engrimLocal SQLite episodic memory shared across Antigravity, Claude Code, Cursor, Windsurf and Codex: hooks/MCP capture decisions, FTS5+model2vec hybrid recall reloads ~1k tokens per session.
Why switchSame single-SQLite-file, FTS5-hybrid, MCP-served memory design; memmolt enforces a bucket-thread-memo hierarchy, engrim focuses on multi-harness hooks and a bounded memory pack.
Full comparison → lossless-memoryLossless long-term memory for a personal AI: verbatim JSONL logs, time-first search over SQLite FTS5 (sqlite-vec as last resort) and a tiny 'where are we now' index injected every turn.
Why switchBoth are single-machine SQLite memory stores with FTS5 plus vector fallback; memmolt imposes a bucket-thread-memo hierarchy, lossless-memory keeps raw lines on a time axis.
Full comparison → memantoCompanion memory agent for 20+ coding agents, built on Moorcheh — its own information-theoretic engine, no third-party vector DB to manage. Runs local (Docker + Ollama, keyless) or on their cloud.
Why switchBoth put persistent memory under your coding agents: MemMolt is strictly local, a bucket-thread-memo hierarchy over MCP; Memanto is a companion memory agent on its own Moorcheh engine, deployable fully local or on their cloud.
Full comparison → memsearchZilliz's unified memory for coding agents: one Markdown + Milvus store shared across Claude Code, Codex, OpenCode and OpenClaw — hybrid search, plus repeated workflows distilled into skills.
Why switchBoth are structured long-term memory with hybrid search for agents: MemMolt enforces a bucket-thread-memo hierarchy in one SQLite file over MCP; memsearch bets on free-form Markdown + Milvus and per-agent plugins.
Full comparison → MemMachineLong-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.
Why switchBoth agent memory layers over MCP: MemMachine ships episodic/profile/working memory with framework SDKs; MemMolt bets on one enforced bucket-thread-memo hierarchy in a single SQLite file.
Full comparison → opencode-memOpenCode plugin giving coding agents persistent cross-session memory — local SQLite + vector search, automatic memory capture, user-profile learning, and a web UI. Nothing leaves your machine.
Why switchLocal SQLite+vector agent memory either way: opencode-mem auto-captures per-session for OpenCode; MemMolt is deliberate, structured recall for any MCP client.
Full comparison → hindsightAgent memory that learns, not just recalls: retain/recall/reflect API over Postgres, SOTA on LongMemEval. Self-host via Docker with UI; Python/TS clients, any LLM provider.
Why switchBoth serve agent long-term memory with hybrid retrieval; memmolt is one SQLite file behind MCP with an enforced hierarchy, hindsight a self-hosted service that consolidates and reflects.
Full comparison → MemoriaRust 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.
Why switchBoth expose structured long-term memory over MCP; memmolt enforces a bucket-thread-memo hierarchy in SQLite, Memoria is a versioned memory database on MatrixOne.
Full comparison →