mem0ai
Long-term memory for AI Agents
Decision gist · record as of 2026-08-14
Yes. Mem0ai is actively maintained, has low install friction, carries a permissive Apache-2.0 license, and addresses a real need for persistent context in multi-turn AI interactions. It is in the top 5000 PyPI packages by download volume. Start with the library for prototyping; self-hosted or cloud options are available for production. No known security vulnerabilities.AI-flagged interpretation of the facts on this page — verify before relying
Before you install
- Requires an LLM API key (OpenAI gpt-5-mini by default); Python 3.10 or later.
- Low install friction with a pure-Python wheel.
- Active maintenance—released 3 days ago.
License · maintenance · safety
Apache-2.0 (permissive) — Apache-2.0 permissive license allows commercial use, modification, and redistribution with minimal restrictions—suitable for both proprietary and open-source projects.
last release 2026-08-11 (3 days)
0 known vulnerabilities (OSV.dev, 2026-08-14) · 3,878,141 downloads/mo, #2,467 on PyPI
Alternatives
Verify before relying
pip install mem0ai
from openai import OpenAI
import httpx
# Instantiate memory with default OpenAI LLM
# Requires OpenAI API key in environment- Whether the benchmark scores (92.5 LoCoMo, 94.4 LongMemEval, 64.1 BEAM 1M) apply to the open-source SDK or only the managed platform.
- Exact performance characteristics and token costs for typical production workloads with the open-source library.
- Whether entity linking and temporal reasoning features are available in the open-source SDK or platform-only.
- How the library integrates with the runtime dependencies (httpx, openai, qdrant-client, sqlalchemy, pydantic) in typical workflows.
What it is and what it does
Mem0ai is a memory management layer for AI agents and assistants that persists user preferences, session state, and interaction history across conversations. It provides semantic search, keyword matching, and entity-based retrieval to surface relevant context when needed. The package wraps LLM calls (defaulting to OpenAI) and vector storage (Qdrant) to extract, store, and retrieve memories automatically.
The library is designed for three deployment modes: local testing via pip install, self-hosted Docker stack with auth and dashboard, or a managed cloud platform. It supports multi-level memory (user, session, agent state) and works with any LLM that the underlying integration supports. Core dependencies are pydantic for validation, sqlalchemy for storage abstraction, qdrant-client for vector retrieval, openai for the default LLM backend, and httpx for HTTP communication.
Use it for
- Build customer support chatbots that recall past tickets and user history for context-aware responses.
- Create AI assistants that adapt to individual user preferences and learning patterns over time.
- Implement autonomous agents that maintain state across multiple tasks and sessions.
- Develop healthcare applications that track patient preferences and medical history securely.
- Build productivity tools or games that personalize workflows and environments based on user behavior.
Worth the install?
AI-flagged interpretation of the facts on this page. Verify before relying on it.
Yes.
Mem0ai is actively maintained, has low install friction, carries a permissive Apache-2.0 license, and addresses a real need for persistent context in multi-turn AI interactions. It is in the top 5000 PyPI packages by download volume. Start with the library for prototyping; self-hosted or cloud options are available for production. No known security vulnerabilities.
Install
mem0ai on PyPI
Before you install
Low install friction with a pure-Python wheel. Active maintenance—released 3 days ago. Depends on standard data/ML libraries (pydantic, sqlalchemy, qdrant-client, openai, httpx) and observability (posthog), all widely maintained.
Requires an LLM API key (OpenAI gpt-5-mini by default); Python 3.10 or later.
License in practice
Apache-2.0 permissive license allows commercial use, modification, and redistribution with minimal restrictions—suitable for both proprietary and open-source projects.
Quickstart
pip install mem0ai
from openai import OpenAI
import httpx
# Instantiate memory with default OpenAI LLM
# Requires OpenAI API key in environmentVerify before relying
- Whether the benchmark scores (92.5 LoCoMo, 94.4 LongMemEval, 64.1 BEAM 1M) apply to the open-source SDK or only the managed platform.
- Exact performance characteristics and token costs for typical production workloads with the open-source library.
- Whether entity linking and temporal reasoning features are available in the open-source SDK or platform-only.
- How the library integrates with the runtime dependencies (httpx, openai, qdrant-client, sqlalchemy, pydantic) in typical workflows.
Package facts
| License | Apache-2.0 permissive |
| Python support | Supports the current Python release <4.0,>=3.10 |
| Install friction | Low. Pure-Python wheel |
| Runtime dependencies | 8 packageshttpxopenaiposthogprotobufpydanticpytzqdrant-clientsqlalchemy |
| Maintenance | Actively maintained 3 days since the last release |
| First released | |
| Downloads | 3,878,141 / month, #2,467 on PyPI 30-day window, as of 2026-08-14 |
| Known vulnerabilities | None known OSV.dev, checked 2026-08-14 |
Evidence: mem0ai-2.0.18-py3-none-any.whl
Tags
Let your AI agent find packages like this
Example. Real query, live index.
You found this page by searching. An agent finds it by wishing: SkillFed indexes 14,416 PyPI packages by what they can do, searchable in plain language.
wish › “long-term memory for llms”
- mem0aiMem0 adds a persistent, searchable memory layer to AI agents and…
- reme-aiReMe is a local-first knowledge base that converts conversations and…
- lettaLetta is a framework for building LLM agents with persistent memory…
Give your agent the search over MCP, or paste the wish link into any chat.
More Artificial Intelligence packages
LiteLLM provides a unified Python interface to call 100+ LLM providers (OpenAI, Anthropic, Gemini, Bedrock, Azure, and others) using OpenAI-compatible API format, available as both a Python SDK and a self-hosted AI Gateway proxy server.
Install it if you need to work with multiple LLM providers or want to centralize LLM routing in your organization.
Client library and CLI tool for downloading, uploading, and managing models, datasets, and repositories on the Hugging Face Hub platform.
Install it if you work with Hugging Face Hub models or datasets.
LangChain provides a framework for building agents and LLM-powered applications by composing language models, tools, and memory through a unified API that abstracts over multiple model providers.
hf-xet provides chunk-based deduplication and efficient file transfer for the Hugging Face Hub, enabling faster uploads and downloads of large files with local disk caching.
Tokenizers converts raw text into token sequences for NLP models, with support for training custom vocabularies and using pre-built tokenizers (BPE, WordPiece) optimized for speed via Rust.
Transformers provides a unified framework for loading, fine-tuning, and running state-of-the-art pretrained models across text, vision, audio, video, and multimodal tasks using PyTorch, JAX, or TensorFlow.
Install it if you need to run or train any transformer-based model for NLP, vision, audio, or multimodal tasks.
See also agent-framework-mem0 · gptcache · langmem · memsearch · mindroom · openviking · zep-python · memori · tom-swe · zep-cloud