Persistent 5-level hierarchical memory for AI agents. SQLite-backed, lazy-loaded.
Hmem — Humanlike Memory For AI Agents MCP server exists for a simple reason — assistants are far more useful when they can act on Hmem — Humanlike Memory For AI Agents directly instead of describing what you should do. Persistent 5-level hierarchical memory for AI agents. SQLite-backed, lazy-loaded.
One load_project() call. ~3000 tokens. Your agent knows everything important about a project — every past mistake, every decision, every open task — across sessions, devices, and AI providers. No setup per conversation. No "let me re-read the codebase." It just remembers.
The server ships on npm as hmem, so your MCP client can launch it on demand — there is no separate build step. Add the server block to your client's configuration, restart it, and the tools register themselves.
Once Hmem — Humanlike Memory For AI Agents is connected, these are the calls the assistant has available:
Curation — The Curation tool exposed by this serverAnnouncements — The Announcements tool exposed by this serverYou will need 6 environment variables: HMEM_PROJECT_DIR, HMEM_AGENT_ID, HMEM_PATH, DEEPSEEK_API_KEY, ANTHROPIC_API_KEY, OPENAI_API_KEY. The server will not start without them, which is usually why the tools fail to appear on a first run. Keep credentials in your client's env block or a secrets manager rather than in a file you might commit.
This sits in the knowledge and memory group, where several servers overlap in what they claim to do but differ sharply once you actually set them up. Hmem — Humanlike Memory For AI Agents's toolset — Curation, Announcements — is a fair guide to whether it matches your workflow. It is maintained by Bumblebiber; worth a glance at recent repository activity before you build anything load-bearing on it.
This entry was verified against Hmem — Humanlike Memory For AI Agents's own documentation before publication; SyncDev keeps the directory reviewed rather than auto-generated.
| Tool | What it does |
|---|---|
| Curation | The Curation tool exposed by this server. |
| Announcements | The Announcements tool exposed by this server. |
{
"mcpServers": {
"hmem": {
"command": "/absolute/path/to/node",
"args": ["/absolute/path/to/hmem/dist/mcp-server.js"],
"env": { "HMEM_PROJECT_DIR": "/home/yourname/.hmem" }
}
}
}Configuration as documented by the project. Restart the client after saving.
| Variable | Description | Required |
|---|---|---|
| HMEM_PROJECT_DIR | Filesystem location the server is allowed to use. | Optional |
| HMEM_AGENT_ID | Configuration value read at startup. | Optional |
| HMEM_PATH | Filesystem location the server is allowed to use. | Optional |
| DEEPSEEK_API_KEY | Credential the server authenticates with. | Yes |
| ANTHROPIC_API_KEY | Credential the server authenticates with. | Yes |
| OPENAI_API_KEY | Credential the server authenticates with. | Yes |
A knowledge graph your assistant keeps between sessions — entities, relations and observations that persist.
Kill hallucinated APIs — version-accurate, up-to-date library documentation injected straight into context.
Your workspace, on speaking terms with AI — search, read and write Notion pages and databases.
A structured scratchpad for hard problems — stepwise reasoning with revisions, branches and visible logic.
Symbol-level code navigation, refactoring and memory for coding agents — the IDE brain your assistant has been missing.
Chat with your second brain — search, read and write vault notes through the Local REST API.