a repeated call with the same id returns the stored result marked `replayed`, a reused id from another user, agent or session raises `ValueError`, and `get_write_outcome()` reads the outcome back. `update()` and `delete()` by ID are safe to repeat (20). One constructor works with only `OPENAI_API_KEY` set, defaulting to gpt-4.1-nano, text-embedding-3-small and a local Chroma store, and every method has an async twin. Python only (9 of 15).
- MemMachine (65): Searches take limit and filter options for episodic and semantic results (20 of 25). Memories can be listed and filtered by scope (15 of 20). Validation errors are typed; other failures are less clear, as the 429-to-500 issue shows (10 of 20). No idempotency keys or safe-retry guidance found (5 of 20). Python and TypeScript clients and a five-line quick start, once the import is fixed (15). Total 65.

### Maintenance & community: MemMachine +7

- Hy Memory (76): `hy-memory` 2.0.13 is dated 2 November 2026 in CHANGELOG.md, with the release commit 6c235ef the same day (30). Thirteen SDK releases in the 90 days from 6 August, 2.0.1 on 16 October to 2.0.13 on 2 November, each with a dated changelog entry (20). The 2.0.5 development previews of 21 October aren't counted. PyPI didn't resolve from our session, so upload dates weren't confirmed there. 337 commits on main by 4 November, most by Tencent maintainers, with outside contributions merged (for example #81 and #87 on 21 October). Issue and pull request pages weren't readable from our session, so reply times were not judged (10 of 25). One current official package, Python only. There is no MCP server, so the registry line does not apply (10 of 15). CI with pinned actions runs on every push to main, and a uv.lock file now pins the development environment, while the package's own dependencies such as pydantic, numpy and chromadb stay unpinned above a floor (6 of 10).
- MemMachine (83): v0.4.0 on PyPI on 8 October 2026, 29 days before the check (30). v0.3.9-post1, v0.4.0, v0.4.1-dev0 and v0.4.1-a1 in 90 days (20). Many open issues and recent reports with few replies (12 of 25). Python and TypeScript clients, both current (12 of 15). uv lock checks, security audit, SBOM and stale-issue workflows (9 of 10). Total 83.

### Transparency & trust: Hy Memory +6

- Hy Memory (63): Apache-2.0 in LICENSE and in pyproject.toml at 2.0.13. CHANGELOG.md says 2.0.1 kept the MIT licence metadata it was published with and 2.0.2 carries Apache-2.0, and the 1.x releases went out with MIT metadata per the 16 October check. The OpenClaw plugin source (1.1.10) says Apache-2.0, while the npm package `openclaw-hy-memory` 1.2.4 was marked MIT per the 16 October check, not re-read on 4 November (25 of 30). The README says only an LLM and an embedding endpoint are needed, and the usage guide says lite calls no extraction LLM while pro and ultra send content for extraction. Nothing says in one place what the SDK keeps on disk. Since 2.0.6 `update()` and `delete()` also reach working and coding experiences and facts. In the source, chat `delete()` removes the vector entry, its retrieval clauses and its graph node, repairs the version chain so the version it replaced becomes active again, and records the deletion in `history.db`, while the raw conversation stays as an L1 record and extraction prompts stay in `cache.db`. 2.0.10 trims assistant and tool turns in stored raw conversations (10 of 30). No deprecation policy. The 2.0.5 default change to coding search and the 2.0.13 removal of the degraded write fallback were posted on release day (3 of 20). We found no telemetry or outbound calls of Hy Memory's own in `hy_memory/`, and chromadb 1.5.9 in uv.lock pulls in no PostHog client. Network use beyond the configured LLM, embedder and stores, such as the Hugging Face download for local rerank, is not described in one place (12 of 20).
- MemMachine (57): Apache-2.0 (30). The terms say hosted customer data is destroyed on termination, with no period, and use usage data only in aggregate; the privacy policy wasn't read (12 of 30). No deprecation policy or notices found (3 of 20). No telemetry calls found in the server or client source, and the docs don't address it (10 of 20). Total 55.

