engram-rs is a memory engine for AI agents that organizes memories across three layers based on importance, allowing for effective recall and management of knowledge. It promotes important memories while allowing less relevant ones to decay over time.
From the registry: Hierarchical memory for AI agents. Three-layer (buffer/working/core) with decay and promotion.

$ curl -fsSL https://raw.githubusercontent.com/kael-bit/engram-rs/main/install.sh | bashPlease install the `engram` MCP server into my current AI client (that's you).
Required prerequisites (do these first if not already done):
- **Install engram-rs binary** — Install the engram-rs Rust binary via the official install script. The MCP wrapper (engram-rs-mcp) talks to the local engram-rs HTTP service on port 3917. Run: `curl -fsSL https://raw.githubusercontent.com/kael-bit/engram-rs/main/install.sh | bash`
Canonical MCP server config (stdio transport):
- command: `npx`
- args: ["-y","engram-rs-mcp"]
- optional environment variables:
- `ENGRAM_LLM_URL`: LLM base URL (OpenAI-compatible). Optional — keyword search and lifecycle still work without an LLM. (example: `<your-llm-base-url>`)
- `ENGRAM_LLM_KEY`: LLM API key. (example: `<your-llm-api-key>`)
- `ENGRAM_LLM_PROVIDER`: LLM provider (set to 'anthropic' for Anthropic native). (example: `anthropic`)
- `ENGRAM_GATE_MODEL`: Strong model for quality gate decisions. (example: `gpt-4o`)
- `ENGRAM_LLM_MODEL`: Lightweight model for text processing. (example: `gpt-4o-mini`)
Note: Rust binary + SQLite memory engine. 17 MCP tools. Also runs as an HTTP server on port 3917 with web UI at /ui.
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.ENGRAM_LLM_URLrequiredURL for the LLM API, necessary for intelligent features.ENGRAM_LLM_KEYrequiredAPI key for accessing the LLM.AI orchestration with hive-mind swarms, neural networks, and 87 MCP tools for enterprise dev.
MCP Toolbox for Databases enables your agent to connect to your database.
MCP Toolbox for Databases enables your agent to connect to your database.