# remembra

Persistent memory for AI agents. Store context, recall semantically, never lose important information.

## Quick Start

```bash
# Connect this server (installs CLI if needed)
npx -y @smithery/cli@latest mcp add remembra-ai/remembra

# Browse available tools
npx -y @smithery/cli@latest tool list remembra-ai/remembra

# Get full schema for a tool
npx -y @smithery/cli@latest tool get remembra-ai/remembra store_memory

# Call a tool
npx -y @smithery/cli@latest tool call remembra-ai/remembra store_memory '{}'
```

## Direct MCP Connection

Endpoint: `https://remembra--remembra-ai.run.tools`

**Optional config:**
- `REMEMBRA_API_KEY` (query) — Your Remembra API key (get one at remembra.dev/signup)

## Tools (5)

- `store_memory` — Store information in persistent memory. Automatically extracts entities (people, organizations, locations) and facts fr…
- `recall_memories` — Search persistent memory for relevant information using hybrid search (semantic + keyword). Use this BEFORE answering q…
- `forget_memories` — Delete memories from persistent storage. GDPR-compliant deletion. Provide exactly one of: memory_id, entity, or all_mem…
- `health_check` — Check Remembra server health and connection status. Returns server version, status, and component health.
- `ingest_conversation` — Ingest a conversation and automatically extract memories. Processes messages and intelligently extracts facts worth rem…

```bash
# Get full input/output schema for a tool
npx -y @smithery/cli@latest tool get remembra-ai/remembra <tool-name>
```

## Resources

- `memory://recent` — Returns the 10 most recently stored memories for quick context

## Prompts (3)

- `recall-context` — Recall recent context for session continuity. Use at the start of a conversation to restore memory.
- `store-summary` — Store a summary of the current session for cross-session continuity.
- `setup-check` — Verify Remembra connection and run health check.