Memori
Open-source, LLM- and datastore-agnostic memory layer for agents from Memori Labs: Python/TypeScript SDKs that wrap your LLM client, bring-your-own DB or Memori Cloud, plus MCP.
Tags
Description
Register an LLM client (e.g. OpenAI) with the SDK and conversations are persisted and recalled automatically, attributed to an entity and process. Self-host free under Apache-2.0 with your own database (BYODB), or use Memori Cloud: a free tier (5,000 memories created and 15,000 recalled) and production plans from $60K/year. Coding agents can connect without the SDK through the remote MCP server at https://api.memorilabs.ai/mcp/ using X-Memori-API-Key, entity and process headers.
Agent access
Related
- Mem0: Memory layer for AI agents and apps: drop-in persistent memory that lets agents learn from past interactions.
- Zep: Unified context layer that combines business data, documents and conversations into governed context and memory for agents.
- Letta: Platform for stateful agents with memory, identity and the ability to learn over time (formerly MemGPT); terminal UI, App Server, desktop app and Agent SDK.
- Hindsight: Open-source agent memory system from Vectorize focused on agents that learn: retain, recall and reflect operations over memory banks, with an MCP server and a managed cloud.
- Supermemory: Memory and context engine for AI agents with a Memory API; can run fully locally or hosted.
Sources
- https://github.com/MemoriLabs/Memori
- https://memorilabs.ai/pricing
- https://memorilabs.ai/docs/memori-cloud/
Machine-readable
- JSON
- Markdown
- Source file on GitHub (edit via pull request)