EverMind

Self-evolving memory across Agent and platform.

[EverMind @evermind]

We are honored to announce that two papers from the EverMind research team have been selected for oral presentation at KDD 2026, Datasets and Benchmarks Track.

Of 466 submissions to the track, only 21 papers (approximately 4.5%) received this distinction.

• Evaluating Long-Horizon Memory for Multi-Party Collaborative Dialogues
• MPCEval: A Benchmark for Multi-Party Conversation Generation

Memory for multi-party collaboration is one of the hardest open problems in AI. Our EverMemBench benchmark spans million-token, multi-user, multi-group conversations with interleaved topics and evolving facts. The findings are striking: even with oracle evidence, today's leading memory systems achieve only 26% accuracy on multi-hop reasoning that requires attributing information across participants.

We congratulate the authors and thank the community for recognizing this work. We look forward to presenting at KDD 2026.

Paper: https://t.co/vsi95PpOMv

[七仔 @Yangtze_Seventh]

https://t.co/RDJJZCxKU4

[EverMind @evermind]

@Rj_Lopez_ Coming soon. We shall see. 😏

[EverMind @evermind]

EverOS 1.0.0 is now available.

EverOS is an open-source, local-first memory runtime for AI agents, designed around one principle:

Agent memory should be readable, portable, and owned by the user.

In EverOS, Markdown is the source of truth.

[EverMind @evermind]

@itsshara_ai 👀
https://t.co/DN3e8kNnEE

[EverMind @evermind]

EverOS just had its fastest 30-day run ever.

+2,700 GitHub stars, 7,000+ total, and EverOS 1.0.0 is now out.

The growth followed a wave of practical agent memory use cases.

Not just stars. Workflow demand.

https://t.co/wyiBLYBjG7

[EverMind @evermind]

11/

This is the first release of a larger roadmap.

Next: Wiki-style knowledge layers and Dreaming for deeper offline evolution.

If you believe agent memory should be transparent, portable, and yours, EverOS 1.0.0 is ready.

https://t.co/wyiBLYBjG7

[EverMind @evermind]

10/

EverOS is part of the broader EverMind open-source ecosystem:

EverAlgo for memory algorithms.
HyperMem for hypergraph memory.
EverMemBench and EvoAgentBench for evaluation.
MSA for 100M-token context research.
EverMe for cross-device personal memory.

[EverMind @evermind]

EverMe doesn’t have an official Codex plugin yet.

But someone in the community already built a local one for their own workflow and sent us a screenshot.

That made our day.

It’s a small signal, but a meaningful one: people want memory to show up where they already work.

More EverMe updates coming soon.

[EverMind @evermind]

Introducing EverMe, a personal memory hub for your AI agents.

With one instruction, your agents can work on top of the same memory across sessions, tools, and workflows.

EverMe makes memory visible, traceable, editable, and portable. It helps agents turn conversations into experience, experience into cases, and cases into reusable skills.

Free to use for now.

https://t.co/4SddPL0ljy

[EverMind @evermind]

@anjanab_ Thank you.

[EverMind @evermind]

https://t.co/wyiBLYBjG7

[EverMind @evermind]

EverOS passed 6,000 stars on GitHub today.

This milestone means a lot to our team. We’ve put serious work into building an open home for long-term and self-evolving memory in agents: real use cases, runnable methods, benchmarks, and tools developers can build on.

If you believe agents need memory to become truly useful, we’d love your support.