Skip to main content

沙漏记忆系统 — 纯本地零依赖L3思考层

Project description

NexSandglass ⏳ — 沙漏记忆系统

pip install nexsandglass · 纯本地 · 零依赖 · 零 API Key

PyPI Python License


不是记住你说过什么——是理解你怎么变成今天的你。

投石问路 + 影子沙双引擎搜索 · 偏移率感知 · 管道聚合画像 · 四层问答式极简注入。纯本地,零依赖,越用越懂你。

特性 说明
🔍 四路并发搜索 影子沙 + FTS5 + IDX + TF-IDF,毫秒级响应
🧬 偏移率追踪 省钱/愿投/放弃 三维量化 + 决策疲劳检测
🎭 管道聚合画像 fact_tags + decision_particles → 越用越懂你
💉 极简注入 ~60 tokens,LLM 一眼看懂
🔒 全本地 数据不出设备,OS 层全盘加密
🚀 一键安装 pip install nexsandglass

快速开始

pip install nexsandglass
from sandglass_vault import search, count
from sandglass_log import log_message

log_message("今天讨论了搜索排序优化", "user")
print(search("搜索排序"))  # 毫秒级返回
print(f"沙漏总量: {count()}条")

Hermes 用户:

hermes plugins install lovevin1314-tech/NexSandglass
# 重启 Desktop → 设置 → 记忆体 → 选择 NexSandglass

与现有方案对比

维度 Mem0 / Letta NexSandglass
依赖 向量数据库+N个包 零依赖,纯 stdlib
注入量 ~200-22000t ~60t
决策追踪 决策粒子+偏移率+心理预判
情绪感知 情绪熵(会话级摘要)
画像溯源 可追溯到行号
搜索 向量检索 四路并发(影子沙+FTS5+IDX+TF-IDF)
安装 服务栈 pip install

版本历程

V2.10 — PyPI 发布

pip install nexsandglass — 全球 AI Agent 一键安装。两段式轮次注入(60t),DB 自省增量启动,沙子自愈。

V2.9 — 极简注入 + 纯本地化

四路并发搜索 + 管道聚合画像 + 去 LLM 全链路闭环。偏移率·纠结度·铁律因子·Porter Stemmer。

V1.x — 奠基

偏移率·情绪感知·决策粒子·影子沙·织布机·场景系统


设计原则

  1. 层追加不替换 — 新层叠加,永不修改下层
  2. 纯本地 — Python stdlib + SQLite,零外部依赖
  3. 极简注入 — 每轮 ~60t,LLM 按需搜索
  4. 越用越懂你 — 管道数据随沙子自然积累

性能基准

操作 median
L1 写 单次落沙 4.3ms
L2 搜 FTS5搜索 1.6ms
影子沙 0.7ms
L3 思 偏移率 <0.1ms
铁律因子 <0.1ms

测试:5900条 · Windows 10 · i5-8265U · Python 3.11

Project details


Download files

Download the file for your platform. If you're not sure which to choose, learn more about installing packages.

Source Distribution

nexsandglass-2.10.3.tar.gz (133.1 kB view details)

Uploaded Source

Built Distribution

If you're not sure about the file name format, learn more about wheel file names.

nexsandglass-2.10.3-py3-none-any.whl (152.8 kB view details)

Uploaded Python 3

File details

Details for the file nexsandglass-2.10.3.tar.gz.

File metadata

  • Download URL: nexsandglass-2.10.3.tar.gz
  • Upload date:
  • Size: 133.1 kB
  • Tags: Source
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/6.2.0 CPython/3.11.15

File hashes

Hashes for nexsandglass-2.10.3.tar.gz
Algorithm Hash digest
SHA256 f21893fda8ce58f3cde18b7df331007c7928d8ba377d3cdb3695fa5961b584ed
MD5 8ce2f865059583a2348c116ad34af0a2
BLAKE2b-256 632ff6fea2fb4c141de80c018ecaae78421992c089ca2d60d758c1e0e11a6f04

See more details on using hashes here.

File details

Details for the file nexsandglass-2.10.3-py3-none-any.whl.

File metadata

  • Download URL: nexsandglass-2.10.3-py3-none-any.whl
  • Upload date:
  • Size: 152.8 kB
  • Tags: Python 3
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/6.2.0 CPython/3.11.15

File hashes

Hashes for nexsandglass-2.10.3-py3-none-any.whl
Algorithm Hash digest
SHA256 81315aca107a1d00a2f21f0be5530d1bd6dc2de4b22a086b864273742e91146c
MD5 29306192178d886dc0b18769041e136d
BLAKE2b-256 22d725603f8b375f23cd4674c0351442e9d17da1008dd8b1ddd90fc2eab68c67

See more details on using hashes here.

Supported by

AWS Cloud computing and Security Sponsor Datadog Monitoring Depot Continuous Integration Fastly CDN Google Download Analytics Pingdom Monitoring Sentry Error logging StatusPage Status page