EverOS
EverMind-AI
One portable memory layer for every AI agent: local-first, Markdown-native, user-owned, and self-evolving across apps, tools, and workflows.
REVIEW SCORECARD
✓ 无Risky检出 · 自动化扫描结果仅供参考,非官方背书
AI DEEP REVIEW
A mature, actively maintained cross-platform memory layer for AI agents with strong docs and a clean Markdown-plus-Milvu
README shows a CI test workflow badge, PyPI packaging, a documented Python API and CLI, and a modular plugin layout across five platforms, indicating solid engineering rigor.
Install is a standard package-manager command with no download-and-execute shell piping, but the Codex path clones and runs an install script and requires `codex --yolo` for ONNX model network access, which warrants mild caution.
Persistent cross-agent semantic memory with hybrid search, dedup, and live sync addresses a real and common pain point for users juggling multiple coding agents.
Last updated 2026-08-23, not archived, 2515 stars, and a 'What's New' section listing recent DSH support and skill distillation show active development.
README provides per-platform install steps, verification commands, recall examples, and links to dedicated docs sites, though the excerpt is truncated mid-Codex section.
Generated by AI after reading the project README, as a decision aid; neutral scores are given when information is thin. Not an official endorsement.
正在读取 GitHub README...
README 暂时无法读取。
前往仓库INSTALL REFERENCE
dsh plugin --profile web add @zilliz/memsearch-dshThis command passed the install-plan safety check and can be executed by a DSH host; verification status is not equivalent to a security audit or official背书。
PROJECT TOPICS
VALIDATION LADDER
FAQ
A persistent, unified memory layer for all your AI agents (e.g. Claude Code, Codex, DSH), backed by Markdown and Milvus.
memsearch has 2,515 stars and 235 forks on GitHub, last updated 2026-08-23.
memsearch is distributed under the MIT license.
memsearch is listed in the DSH Universe directory as a tool for DeepSeek Harness. This plugin is listed in the DSH Universe directory and covered by its validation pipeline.
CLASSIFICATION EVIDENCE
System reads GitHub Topics first, then compares against the in-site category dictionary and word-root rules. Current match:skills、agent-memory、claude-code、claude-code-plugin、embeddings、hybrid-search、long-term-memory、memory、rag、semantic-search。