Verified project record

MemoriLabs/Memori

memorilabs/memori provides agent-native memory infrastructure that captures structured state from conversations and agent execution, making it available for future recall. It requires a supported LLM API key and coding to implement, and operates as a library, CLI, or managed service.

Project overview

Project type: AI Agent · RAG
Use cases: Knowledge Q&A · Automation
Deployment: Refer to project documentation
License: License pending

Best for

Developers, enterprise teams, and AI engineers who need to build production agents with persistent state and are willing to integrate a library using code.
Systems needing to group LLM interactions into manageable sessions.

Key capabilities

Automatically captures structured memory from conversations and agent execution in the background after each turn, and makes it available for agents to recall.
Enhances memories at entity, process, and session levels with attributes, events, facts, people, preferences, relationships, rules, and skills.
Groups LLM interactions together into sessions, with support for resetting or overriding the session ID.
Allows users to use their own database for storing memories instead of the managed cloud.
A unified tool for managing account, keys, and quotas across all SDKs.

Limitations and risks

Memori cannot make memories if no attribution is provided.
The free tier is rate-limited by IP address quota; exceeding limits requires signup or an API key.
The system currently supports text inputs and outputs.
GPU requirements and telemetry practices are not documented.

Getting started

Sign up at app.memorilabs.ai, install the package via pip or npm, set your MEMORI_API_KEY and a supported LLM API key (like OPENAI_API_KEY) in the environment, and call client.chat.completions.create via the registered LLM.

Evidence and sources

GitHub project description: Memori is agent-native memory infrastructure. A LLM-agnostic layer that turns agent execution and conversation into structured, persistent state for production systems.
README: pip install memori
README: npm install @memorilabs/memori
README: Your agent forgets everything between sessions. Memori fixes that. It remembers your stack, your conventions, and how you like things done so you stop repeating yourself.
README: Memori was evaluated on the LoCoMo benchmark for long-conversation memory and achieved 81.95% overall accuracy while using an average of 1,294 tokens per query. That is just 4.97%…

Reviewed at: 2026-07-17T14:09:15Z