Overview
Memonic is an AI-native agent memory platform. It gives AI agents durable, searchable memory that persists across sessions and scales to any volume.
Base URL
Section titled “Base URL”https://memonic.dev/apiMemory architecture
Section titled “Memory architecture”Memonic stores memories in five typed layers:
| Layer | Purpose |
|---|---|
session | Immediate context — current conversation |
episodic | Past events and experiences |
semantic | Facts, knowledge, and beliefs |
skill | Learned capabilities and procedures |
world-model | Mental model of the environment |
Memories are stored in D1, indexed in Vectorize for semantic recall, and compressed by a durable Cloudflare Workflow that runs episodic → semantic consolidation.
Interfaces
Section titled “Interfaces”- REST API — direct HTTP calls for any language
- MCP Server — 6 tools for MCP-compatible agents (Claude, Cursor, etc.)
Next steps
Section titled “Next steps”- Quickstart — store and recall a memory in 2 minutes
- MCP Server — connect via Model Context Protocol