Sophia (Yunyun Han)

Agent Memory: A Real-World Use Case on Rokid AI Glasses Your next conversation with your AI glasses shouldn’t start from zero. A community builder has brought EverOS Cloud to @RokidGlobal glasses, giving a wearable assistant a memory that carries across conversations. As you use it, saved details and preferences can help it respond with more relevant context, without making you explain everything again. We love seeing our community bring long-term memory into everyday life, on devices you can actually wear. Build something of your own. Subscribe to EverOS Cloud Pro now and get 3× the standard monthly usage for your first 6 months. everos.evermind.ai

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:discord.gg/VVSm8MESch). More in the video and slides below. Open source, Apache-2.0. github.com/EverMind-AI/Raven (lots of work made with Raven lives there, and much of this launch's material was made with Raven too)

Day 91 — 🥉 3rd Prize + Paid User at @Snowflake × @UofBeta × @evermind Hackathon At the @VoiceOSApp (YC P25) × @a1mobile hackathon, I briefly met Samvrith Bandi. I think we talked for maybe 2 minutes. But I remember thinking: “I want this guy on my team for the next hackathon.” So right there, we found another hackathon, signed up, and just like that, I had my first teammate. When I got to today’s hackathon, I started looking for more people. I always try to go for the max team size. I know quite a few builders now, but I also love finding people I don’t know yet. Especially first-time hackathon people. I have a strangely high success rate with first-time hackathon teammates. There is a reason my shirt says: “First time at a hackathon? Please join me.” Then I met Isha Singh . This time, I actually asked her if she wanted to join the team. Not my usual style, lol. Usually I just say: “You are in my team.” Then I met Rikin Shah, CSM®, FOCP AI on the spot too, and he became part of the team. So that was the team: Sam, Isha, Rikin, and me. Then we started building. Sam did not disappoint at all. We divided the work, and his part was basically: “Build the app.” Not a small task. He single-handedly built a better app than I expected. Not only did he build it, but he also made it work. I already had a feeling he was a GOAT. He proved it. BOY IS KILLING AT 18. ASK ME WHAT I WAS DOING, LEARNING HOW TO USE A MOUSE IN 12TH CLASS. Isha killed every task I gave her. Near the end, we needed to integrate YouTube. None of us had done it before. She figured it out in around 20 minutes. And this was her first hackathon. Not bad for a first one 😄 Ask me — I lost quite a bit before winning one. What stood out about Rikin was his ability to handle pressure. He kept up with the pace. He stayed objective. He did not bring ego into the room. That matters a lot. In hackathons, pressure exposes people quickly. Some people freeze. Some people argue. Some people drift. Rikin stayed locked in and helped put everything together until the last moment. That is rare. We ended up winning 3rd prize. And even better, we got a paid user. That part matters to me because it means the idea was not just interesting to judges. Someone actually saw value in it. Huge thanks to Samvrith Bandi, Isha Singh and Rikin Shah, CSM®, FOCP AI for trusting the process and building hard with me. Hackathons keep reminding me: You don’t always need a team before you arrive. Sometimes you just need to recognize hungry people quickly. Give them trust. Give them ownership. And then run together. @Snowflake @UofBeta @evermind

Our new paper. Self-evolving agents have a measurement problem. The hard part isn’t generating changes to an agent harness. It’s knowing which changes genuinely helped rather than got lucky, overfit, or never activated at all. LLMs diagnose failures and propose changes across prompts, knowledge, runtime, tools, and configuration. But deterministic code owns the credit: validity checks, activation checks, paired significance testing, and a sealed test. Across 7 domains, the evolved harnesses gained +9.0 to +15.5pp on the 6 statistically credited sealed tests, retaining 86–147% of the training gain. What transfers is not one universal harness. It’s the diagnose-and-credit loop. arxiv.org/abs/2607.13683

Meet EverMind Skill Hub, a measured capability layer for AI agents. We aggregated 800K+ raw SKILL.md files and curated them into 96,401 license-audited, OSI-compliant skills. Then we built purpose-trained matching and tested the result across four real-world benchmarks, delivering statistically significant gains on every one. Search by task, inspect the source and quality signals, then install or adapt your own version. In Raven, the loop continues: EverOS preserves what works, while SkillForge turns repeated workflows and feedback into evolving local skills. Agents don’t need another directory full of skills. They need the right capability, at the right moment, with evidence that it works. evermind.ai/skillhub

What it learns, it keeps. What it doesn’t know, it pursues. EverOS gives Raven continuity across every run. MiroThinker gives it the depth to search, verify, and go beyond the first answer. Persistent memory meets deep research. One Raven 🐦‍⬛. @EverMind × @miromind_ai

From research result to research infrastructure. @Xiaomi new Mi-Memory paper evaluates its memory stack across LoCoMo, LongMemEval, and PersonaMem-V2 using the EverMemOS evaluation harness, with our paper EverMemOS included as a named reference system. Proud to see our work helping set the standard for how long-term AI memory is evaluated. arxiv.org/pdf/2607.18975

Most agent observability stops at the model layer. EverOS lets you observe the memory layer in @langfuse too: - what got stored - what got recalled - recall confidence - token cost across extraction, search, and reflection The example is open in our repo and runnable in minutes. Docs: langfuse.com/integrations/ot… Code: github.com/EverMind-AI/EverO…

M3 brings long-context reasoning, while Raven adds the durable memory and reusable skills that help work compound across runs. Excited to see MiniMax integrated into @evermind Raven 🐦‍⬛ Let us know what you build with it.

We’re excited to bring @MiniMax_AI to Raven 🐦‍⬛ as a first-class model option. MiniMax powers the model. Raven makes that intelligence compound across runs. Built on EverOS, Raven is a memory-first, self-improving agent harness. It gives models durable user and agent memory, actively manages context during long-running work, follows up proactively through Sentinel, and turns successful workflows into reusable skills that improve with feedback. Paired with MiniMax’s long-context capabilities, agentic reasoning, coding performance, and tool use, Raven can take on longer, more complex workflow, from deep research and coding to automation and persistent digital workers. Try Raven × MiniMax and let us know what you build. github.com/EverMind-AI/Raven Get 12% off MiniMax API plans through our dedicated links:

The ancient Greek philosopher Protagoras said: "Man is the measure of all things." At an event yesterday, I shared how EverMind is trying to build that measure from the human vantage point — by constructing a generalized memory, and bringing memory and reasoning together, to work out a framework for how individuals and organizations perceive the world, along an axis orthogonal to LLMs' general intelligence. Today we're shipping Raven v0.1.5 (thanks to the community for the Raven artwork!) — our first release where in-house deep research is deeply fused with the harness. Come feel a deep intelligence that's truly yours, built for long-horizon tasks. Try it here: github.com/EverMind-AI/Raven More big things coming soon.

自从 EverOS 1.0.0 发布之后，Markdown-first，Wiki 和 Reflection 等新功能大家都很喜欢。 开源生态也越来越好，线上和线下都有不少想合作的朋友，我们乐意得很。 这不，上周刚见过 @yinmin1987 和 @JackLi567 两位彦祖，这马上就和 @milvusio 达成合作，这速度有点快。 开源生态就是这么好玩。✌️ github.com/EverMind-AI/EverO…

EverMe × Kimi Code @Kimi_Moonshot @KimiDevs Kimi Code now has shared memory. Connect Kimi Code to EverMe Memory with one prompt, carry context across sessions, agents, machines, and operating systems, and turn what it learns into reusable Skills. Less cold start. More continuity. EverMe: evermind.ai/everme Kimi Code: kimi.com/code/zh?track_id=5f…