StackMap
Subscribe

agentmemory vs ai-memory

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 — Rust 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.

The curated verdict

Both 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.

agentmemoryai-memory
Stars27k4.3k
Forks2.3k314
LanguageTypeScriptRust
LicenseApache-2.0MIT
Last activitytodaytoday
Topicsmemory, codingmemory, coding
Curated connections66

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.

ai-memory — the curator's take

The strongest bet if you genuinely switch harnesses mid-task: hook and MCP installers for roughly fifteen CLIs, a portable event ledger, `ai-memory run <harness>` for managed cross-vendor resume, and one Rust binary you can systemd. You pay for that reach in surface area — per-harness caveats matter (several CLIs discard SessionStart stdout, so handoffs come back through MCP `memory_handoff_accept`; Codex and Kiro need an explicit `finalize-session`), and you configure capture exclusions plus LLM and embedding providers. If you live in exactly one harness, a single-harness plugin gets you 80% of this with a tenth of the setup.