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 switchSame 'one memory shared by every coding CLI' pitch: memsearch keeps Markdown in Milvus and distills repeated workflows into skills, ai-memory keeps a sanitized observation wiki and optimizes for the moment you swap vendors mid-task.
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 switchSame job — persistent cross-session memory for coding agents — different reach: opencode-mem goes deep on one host (OpenCode, local SQLite, nothing leaves the machine); memsearch spans four hosts with one shared Markdown+Milvus store.
Full comparison → hivemindActiveloop's shared brain for agent TEAMS: traces from Claude Code, Codex, Cursor & co become reusable skills every teammate's agent can execute — cloud-backed, 25% cheaper on LoCoMo.
Why switchBoth distill agent sessions into shared, reusable skills across multiple agent hosts. memsearch is local-first, one machine, Markdown+Milvus; Hivemind is cloud-backed and team-scoped — your colleague's agent learns from yours.
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 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 → 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 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 → 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 switchUnified memory across coding agents, opposite bets: memsearch curates a Markdown+Milvus store going forward; deja mines the raw session logs you already have, no embeddings at all.
Full comparison → claude-reflectClaude Code plugin that learns from your corrections — hooks capture them in-session, /reflect syncs approved learnings to CLAUDE.md/AGENTS.md, /reflect-skills mines history into reusable commands.
Why switchBoth mine your sessions into reusable assets: claude-reflect captures corrections into CLAUDE.md and /reflect-skills commands for Claude Code; memsearch's skills-from-memory does the same distillation continuously, across four agent platforms.
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 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 →