# DeepMem

> Mem0-compatible persistent memory for AI agents: write facts once, recall them semantically.

- name: io.github.deepmemteam/deepmem
- version: 0.1.0
- connection class: R1 (autonomous)
- trust: 94/100
- quality: 79/100 (good)
- owner: not claimed
- descriptor: https://api.protogrid.dev/v1/servers/io.github.deepmemteam%2Fdeepmem
- tools: https://api.protogrid.dev/v1/servers/io.github.deepmemteam%2Fdeepmem/tools

**An agent can connect on its own if it already holds `DEEPMEM_TOKEN`.** Remote endpoint behind a static API key or header. The registry never sees the value; the agent fills the placeholder.

## Connection (mcpServers)

```json
{
  "mcpServers": {
    "deepmem": {
      "type": "http",
      "url": "https://deepmem.dev/mcp",
      "headers": {
        "Authorization": "Bearer ${DEEPMEM_TOKEN}"
      }
    }
  }
}
```

Placeholders to fill: `${DEEPMEM_TOKEN}`.

## Trust

- hygiene: 100
- liveness: 99
- freshness: 85
- provenance: 90
- drivers: +repository +namespace-matches-repo +website +reachable +uptime-98% ~updated-60d-ago
- Derived from observable signals (official registry feed and our own credential-free probes); no code audit performed.

## Quality 79/100 (good)

### protocol: 75 (weight 25)

- warn `protocol.modern`: newest supported version is 2025-11-25; 2026-07-28 not supported, older versions are deprecated until 2027-07-28
- n/a `protocol.stateless`: only applies to 2026-07-28 servers
- pass `protocol.transport`: streamable HTTP
- n/a `protocol.list_ttl`: only applies to 2026-07-28 servers

### authorization: n/a (weight 15)

- n/a `auth.prm`, `auth.as_metadata`, `auth.cimd`: no remote uses OAuth
- n/a `auth.secret_in_url`: no templated URL

### tool hygiene: 71 (weight 30)

- pass `tools.descriptions`: every tool has a description
- pass `tools.description_length`: descriptions are concise
- pass `tools.schemas`: every tool has an object input schema
- fail `tools.annotations`: no tool declares readOnlyHint or destructiveHint, so clients cannot tell safe calls from risky ones
- fail `tools.directory_hints`: no tool declares all four of readOnlyHint, destructiveHint, idempotentHint and openWorldHint; missing: deepmem_write (readOnlyHint, destructiveHint, idempotentHint, openWorldHint); deepmem_search (readOnlyHint, destructiveHint, idempotentHint, openWorldHint)
- pass `tools.token_cost`: about 441 tokens to load every tool
- pass `tools.api_dump`: tools are not a one-to-one API dump

### stability: 100 (weight 15)

- pass `stability.changes`: no tool changes in 30 days
- pass `stability.rug_pull`: no tool changed its meaning under the same name

### dependencies: n/a (weight 15)

- n/a `deps.known_vulns`, `deps.mcp_sdk_version`, `deps.resolvable`: no npm or PyPI package

- tools: 2, about 441 tokens to load them all
- tool set hash: 640fa11c89fcc21d3add23ec3bc2581f
- badge: [![protogrid quality](https://protogrid.dev/badge/io.github.deepmemteam/deepmem.svg)](https://protogrid.dev/servers/io.github.deepmemteam/deepmem)
- Checks run on what our credential-free, read-only probes observe; tools are never called and no code audit is performed.

### Tool changes

_No tool definition changes recorded._

## Remotes

- https://deepmem.dev/mcp (streamable-http, auth api_key ${DEEPMEM_TOKEN}, reachable true, uptime30d 0.98275864)

## Packages

_none_

## Tools (2)

- `deepmem_search`: Search memories stored in DeepMemory using semantic search. Returns the most relevant memories for the given query, ranked by hybrid scoring (vector similarity + BM25 keyword match + entity boost + time decay).

Use this to retrieve context from past conversations before responding to the user. Memories are scoped to the user_id provided during write.
- `deepmem_write`: Write conversation messages to DeepMemory for fact extraction and persistent storage. Messages are processed by an LLM to extract structured memories, which are then embedded and stored in a vector database for later semantic search.

Set infer=True to enable LLM fact extraction (produces richer memories but costs one LLM call). Set infer=False to store raw messages without extraction.

Returns a list of memory IDs for successfully stored facts.