The response to Raven these past two days has blown us away. Thank you! 🐦‍⬛ Clearly the ideas resonate: • One harness can't be best at everything, so Raven turns its own specialist harnesses and the agents you already use (Claude Code, Codex and more) into one team • RSI goes beyond skills: the whole harness, orchestration layer included, is built to be rewritten and improved by AI And it's not just an idea. It's backed by research. Our technical report is out: Raven: The Harness of Harnesses for Composable Agentic Intelligence 📄 🤗 An upvote on Hugging Face means a lot 🙏

Raven 0.2.0 — The Harness of Harnesses, built for RSI. 🐦‍⬛ One harness can't be best at everything. Raven combines its own specialist harnesses (Research, Code, Design, Oncall) with the agents you already use (Claude Code, Codex and more) into one team. And it's built for RSI, and not just at the skill level. The whole harness can be rewritten by AI: prompts, policies, strategy code, playbooks. Every sub-harness, including the orchestration layer itself, is its own instance that can be improved. With Raven you can: 1. Orchestrate many agents as one team. Raven's sub-harnesses and external agents work in one task graph with shared memory across sub-agents, powered by leading orchestration (0.963 Node F1 on the Multi-Agent Orchestration Benchmark). 2. Run long, complex tasks. Oncall and proactive execution keep work going for days, from scientific research loops to shipping a full Godot game. 3. Build vertical agents with RSI. Use Raven's RSI to develop and refine an agent for your domain, and we'll optimize it with you. Experimental for now; reach out to the Raven team(Discord: More in the video and slides below. Open source, Apache-2.0. (lots of work made with Raven lives there, and much of this launch's material was made with Raven too)

EverMind is Hiring: Technical PM (Agent OS & Memory) Based in Silicon Valley | Shanghai | Beijing What we need: Tech + Product: Deeply understand Agent execution mechanics under the hood (OpenClaw/Hermes Agent is a +). AI-Native: Fluent in Vibe Coding. You can spin up working demos yourself to validate concepts. LTM Focus: Intensely driven to build an Agent OS with true Long-Term Memory. Flexible setup: Open to part-time/intern as a trial. DM me to chat!

AI self-evolution is undoubtedly the ultimate core of next-gen AI—and true evolution is fundamentally built on Long-Term Memory. 🧠 At EverMind, we believe every AI of the future must have long-term memory. If you want to build an AI that continuously adapts and unlocks a massive data flywheel, you need EverOS. ♾️ The update we’ve been polishing for ages is FINALLY live! 🚀 It's way more than just a product update—Methods, Benchmarks, Usecases, and a fresh site are all here. Here’s the breakdown: 👇 1️⃣ EverMemOS ➡️ EverOS: The ultimate one-stop shop. EverOS now empowers your Agents with self-evolution capabilities—just like Hermes Agent. Plus, we’ve added full multi-modal support. Use our Methods to customize Usecases into your own Agents, then benchmark to optimize them. It's the absolute all-in-one king. 👑 2️⃣ EvoAgentBench is LIVE & Open-Source: The perfect tool to test your custom Claude Code, OpenClaw, Hermes, or any Agent you throw at it. 📊 3️⃣ Brand New Website: Aesthetics matter. The new vibe, colors, and interactive experiences are absolutely off the charts. 🎨🔥 Dive in here: #EverOS# #AI# #AgentTools# #Harness# @Memory #OpenClaw# #Hermes# #ClaudeCode#

Every major wave of computing has been defined by how we store and retrieve information. Mainframes, databases, the cloud. AI is no different. The teams that competed at Memory Genesis 2026 understand something most of the industry has not fully internalized yet: memory is not just infrastructure. It is intelligence itself. This event was a glimpse of that future. Grateful to everyone who showed up to build it with us.

A few weeks ago we published our Memory Sparse Attention paper, a new way to give AI models long-term memory that actually works. Today's LLMs/Agents forget. They can only hold so much context before things start falling apart. We built a system that lets a model remember up to 100 million tokens, the length of about a thousand books, and still find the right answer with less than 9% performance loss. On several benchmarks, our 4-billion parameter model even beats RAG systems built on models 58× its size. The idea? Instead of searching a separate database and hoping the right info comes back (that's how RAG works), we built the memory directly into how the model thinks. It learns what to remember and what to ignore, end to end, no separate retrieval pipeline needed. The response to the paper blew us away. Researchers and engineers everywhere asking the same thing: "When can we see the code?" So we got to work, cleaned up the inference code, documented it, and made it ready for the community to dig in. You asked for it. We open-sourced it.