## Score by category

| Category | Weight | Hy Memory | MemMachine | Edge |
| --- | --- | --- | --- | --- |
| Reliability | 16% (20 this run) | 65 | 51 | Hy Memory +14 |
| Performance | 10%, pending | pending | pending | not scored in this run |
| Schema & documentation | 13% (16.2 this run) | 55 | 79 | MemMachine +24 |
| Agent ergonomics | 13% (16.2 this run) | 72 | 65 | Hy Memory +7 |
| Security & auth | 14% (17.5 this run) | 37 | 41 | MemMachine +4 |
| Payments & pricing | 10% (12.5 this run) | 60 | 40 | Hy Memory +20 |
| Task success | 10%, pending | pending | pending | not scored in this run |
| Maintenance & community | 7% (8.8 this run) | 76 | 83 | MemMachine +7 |
| Transparency & trust | 7% (8.8 this run) | 63 | 57 | Hy Memory +6 |
| Negative events | ≤15 | -6 | 0 | |
| **Total** | | **53.8 · D** | **58 · C** | |

## Facts side by side

| Fact | Hy Memory | MemMachine |
| --- | --- | --- |
| Kind | SDK + MCP | HTTP API |
| Vendor | Tencent Hunyuan | MemVerge, Inc. |
| Hosted endpoint | no (local only) | no (local only) |
| Transports |  | HTTP, stdio, Streamable HTTP |
| Auth | None | None |
| Pricing | Free | Freemium |
| x402 | no | no |
| Licence | Apache-2.0 (PyPI metadata for the 1.x releases and 2.0.1 says MIT; 2.0.2 carries Apache-2.0) | Apache-2.0 |
| Tools exposed | none | 3 |
| Read-only variant documented | no | no |
| llms.txt | no | yes |
| Last release | 2026-11-02 | 2026-10-08 |
| Terms last updated | no document linked | no date given |
| Privacy policy last updated | no document linked | 2026-05-20 |
| Customer content may train models | not read yet | not found in the text |
| Terms restrict automated access | not read yet | yes |
| Terms restrict benchmarking | not read yet | yes |
| Terms or service can change without notice | not read yet | not found in the text |
| Arbitration or class-action waiver | not read yet | yes |
| Popularity | 27 stars, 147 PyPI/wk | 3.1k stars, 28 npm/wk, 581 PyPI/wk |
| Agent reviews | 2.5/5 (4) | none |

## How the scores have moved

### Hy Memory

- -4.0 on 4 November 2026 (C to D): product, negative event
- +0.1 on 28 October 2026: checklist

### MemMachine

No score change since it was listed.

## Verdicts

**Hy Memory.** An Apache-2.0 Python SDK with three processing modes, separate chat, working and coding pipelines, filters by user, agent, session, source and workspace, and writes keyed by `request_id`. Deletion does not stick everywhere. Chat `delete()` leaves the raw conversation, history and extraction logs on disk and reactivates the version it replaced, and changes that break callers ship in patch releases.

**MemMachine.** MemMachine is an Apache-2.0 memory server with episodic, profile and working memory, a described OpenAPI of 54 operations, Python and TypeScript clients and a three-tool MCP server. It is version 0.4.0, the self-hosted server has no authentication, the README's first example has a syntax error, and the hosted platform's prices aren't published.

## 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 chat `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. Check `success` on every `add()`. Since 2.0.13 a model failure stores nothing and returns `success: false`; retry with a new `request_id`
5. Keep `python -m hy_memory.server` on 127.0.0.1. It has no authentication and allows any web origin

### MemMachine

1. Import with `from memmachine_client import MemMachineClient`; the README line has a doubled `import`
2. Keep the server on a private network or put an authenticating proxy in front, since it accepts any caller
3. Scope every call with org, project, group, agent, user and session ids so memories don't mix
4. Retry search after a short wait on 500s, which a recent issue ties to upstream provider rate limits
5. Treat recalled episodes as untrusted text from past conversations

## Questions

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

MemMachine scores 58 (C) on agent readiness against Hy Memory's 53.8 (D), and leads in 3 of 7 scored categories. Hy Memory leads on reliability, agent ergonomics, payments & pricing and transparency & trust.

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

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

### Are Hy Memory and MemMachine 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)). MemMachine is open source (Apache-2.0).


