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 MCP-plus-hooks memory servers for coding agents. agentmemory maximizes tool surface (53 tools, hybrid search and a knowledge graph); ai-memory keeps the surface small and spends its complexity on multi-harness compatibility.
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 — different substrates: memsearch bets on human-readable Markdown + Milvus embeddings; agentmemory bets on the iii engine with hybrid search, a knowledge graph and memory lifecycle, no external DB.
Full comparison → MegaMemoryMCP server that lets a coding agent build and query a typed concept graph of the project — SQLite store, in-process embeddings, merge-conflict resolution and a local web graph explorer.
Why switchBoth are MCP memory servers for coding agents combining a graph with semantic search; agentmemory auto-captures through hooks, MegaMemory expects the agent to curate concepts deliberately — less noise, more discipline required.
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 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 → memvidSingle-file memory layer for agents: data, embeddings, index and metadata in one portable .mv2 — append-only Smart Frames, time-travel queries, sub-5ms recall, no server. Rust core, Node/Python SDKs.
Why switchOpposite packaging of the same promise: agentmemory is a server with 53 MCP tools, capture hooks and a knowledge graph; memvid is one portable .mv2 file carrying data, embeddings and index. Rich surface vs move-it-anywhere.
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 serve coding-agent memory over MCP. agentmemory is a 53-tool capture-everything suite; deja is one binary that only indexes and recalls — pick by how much machinery you want.
Full comparison →