Meet EverMe for Chrome.
Turn your ChatGPT, Claude, and Gemini conversations into memory you can keep and reuse.
The preferences you’ve shared. The projects you’re working on. The context you’ve spent time explaining.
Keep chatting as usual. EverMe syncs completed
EverOS 1.3.0 is out.
You can now use @milvusio or Zilliz Cloud to index your agent’s memory.
LanceDB remains the default. Markdown remains the source of truth.
Switching backends means rebuilding the index from your memory files.
Already running Milvus? EverOS now fits into
Our CEO, Yafeng Deng, joined INCLUSION · Conference on the Bund to share EverMind’s work on memory and agent self-evolution.
The talk explored the whole agent, rather than the LLM alone, as a possible analogy for the human brain, and the prospect of building a trainable agent
From 8,594 tokens to 1,946 per answer.
EverOS selects the memories a question actually needs instead of injecting a fixed 20 every time.
In our LongMemEval-S test, that meant 77% fewer answer-stage input tokens, with 91% accuracy versus 93.4%.
Less context to process. Relevant
EverOS 1.3.1 is here.
The multi-round retrieval we just shared is now available in EverOS: let the model decide what evidence to keep, what to search next, and when to stop.
Also in this release:
• One reproducible runner for four memory benchmarks: LoCoMo, LongMemEval,
