Give your AI memory in 2 minutes

Your AI forgets everything between sessions. Deep Recall fixes that. Install the MCP server and your AI agent remembers conversations, preferences, facts — forever.

Install

1 Install the MCP server 30 seconds

pip install deeprecall-mcp

That's it. One package, no dependencies to manage.

2 Create your account 30 seconds

Sign up at deeprecall.dev with Google, GitHub, or email. You'll get your API key instantly — no email verification needed to start using the API.

Or use the API directly:

curl -X POST https://api.deeprecall.dev/v1/signup \
  -H "Content-Type: application/json" \
  -d '{"name": "Your Name", "email": "you@example.com", "password": "your-password"}'

Copy the api_key from the response. Save it — it's only shown once. You can always create more in your dashboard.

3 Add to your AI tool 60 seconds

Claude Code
Cursor
Windsurf
Cline
{
  "mcpServers": {
    "deeprecall": {
      "command": "deeprecall-mcp",
      "env": {
        "DEEPRECALL_API_KEY": "ec_live_YOUR_KEY"
      }
    }
  }
}

Add this to ~/.claude/settings.json or run /mcp in Claude Code to manage MCP servers.

{
  "mcpServers": {
    "deeprecall": {
      "command": "deeprecall-mcp",
      "env": {
        "DEEPRECALL_API_KEY": "ec_live_YOUR_KEY"
      }
    }
  }
}

Add this to .cursor/mcp.json in your project root, or add globally in Cursor settings.

{
  "mcpServers": {
    "deeprecall": {
      "command": "deeprecall-mcp",
      "env": {
        "DEEPRECALL_API_KEY": "ec_live_YOUR_KEY"
      }
    }
  }
}

Add to your Windsurf MCP configuration file.

{
  "mcpServers": {
    "deeprecall": {
      "command": "deeprecall-mcp",
      "env": {
        "DEEPRECALL_API_KEY": "ec_live_YOUR_KEY"
      }
    }
  }
}

Add to Cline's MCP server settings in VS Code.

4 Start using it Immediately

That's it. Start a new conversation. Your AI now has persistent memory.

Try saying things like:

The AI will automatically use Deep Recall tools to store and retrieve memories across sessions.

Pro tip: Drop this CLAUDE.md snippet into your project root to teach the AI to use memory proactively — searching at the start of every conversation and remembering important facts automatically.

What your AI can do now

deeprecall_remember

Store facts, preferences, episodes, skills. Optionally tag with emotional context (happy, frustrated, excited).

deeprecall_search

Find memories by meaning, not just keywords. "outdoor hobbies" finds "loves hiking in mountains."

deeprecall_conversation

Store conversation turns. On paid plans, auto-extracts facts and entities from the conversation.

deeprecall_entities

Track people, organizations, places — and the relationships between them.

deeprecall_contradictions

Auto-detects when new memories conflict with old ones. "The API uses Postgres" vs "The API uses SQLite" — flagged.

deeprecall_reinforce

Memories that get used grow stronger. Unused memories fade. Your memory self-optimizes.

deeprecall_decay

Intelligent forgetting runs automatically. Important memories resist decay. Noise fades.

deeprecall_stats

See total memories, entities, usage, and plan limits.

deeprecall_account

Check your plan, usage percentage, and upgrade options.

deeprecall_emotional_search

Search boosted by emotional similarity. Memories stored during frustration surface when frustrated again.

deeprecall_topology

See how your memories cluster into communities. Knowledge graph analysis with Louvain detection.

How it works under the hood

Why is this different from CLAUDE.md or .cursorrules?

Those files are loaded into context every time. They eat tokens and have no structure. Deep Recall stores memories in a real database with semantic search — your AI retrieves only what's relevant, not everything.

What happens to my memories?

Stored in your own isolated database. Not shared with anyone. Not used to train models. You can export or delete everything at any time.

How does intelligent forgetting work?

Every memory has a salience score (0-1). Memories you access frequently resist decay. Memories you never look at gradually fade. When you're near your storage limit, dead memories get pruned automatically. The result: your memory store stays clean without you doing anything.

What's Hebbian reinforcement?

When your AI retrieves memories and uses them in a good response, those memories get stronger (higher salience). When retrieved memories aren't useful, they get weaker. Over time, your memory store self-optimizes — useful knowledge rises, noise sinks.

Free tier limits

Need more? See pricing — plans start at $19/mo for 100,000 memories.

Direct API access

Don't use MCP? The same features are available as a REST API. Full interactive docs at api.deeprecall.dev/docs.

import httpx

dr = httpx.Client(
    base_url="https://api.deeprecall.dev",
    headers={"X-API-Key": "ec_live_..."}
)

# Store
dr.post("/v1/memories", json={
    "content": "Alice prefers dark mode",
    "person": "alice",
    "kind": "preference"
})

# Search
results = dr.get("/v1/memories/search",
    params={"q": "user preferences"}).json()

Need help?

Email aidan@deeprecall.dev