Is hmem — Humanlike Memory for AI Agents safe and trustworthy?

tashan scores hmem — Humanlike Memory for AI Agents on public evidence — tashan score 48.0/100, it is currently active, note: a single primary maintainer (bus-factor risk), no known advisories against the current release, it runs a script at install time. Audit scope: OSV advisories, install-time scripts, build provenance and declared permission surface. We do not review source code or execute the capability.

How do I install hmem — Humanlike Memory for AI Agents?

In Claude Code: run `claude mcp add hmem -- npx -y hmem-mcp`. In Cursor / Claude Desktop, add it to mcp.json / claude_desktop_config.json.

‹ The Index

hmem — Humanlike Memory for AI Agents

npm

Persistent 5-level hierarchical memory for AI agents. SQLite-backed, lazy-loaded.

Works with: Claude Code, Cursor, Claude Desktop, Codex CLI, Gemini CLI, Cline, Windsurf, VS Code (installable)
installable: each client documents how to load an MCP server of this type — that is the client's promise, not a claim verified against this capability

Category: Database — see all ranked ›

Work: Knowledge management

Who it is for: Operations · Researcher

Install (Claude Code):

claude mcp add hmem -- npx -y hmem-mcp

solid

“Two servers, 24 tools tabled, 21 skills with triggers; install is not in the first 10k.”

This grade is wrong ›

tashan score: 48.0
Instruction depth: 78.0 (solid — documents the job properly, with examples you could follow)
Adoption: 82/wk
Upkeep: 66.0
Freshness: 79.0
Evidence coverage: 100% of the inputs this score can use
Health: active
License: MIT

Security audit

Every finding is shown in full — which advisory, the version that fixes it, and the exact command run at install time. Nothing in this audit is behind a licence.

No known advisoriesclearchecked against OSV for 8.0.0 — this package, not its dependency tree

Runs a script at install timecode

node scripts/use-prebuild.cjs && node -e "try{require('child_process').execSync('node dist/cli.js update-skills',{stdio:'ignore'})}catch(e){}"

No access inferred from declared dependenciesnothing it depends on reaches files, shell or network. This reads declarations only — built-in APIs are invisible to it, so absence of a declaration is not absence of access

No build provenanceno attestation — the published artifact cannot be traced to its source

You searched for one. Check the rest of your stack:

npx tashan-cli doctor

Reads the config already on your machine and names what is dead, deprecated or running code at install time. No account, nothing uploaded.

tashan Pro$6/mo

hmem — Humanlike Memory for AI Agents scores 48 today. Pro keeps the series, so you can see whether that is a project getting better or one on its way down.

The whole series behind any row, back to the first day we measured it
The replacement, named — not just the news that something died
tashan doctor over your own config, on your own machine

Start a 7-day trial › Everything measured on this page stays free.

Show your score

Measured this well? Put the live badge in your README — it updates as the score does.

[![tashan](https://tashan.sh/badge/pkg-hmem-mcp.svg)](https://tashan.sh/capability/pkg-hmem-mcp.html)

npm ↗ · source ↗ · pkg:hmem-mcp

Everything on this page is public evidence and free. What it cannot know is whether you run this — check your whole config, free, in the browser. tashan Pro adds the series behind each row and names a replacement for anything dying.

Already running this? Check your whole config — free, in your browser, nothing installed. Or npx tashan-cli doctor locally, which sends nothing at all.

Measured 2026-09-13 · scorer s5 · how · something wrong here?