StackMap
Subscribe

MemMachine vs Memoria

Long-term memory layer for AI agents — episodic (graph), profile (SQL) and working memory behind Python/TS SDKs, REST and MCP; ships LangChain, LangGraph, CrewAI and LlamaIndex integrations. — versus — Rust memory layer for AI agents with Git-style version control — snapshot, branch, merge and rollback over MatrixOne's copy-on-write engine, plus hybrid vector + full-text retrieval.

The curated verdict

Both are long-term memory layers for agents; memmachine splits episodic-graph/profile-SQL/working tiers, Memoria adds Git-style snapshot/branch/merge/rollback and contradiction quarantine on MatrixOne's copy-on-write engine.

MemMachineMemoria
Stars3.3k422
Forks19753
LanguagePythonRust
LicenseApache-2.0Apache-2.0
Last activity3 days ago27 days ago
Topicsmemorymemory
Curated connections94

MemMachine — the curator's take

Pick it when memory is a product requirement, not a cache: separating episodic (graph) from profile (SQL) from working memory maps to how assistants actually personalize, and the documented LangGraph/CrewAI/LlamaIndex integrations mean you don't write the glue. NOT worth the footprint for a single-user tool — it wants a server plus Neo4j and SQL; a vector store or a JSON file gets a prototype further. Watch the open-core boundary: the managed platform is the business model.

Memoria — the curator's take

Pick it when memory auditability and reversibility matter — you want to branch an agent's memory, roll back a bad write, or trace the provenance of every fact, and you're fine running MatrixOne underneath. Overkill if you just need a simple recall store (memmachine, memmolt) or fully-local files (memanto) — the versioning engine and DB dependency are the cost. Young project, Apache-2.0.