AI Agents
agent-beacon
Self-improving memory layer that works across AI agent harnesses.
★ 1.8k starsMIT
View guide →// agents · BAI-LAB/MemoryOS
MemoryOS
MemoryOS is an open-source ai agents project by BAI-LAB (BAI-LAB/MemoryOS on GitHub). It has 1,591 GitHub stars and 165 forks, is released under the Apache-2.0 license, and was last updated on GitHub on 7 July 2026.
A memory operating system for long-term, personalized AI agents.
💎 Hidden gem★ 1.6k stars⑂ 165 forksApache-2.0updated 2026-07
▦ visual — this project's README ships no embeddable screenshot,
so here's a placeholder. The guide below is complete regardless.
so here's a placeholder. The guide below is complete regardless.
// project facts
Project facts
- Repository
- BAI-LAB/MemoryOS
- GitHub stars
- 1,591
- Forks
- 165
- License
- Apache-2.0
- Last updated on GitHub
- 7 July 2026
- Category
- AI Agents
- Listing
- Hidden gem — a shorter page for a lesser-known project
- Official site
- Official site
// how it works
How it works
- Clone the repository
Download the source and enter the folder.
- Install dependencies
Pull the Python packages it needs.
- Configure memory stores
Set up the storage backends per the README.
- Build a remembering agent
Wire your agent to the memory OS.
// features
Why people love it
Long-term memory
Agents retain knowledge across sessions.
Personalization
Memory scoped to individual users.
EMNLP 2025 oral
Peer-reviewed research behind the design.
RAG retrieval
Recall the right memory at the right time.
Python framework
Integrates with existing agent code.
1,591 stars
Wide research and builder interest.
Advertisement
// run it
Run it yourself
- Step 1 — Clone the repo
Download the source and move into the project folder.
git clone https://github.com/BAI-LAB/MemoryOS.git cd MemoryOS - Step 2 — Install dependencies
Pull the Python packages it needs.
pip install -r requirements.txt - Step 3 — Run the demo
Try the memory flows per the README.
python demo.py
// use cases
What you can build
- Give a personal assistant real long-term memory.
- Personalize an agent per user at scale.
- Study memory architectures from the paper.
- Build agents that learn across sessions.
The AI Agents shelf also holds AiSOC — open-source AI SOC — alert fusion, LLM triage, MITRE ATT&CK investigation and a replayable decision ledger. Readers working through the Agents shelf also stop at yomo, Serverless AI agent framework running on geo-distributed edge infrastructure. Also on this shelf: rocketmq-rust — Apache RocketMQ rewritten in Rust for the AI era.
Advertisement
// faq
Questions, answered
Who maintains MemoryOS?
It is an open-source project at BAI-LAB/MemoryOS with 165 forks.
Is it free for commercial use?
Yes. It is Apache-2.0 licensed.
What is the research behind it?
It was presented as an oral paper at EMNLP 2025.
How is it different from vector memory?
It is a full memory operating system: organization, retrieval, and personalization.
Which language is it in?
Python, built on LLM and RAG primitives.
// keep exploring
Similar tools
RAG & Knowledge
wenlan
Agent-fed knowledge base that distills learnings into cited wiki pages.
★ 79 starsApache-2.0
View guide →AI Chat
Smart-Memory
SillyTavern extension giving AI roleplay characters long-term memory.
★ 61 starsAGPL-3.0
View guide →AI Agents
langmem
LangMem: long-term memory primitives for LangGraph agents that learn and adapt from conversations.
★ 1.7k starsMIT
View guide →AI Agents
cognee
Open-source AI memory that gives agents persistent long-term recall.
★ 31.6k starsApache-2.0
View guide →AI Agents
agent-memory
Long-term memory runtime for AI agents — plain Markdown as truth, local ranked retrieval, no API key
★ 2.6k starsMIT
View guide →// alternatives
Alternatives in AI Agents
The most-starred other AI Agents projects in the LibreAI catalogue — the realistic shortlist if MemoryOS is not the right fit.
- openclaw★ 391.6k
A personal AI that really does things — on any OS, with your data staying yours.
- superpowers★ 294.9k
An agentic skills framework & software development methodology that works.
- ECC★ 275.2k
Agent harness optimization system with skills, memory and security for Claude Code, Codex and more
- hermes-agent★ 252.0k
The agent that grows with you — a Python framework for adaptive AI agents.
- deepseek-harness★ 245.5k
DeepSeek's plugin-based agent harness where everything is a plugin.
// more in agents
More in AI Agents
Nearby AI Agents projects in the catalogue, closest in stars to MemoryOS — keep exploring the shelf either side of it.
- ktx★ 1.6k
Context layer so AI agents query your analytics databases accurately.
- patchwork★ 1.6k
Agentic AI framework for automating enterprise workflows like code review.
- matlab-mcp-server★ 1.6k
Official MathWorks MCP server: drive MATLAB from AI coding agents.
- cc-safety-net★ 1.6k
Pre-execution guard that stops AI agents' destructive commands cold.
- Adala★ 1.6k
Autonomous data-labeling agents: let AI do the annotation grunt work.
- AVA★ 1.6k
AI-native visual analytics framework that helps agents chart your data.
Get MemoryOS
Free and open — grab the source, star the repo, and start creating.