MSA (Memory Sparse Attention) represents our significant exploration in the field of long-term memory. It stands as the first end-to-end long-term memory framework for large models to genuinely achieve a 100M context length. Interestingly, as the memory length scales from 16K to 100M, the model's performance score decreases by a mere 9%, demonstrating highly robust scalability. Main contribution： 1，We propose MSA, an end-to-end trainable, scalable sparse attention architecture with a document-wise RoPE that extends intrinsic LLM memory while preserving representational alignment. It achieves near-linear inference cost and exhibits < 9% degradation even when scaling from 16K to 100M tokens. 2，We introduce KV cache compression to reduce memory footprint and latency while maintaining retrieval fidelity at scale. Paired with Memory Parallel, it enables high-throughput processing for 100M tokens under practical deployment constraints, such as a single 2×A800 GPU node. 3，We present Memory Interleave, an adaptive mechanism that facilitates complex multi-hop reasoning. By iteratively synchronizing and integrating KV cache across scattered context segments, MSA preserves cross-document dependencies and enables robust long-range evidence integration. 4，Comprehensive evaluations on long-context QA and Needle-In-A-Haystack benchmarks demonstrate that MSA significantly outperforms frontier LLMs, state-of-the-art RAG systems and leading memory agents. Welcome to feedback: We are looking for passionate talents to join our team! If you are interested in our work and vision, please don't hesitate to send us an email at evermind@shanda.com.

Memory Genesis Competition 2026 is in last call — submissions close on March 15. You're also welcome to join us on April 4 at the Computer History Museum for an in-person gathering and high-signal conversations with the EverMind core team and leaders across OpenAI, AWS, research institutes, open-source communities, and the investment world. Guess who will you meet? Follow the competition website for the latest updates: #AIMemory# #AgentMemory# #EverMemOS# #AgenticAI# #Hackathon# #Developers# #AIInfra#

We hit 2000 GitHub Stars today. Huge thanks to our amazing community for your support and contributions. Exciting updates are on the horizon, stay tuned. Shoutout to @scastiel for creating this awesome GitHub Star animation.

🚀 Excited to announce the release of our latest research on EverMemOS, now available on arXiv! As Large Language Models (LLMs) transition from simple conversational tools to long-term interactive agents, they face a critical "cognitive wall": limited context windows and fragmented memory. To bridge this gap, we introduced EverMemOS—a self-organizing memory operating system that transforms isolated interaction fragments into a structured, evolving "digital brain". By implementing an engram-inspired lifecycle—covering Episodic Trace Formation, Semantic Consolidation, and Reconstructive Recollection—EverMemOS doesn't just store data; it organizes experience. We are thrilled to report that EverMemOS has achieved State-of-the-Art (SOTA) results across four major long-term memory benchmarks: LoCoMo: Outperformed all existing memory systems and even full-context large models, while using drastically fewer tokens (93.05% overall accuracy). LongMemEval: Achieved a leading 83.00% accuracy, showing particularly strong gains in Knowledge Updates and temporal reasoning. HaluMem: Set a new standard for memory integrity and accuracy (90.04% recall). PersonaMem v2: Demonstrated superior performance in deep personalization and behavioral consistency across diverse scenarios. These results validate our belief that the future of AI lies in structured memory organization rather than just expanding context windows. Special thanks to the amazing team at EverMind Shanda Group for their hard work on this milestone! Check out the full paper on arXiv: Explore our code on GitHub: #AI# #LongTermMemory# #LLM# #MachineLearning# #EverMemOS# #AIInfra# #SOTA#

My recent experience writing articles and patents has made it increasingly clear: in the realm of pure text synthesis and expression, Large Language Models have already surpassed humans. In the future, a person’s value will lie in being a mentor who breathes "soul" into AI. Our sole task is to provide the thinking frameworks, viewpoints, and preferences. This is not because AI is inferior in these logical areas, but because it is only by adding these "personalized biases" that we remain imperfect yet valuable independent individuals. It ensures our output is not just a perfect but homogenized template. The real question is: Do we have thinking frameworks, core viewpoints, and personalized preferences worth outputting?

Most AI Agent applications today have zero moat. 🚫 They face two major threats: intense homogeneous competition from peers, and the constant erosion of value by foundational models. A whole year of technical progress and UX refinement can be rendered obsolete by a single base model update. So, where does the future of Agents lie? 🧵👇 Let's look at internet history. The two truly dominant commercial AI ecosystems—Search and Recommendation Systems—succeeded for one reason: User Feedback Loops. 🔄 User interactions continuously improved the system, creating a virtuous cycle and an insurmountable first-mover advantage. That was their moat. The future of AI Agents requires the exact same dynamic. The only way to build real defensibility is through user data feedback. If your agent isn't learning from its users, it’s just a commodity waiting to be replaced by the next GPT update. You need data gravity. 🛡️ To build this barrier and increase switching costs, agents must leverage user history. The goal is simple: "The more you use it, the better it gets, and the more it understands you." This is the critical function of a Memory System. 🧠 Our thesis: In the future, every application must have a memory system. Apps that successfully integrate memory will define the next generation of commercial ecosystems. They will win through superior, personalized experiences and undeniable data moats. 🚀