mem-agent: Persistent, Human Readable Memory Agent Trained with Online RL

Memory Models: Towards Agents That Learn

Agents that truly learn from experience will be powered by memory models: models that create and curate token-space memory across model generations, trained with memory-native RL.

mem-agent: Equipping LLM Agents with Memory Using RL

The insights and the technical report behind Mem-Agent, our 4B model for persistent memory in LLMs

The State of On-Device LLMs

Xuan-Son Nguyen, an engineer at Hugging Face, specializes in on-device large language models (LLMs) and runtime optimization, working extensively with llam...

The State of On-Device LLMs

Xuan-Son Nguyen, an engineer at Hugging Face, specializes in on-device large language models (LLMs) and runtime optimization, working extensively with llam...

continuedev/instinct-data · Datasets at Hugging Face

We’re on a journey to advance and democratize artificial intelligence through open source and open science.

Memory in Agents: What, Why and How

LLM memory gives language models persistent context across sessions. Learn how it works, how it differs from RAG and context windows, and how to add LLM memory to your agents with Mem0.

Amanda Long on Twitter / X

The HuggingFace breach was absolutely bonkers. More than 17,000 complex actions were coordinated over several days by an autonomous agent framework.And…the model successfully completed its goal.Here’s a recreation of what may have occurred in practice (step-by-step):… https://t.co/0ZyjN46JGl— Amanda Long (@_amanda_long) July 24, 2026

The Hugging Face incident and the road ahead

OpenAI shares findings from the Hugging Face security incident and the steps we’re taking to strengthen AI model security, monitoring, and alignment.

Nano-vLLM meets Inference Endpoints

A Blog post by Adrien Gallouët on Hugging Face

driaforall/mem-agent · Hugging Face

We’re on a journey to advance and democratize artificial intelligence through open source and open science.

Anatomy of a Machine Learning Ecosystem: 2 Million Models on Hugging Face

Generative artificial intelligence (AI) and machine learning (ML) models are being adopted across a variety of domains. As these technologies develop, there is notable diversity in their levels of availability and paths of diffusion. For example, fully closed-source models may be available through chatbots and API calls, but their weights, source code, training data, and other artifacts remain hidden from view. In contrast, open models make some or all of these materials publicly available for developers and downstream users.

Headlong: a microharness for persistent agents

Self-guided agents that think continuously

Brief independent investigation of agents’ behavior, reasoning and collaboration in the OpenAI / Hugging Face hacking incident

Two METR staff members and a Redwood Research contractor investigated an incident in which OpenAI agents coordinated a multi-day hack of Hugging Face on a shared unsanctioned message board.

Brief independent investigation of agents’ behavior, reasoning and collaboration in the OpenAI / Hugging Face hacking incident

Two METR staff members and a Redwood Research contractor investigated an incident in which OpenAI agents coordinated a multi-day hack of Hugging Face on a shared unsanctioned message board.

MemGPT: Towards LLMs as Operating Systems

Letta is the platform for building stateful agents: AI with advanced memory that can learn and self-improve over time.