hmem — Humanlike Memory for AI Agents
io.github.Bumblebiber/hmem-mcp · v1.6.7
Persistent 5-level hierarchical memory for AI agents. SQLite-backed, lazy-loaded.
Install hmem — Humanlike Memory for AI Agents
Ready-to-paste config for every major MCP client
claude mcp add hmem-mcp -- npx io.github.Bumblebiber/hmem-mcp # or uvx io.github.Bumblebiber/hmem-mcp for Python
Why Beta?
5-49 stars · working prototypes, early adopters welcome.
Alternatives
Same category · same transport · ranked by stars
More Database servers
Top picks in the same category
Embeddable badge
Drop into your README · auto-updates when the rating changes
[](https://benchgecko.ai/mcp/hmem-mcp)
FAQ
Auto-generated from the dataset · updated daily
What is hmem — Humanlike Memory for AI Agents?
hmem — Humanlike Memory for AI Agents is an MCP (Model Context Protocol) server in the Database category. Persistent 5-level hierarchical memory for AI agents. SQLite-backed, lazy-loaded.
How is hmem — Humanlike Memory for AI Agents rated?
BenchGecko rates hmem — Humanlike Memory for AI Agents Beta on the Gecko Rating ladder (40/100). 5-49 stars · working prototypes, early adopters welcome. The underlying GitHub repository has 24 stars.
How do I install hmem — Humanlike Memory for AI Agents?
hmem — Humanlike Memory for AI Agents supports Claude Code, Cursor, Windsurf, and VS Code. Each client needs a different config format · BenchGecko shows ready-to-paste snippets for all four above. Stdio servers run locally via npx; streamable-http and SSE servers connect over the network.
See also
Keep exploring the BenchGecko graph