vecRecall

VecRecall 是一个进化版的 AI 长期记忆系统, v2.0 在纯向量检索之上,叠加 LLM 认知层(写入时自动抽取实体/关系/摘要/话题 + 语义去重)、时序知识图谱、遗忘曲线与主动蒸馏、多跳向量+图谱混合检索与静态加密,并把嵌入升级为「零依赖 subword 词法 + 多语言语义模型」双层。内置可复现评测集(21 组中英混合 query)中,召回率(R@5)达到 语义嵌入 100% / 零依赖词法 76.2%,为 AI Agent 提供更精准、更高效的上下文记忆支持。

Description supplied by the publisher; it is a claim, not verified evidence.

Name
github:snowfoxHQ/vecRecall
Listed in
GitHub
Publisher
@snowfoxhq
Published
2026-10-08
License
MIT
Evidence
Listed only, not analyzed yet

Source: https://github.com/snowfoxhq/vecrecall

What a full analysis of vecRecall checks

Not checked yet. About 60 tools are analyzed every hour; each check links to its source when it runs:

Before you install it

  1. Open the repository and confirm the account is the one you expect: look-alike names are common.
  2. Read what it asks for: files, accounts, network access and credentials it needs.
  3. Prefer a version from a verified publisher when one exists.

Search the catalog · How UND Assay checks tools