Alaya is an embeddable Rust library that provides a memory engine with neuroscience-grounded memory dynamics, allowing agents to store and retrieve conversations efficiently while managing memory decay and structure.
From the registry: Local memory engine for AI agents with knowledge graphs, forgetting, and semantic recall
Please install the `alaya-mcp` MCP server into my current AI client (that's you).
Canonical MCP server config (stdio transport):
- command: `npx`
- args: ["-y","alaya-mcp"]
- optional environment variables:
- `ALAYA_DB`: SQLite database path (example: `~/.alaya/memory.db`)
- `ALAYA_LLM_API_KEY`: OpenAI-compatible API key for auto-consolidation (example: `<your-openai-api-key>`)
- `ALAYA_LLM_API_URL`: OpenAI-compatible chat completions endpoint (example: `https://api.openai.com/v1/chat/completions`)
- `ALAYA_LLM_MODEL`: Model name for auto-consolidation (example: `gpt-4o-mini`)
Add this MCP server to my current client's config in the correct format for you. If you need secrets or credentials I haven't provided, ASK me — do not invent values or leave raw placeholders. After adding it, tell me how to verify the server is connected.ALAYA_DBPath to SQLite database.ALAYA_LLM_API_KEYrequiredAPI key for auto-consolidation, enables ExtractionProvider.ALAYA_LLM_API_URLOpenAI-compatible chat completions endpoint.ALAYA_LLM_MODELModel name for the LLM.AI Agents Framework with Self Reflection and MCP support