MemMachine vs spector
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 — Java cognitive memory engine for agents: working, episodic, semantic and procedural tiers with decay, consolidation and association graphs, SIMD hybrid recall, served over MCP, REST/gRPC and SDKs.
Both split agent memory into cognitive tiers (episodic, profile/semantic, working) behind SDKs; MemMachine is the more established Python stack, Spector adds decay, consolidation and procedural memory in Java.
| MemMachine | spector | |
|---|---|---|
| Stars | 3.1k | 28 |
| Forks | 228 | 16 |
| Language | Python | Java |
| License | Apache-2.0 | Apache-2.0 |
| Last activity | today | yesterday |
| Topics | memory | memory |
| Curated connections | 17 | 3 |
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.
spector — the curator's take
Consider it if you want memory that forgets and consolidates like a cognitive model rather than an ever-growing vector store, with an `npx` MCP server that embeds the kernel. Tiny project needing JDK 25 preview features — not something to bet production on yet; mature options like Hindsight or MemOS have far more evaluation behind them.