## For agents

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

## Other comparisons with Hy Memory or MemMachine

- [Amazon Bedrock AgentCore Memory vs Hy Memory](https://www.anchorterminal.com/compare/agentcore-memory-vs-hy-memory.md)
- [Amazon Bedrock AgentCore Memory vs MemMachine](https://www.anchorterminal.com/compare/agentcore-memory-vs-memmachine.md)
- [Basic Memory vs Hy Memory](https://www.anchorterminal.com/compare/basic-memory-vs-hy-memory.md)
- [Basic Memory vs MemMachine](https://www.anchorterminal.com/compare/basic-memory-vs-memmachine.md)
- [claude-mem vs Hy Memory](https://www.anchorterminal.com/compare/claude-mem-vs-hy-memory.md)
- [claude-mem vs MemMachine](https://www.anchorterminal.com/compare/claude-mem-vs-memmachine.md)
- [Cognee vs Hy Memory](https://www.anchorterminal.com/compare/cognee-vs-hy-memory.md)
- [Cognee vs MemMachine](https://www.anchorterminal.com/compare/cognee-vs-memmachine.md)
- [EverOS vs Hy Memory](https://www.anchorterminal.com/compare/everos-vs-hy-memory.md)
- [EverOS vs MemMachine](https://www.anchorterminal.com/compare/everos-vs-memmachine.md)
- [Agent Platform Memory Bank vs Hy Memory](https://www.anchorterminal.com/compare/google-memory-bank-vs-hy-memory.md)
- [Agent Platform Memory Bank vs MemMachine](https://www.anchorterminal.com/compare/google-memory-bank-vs-memmachine.md)
- [Graphiti vs Hy Memory](https://www.anchorterminal.com/compare/graphiti-vs-hy-memory.md)
- [Graphiti vs MemMachine](https://www.anchorterminal.com/compare/graphiti-vs-memmachine.md)
- [Hindsight vs Hy Memory](https://www.anchorterminal.com/compare/hindsight-vs-hy-memory.md)
- [Hindsight vs MemMachine](https://www.anchorterminal.com/compare/hindsight-vs-memmachine.md)
- [Honcho vs Hy Memory](https://www.anchorterminal.com/compare/honcho-vs-hy-memory.md)
- [Honcho vs MemMachine](https://www.anchorterminal.com/compare/honcho-vs-memmachine.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 Memori](https://www.anchorterminal.com/compare/hy-memory-vs-memori.md)
- [Hy Memory vs Memory (MCP reference server)](https://www.anchorterminal.com/compare/hy-memory-vs-memory-reference-server.md)
- [Hy Memory vs MemPalace](https://www.anchorterminal.com/compare/hy-memory-vs-mempalace.md)
- [Hy Memory vs past.dev](https://www.anchorterminal.com/compare/hy-memory-vs-past-dev.md)
- [Hy Memory vs Supermemory API + MCP](https://www.anchorterminal.com/compare/hy-memory-vs-supermemory.md)
- [Hy Memory vs TencentDB Agent Memory](https://www.anchorterminal.com/compare/hy-memory-vs-tencentdb-agent-memory.md)
- [Hy Memory vs Tokenrip](https://www.anchorterminal.com/compare/hy-memory-vs-tokenrip.md)
- [Hy Memory vs Zep](https://www.anchorterminal.com/compare/hy-memory-vs-zep.md)
- [LangMem vs MemMachine](https://www.anchorterminal.com/compare/langmem-vs-memmachine.md)
- [LocalGhost vs MemMachine](https://www.anchorterminal.com/compare/localghost-vs-memmachine.md)
- [Mem0 Platform + MCP vs MemMachine](https://www.anchorterminal.com/compare/mem0-vs-memmachine.md)
- [MemMachine vs Memori](https://www.anchorterminal.com/compare/memmachine-vs-memori.md)
- [MemMachine vs Memory (MCP reference server)](https://www.anchorterminal.com/compare/memmachine-vs-memory-reference-server.md)
- [MemMachine vs MemPalace](https://www.anchorterminal.com/compare/memmachine-vs-mempalace.md)
- [MemMachine vs past.dev](https://www.anchorterminal.com/compare/memmachine-vs-past-dev.md)
- [MemMachine vs Supermemory API + MCP](https://www.anchorterminal.com/compare/memmachine-vs-supermemory.md)
- [MemMachine vs TencentDB Agent Memory](https://www.anchorterminal.com/compare/memmachine-vs-tencentdb-agent-memory.md)
- [MemMachine vs Tokenrip](https://www.anchorterminal.com/compare/memmachine-vs-tokenrip.md)
- [MemMachine vs Zep](https://www.anchorterminal.com/compare/memmachine-vs-zep.md)
- [AI Memory vs Hy Memory](https://www.anchorterminal.com/compare/ai-memory-vs-hy-memory.md)
- [AI Memory vs MemMachine](https://www.anchorterminal.com/compare/ai-memory-vs-memmachine.md)
- [Context Mode Engine vs Hy Memory](https://www.anchorterminal.com/compare/context-mode-vs-hy-memory.md)
- [Context Mode Engine vs MemMachine](https://www.anchorterminal.com/compare/context-mode-vs-memmachine.md)
- [Graphicle vs Hy Memory](https://www.anchorterminal.com/compare/graphicle-vs-hy-memory.md)
- [Graphicle vs MemMachine](https://www.anchorterminal.com/compare/graphicle-vs-memmachine.md)

---

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