agentmemory vs memsearch
Persistent 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. — versus — Zilliz'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.
Same 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.
| agentmemory | memsearch | |
|---|---|---|
| Stars | 26k | 2.4k |
| Forks | 2.2k | 209 |
| Language | TypeScript | Python |
| License | Apache-2.0 | MIT |
| Last activity | yesterday | 4 days ago |
| Topics | memory, coding | memory, coding |
| Curated connections | 2 | 6 |
agentmemory — the curator's take
The benchmark-forward entry in a crowded field — '#1 on real-world benchmarks' is self-run, so weigh it accordingly; what's independently real: 1,428 tests, the viral design gist it implements (Karpathy's LLM-wiki pattern plus confidence scoring and lifecycle), and the smoothest onboarding in the category — hand your agent one URL and it installs itself. The iii engine is your infrastructure bet: a server on :3111, not a library. A 53-tool MCP surface is the opposite of the plain-files philosophy — richer, but agents need guidance to use it well (they ship 15 skills for exactly that reason). Same prolific author as pro-workflow and tailclaude — expect fast movement, budget for churn.
memsearch — the curator's take
The cross-platform play is the point: a conversation in Claude Code becomes searchable context in Codex, OpenCode and OpenClaw — one memory, four plugins, zero per-agent setup. Memories live in readable Markdown (greppable, versionable) with Milvus doing hybrid search, and the standout feature is procedural: it watches for workflows you repeat and distills them into installable skills, maintained in the background. NOT for single-agent loyalists — if you only run Claude Code, opencode-mem-style plugins are lighter — and it's a Zilliz project: the Milvus dependency is also the funnel; check what 'backed by Milvus' costs you operationally before teams adopt.