ai-memoryRust long-term memory server for coding CLIs: lifecycle hooks capture sessions into a sanitized shared wiki, then hand a bounded summary to the next agent so Codex can resume what Claude Code started.
Why switchBoth are cross-harness memory companions for coding agents; memanto leans on its own information-theoretic retrieval engine with no vector DB to run, ai-memory on lifecycle-hook capture compiled into a shared wiki plus explicit vendor-to-vendor handoffs.
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 switchSame job — one persistent memory shared across your coding agents — opposite infrastructure bets: memsearch runs Markdown + Milvus with embedding models you manage; Memanto runs on Moorcheh, its own information-theoretic engine — local Docker (keyless) or managed cloud.
Full comparison → deja-vuIndexes the session histories your coding agents already wrote — 17 harnesses, months retroactive — and serves recall over MCP. 84.9% hit@1 on LongMemEval-S, no LLM, no embeddings. One Go binary.
Why switchBoth give coding agents cross-session memory with nothing to write by hand: deja-vu retro-indexes the logs your harnesses already produced (no hooks, no embeddings, months instantly), memanto runs its own retrieval engine over captured context. Instant history vs richer recall.
Full comparison → agentmemoryPersistent memory for coding agents on the iii engine: MCP server with 53 tools, 12 auto-capture hooks, hybrid search + knowledge graph, zero external DBs. Claims 95% R@5 and 92% token cuts.
Why switchBoth give many coding agents persistent memory without a third-party DB: Memanto is a companion memory agent — three primitives (remember/recall/answer) on its own Moorcheh engine; agentmemory is a 53-tool MCP toolbelt with auto-capture hooks and a knowledge graph.
Full comparison → MemMoltStructured long-term memory over MCP: an enforced bucket-thread-memo hierarchy in one SQLite file, hybrid FTS5 + vector search fused with RRF, local embeddings.
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 →