One portable memory layer for every AI agent: local-first, Markdown-native, user-owned, and self-evolving across apps, tools, and workflows.
$ git clone https://github.com/EverMind-AI/EverOS.gitSelf-evolving memory OS for LLM & AI Agents: ultra-persistent memory, hybrid-retrieval, and cross-task skill reuse, with 35.24% token savings and DeepSeek Harness support.
▲ +11 ★ this week
The memory that dreams — long-term memory for AI agents. Readable files on your own machine, consolidated between sessions. Runs as a DeepSeek Harness plugin or over MCP.
Memory for AI that works like yours—local, instant, persistent. 13x faster than Pinecone, 5x leaner than RAG. Finds what RAG misses. Zero cloud, zero cost.
Recent memories stay detailed. Older ones grow concise. Important ones live on.近期记忆保持详细，旧记忆逐渐精简，重要记忆长期存在。
▲ +46 ★ this week
A persistent, unified memory layer for all your AI agents (e.g. Claude Code, Codex, DSH), backed by Markdown and Milvus.
▲ +5 ★ this week
Open-source infrastructure that turns scattered SKILL.md files into curated, retrieval-ready agent-skill corpora—with retrieval and evaluation tooling included.
Data from GitHub · snapshot Nov 13, 2026