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
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.
Reliable agent memory depends on observability as much as on model capability.
We welcome MemTrace's contribution to this space, and appreciate the inclusion of EverMemOS alongside other leading memory systems.
Introducing MemTrace: Making LLM Memory Systems Finally Debuggable 🔍🧠
Memory is becoming a core component of AI agents. But today’s memory systems are still a "black box".
When a memory-augmented agent fails, the real error may have happened:
- dozens of turns earlier,
- inside a retrieval step,
- during memory consolidation,
- or from a corrupted update that silently propagates over time.
Existing logs cannot recover these long-range causal chains.
MemTrace changes this.
We introduce the automated tracing framework for LLM memory systems — turning opaque memory pipelines into transparent execution graphs that can be inspected, explored, and diagnosed step by step.
⚡ What MemTrace enables:
🧩 Plug-and-Play Instrumentation
Seamlessly integrates with diverse memory systems (RAG, Mem0, EverMemOS, etc.) without modifying the original architecture.
🧠 Transparent Memory Execution
Transforms opaque memory pipelines into structured execution graphs, making information flow, retrieval, updates, and propagation fully traceable.
🔍 Error Attribution
Pinpoint the exact operation responsible for failure across long-horizon memory execution.
🚨 Benchmark Auditing
While building MemTraceBench, we found that failure attribution in memory systems remains highly challenging — MemTrace still has substantial room for improvement.
We also discovered annotation errors in existing memory benchmarks, revealing broader reliability issues in current memory-agent evaluation.
🔄 Towards Self-Evolving Agents
MemTrace is not only a debugging tool.
Its fine-grained attribution signals can directly drive closed-loop optimization, enabling agents to automatically repair faulty behaviors and continuously evolve from failures.
📈 Using MemTrace-guided optimization, we improve downstream task performance by up to 7.62%.
📖 Paper: https://t.co/48arX35l1m
⌨️ Code (coming soon):
• MemTrace: https://t.co/pm0JLSpLLr
• smartcomment: https://t.co/ieLcwGFHtY
• MemBase: https://t.co/GX1w7ImczE
We believe memory systems need the same thing software engineering once needed:
not bigger models — but observability, tracing, and debugging infrastructure. #MemTrace #LLM #NLP #Agent #Tracing #Debugging
A child remembers a lullaby.
A parent remembers a red ribbon. Time blurs the rest.
Reunite uses AI to find families across the gaps memory leaves behind.
Built by Xiao Ba (Japan), Public Value Award winner at Memory Genesis Competition 2026.
We are proud to co-host the One Person Company Hackathon with Beta Fund, @UofBeta, and Butterbase.
A single day for solo founders and small teams to prototype and ship working products across three tracks: Autonomous GTM, MVP Speed-Run, and Next-Gen Infrastructure.
Participants are welcome to build on any of the 20+ open-source use cases available in our GitHub repository as a starting point.
🧵
We are proud to co-host the One Person Company Hackathon with Beta Fund, @UofBeta, and Butterbase.
A single day for solo founders and small teams to prototype and ship working products across three tracks: Autonomous GTM, MVP Speed-Run, and Next-Gen Infrastructure.
Participants are welcome to build on any of the 20+ open-source use cases available in our GitHub repository as a starting point.
🧵
We are proud to co-host the One Person Company Hackathon with Beta Fund, @UofBeta, and Butterbase.
A single day for solo founders and small teams to prototype and ship working products across three tracks: Autonomous GTM, MVP Speed-Run, and Next-Gen Infrastructure.
Participants are welcome to build on any of the 20+ open-source use cases available in our GitHub repository as a starting point.
🧵
We are proud to co-host the One Person Company Hackathon with Beta Fund, @UofBeta, and Butterbase.
A single day for solo founders and small teams to prototype and ship working products across three tracks: Autonomous GTM, MVP Speed-Run, and Next-Gen Infrastructure.
Participants are welcome to build on any of the 20+ open-source use cases available in our GitHub repository as a starting point.
🧵