
A unified agent memory workspace for human and agent
Install Sivtr
Installs but activates nothing: package.json has no `dsh.bundle` declaration, so `dsh plugin` warns and loads no config layer.
This repository is not a DSH plugin
package.json declares no dsh.bundle. In the official docs' own words, a package like this “still installs, but only as a plain dependency: dsh plugin prints a warning and activates no layer”. The install looks like it worked and nothing happens.What it actually is: A unified agent memory workspace for human and agent If that is what you came for, use it directly from the repository — it is just not something dsh plugin add can activate.
Before you run it
- A plugin runs with your permissions once loaded: it can read your files, use your credentials and reach the network. Tool approvals do not sandbox it.
- Installing from git resolves a moving branch. Pin a commit —
github:Ariestar/sivtr#<commit-sha>— so the code you reviewed is the code you install.
Prerequisites
- API key
- Not required.
- Network access
- Not required at runtime.
- Language
- Rust
Install check
Every field the verdict was derived from, so you can re-derive it yourself
| Field checked | Result | Weight | What the spec says about it |
|---|---|---|---|
| lifecycleScripts | pass | info | no install-time scripts |
| dsh.bundle | missing | fatal | package.json has no `dsh.bundle` key |
- Verdict reason
- no dsh.bundle declaration — installs as a plain dependency only
- package.json read
- docs-site/package.json
- Rules applied from
- docs/user/develop/basic/publish.md
- Checked at
- 2026-08-15
From the README
Excerpt as published by the author, plain text, unedited
一个面向智能体和人的统一的记忆空间 让智能体和终端共享同一个上下文 · · · 开发者和 Agent 经常浪费时间重建已经存在的上下文:终端报错、测试输出、工具日志、之前的 AI 会话。`sivtr` 把这些本地工作变成可搜索的记忆,但不要求你引入一套很重的知识系统。 有了 `sivtr`,你可以: - 让 Agent 修复最近一次失败,而不用自己粘贴日志; - 几秒钟找回昨天的测试输出、构建报错或关键决策; - 从摘要跳回当时那条命令输出或 Agent 回复; - 把一组有用结果保存成 `@failures` 这样的变量,在下一条命令里继续用。 > [!IMPORTANT] > Agent 工作流建议安装 `sivtr` CLI,用 `sivtr mcp install` 注册 MCP,并可选用内置 `sivtr-memory` skill。MCP 是 Agent 读取本地证据的主路径;skill 负责教它何时、如何调用。 - **MCP 优先的 Agent 记忆**:一次 `sivtr mcp install`,Agent 直接调用 `sivtr_search` / `sivtr_show` / `sivtr_zoom` / `sivtr_filter` / `sivtr_status`,不用你粘贴日志。 - **带输出的 shell history**:记录 Bash、Zsh、PowerShell、Nushell 里的命令、stdout/stderr、退出码、目录和耗时。 - **一个搜索面覆盖本地工作**:终端输出 + 所有已注册 Agent provider(Codex / Claude Code / Cursor / Hermes / OpenCode / OpenClaw / Grok / Pi …)——MCP 或 CLI 都能用。 - **精确证据,而不是摘
Topics
GitHub topics on this repository
More in Cli Codex Agent Automated
Ranked by similarity inside the cluster, not alphabetically
Dsh Whale Report
SenmuuuuW
🐋 鲸鱼记事本 — 你的 Agent 年度报告:从会话事件日志生成日报/周报/月报/年报,任意区间、只读不改写
Deepseek Harness Learning
Lucky2024-pllove
基于 deepseek-harness 仓库系统化拆解产物搭建的学习网站,面向想了解「AI Agent 框架如何工作」的开发者与爱好者。
DSH Novel
KurohaneKaoruko
一个Agent。让DeepSeek Herness变成AI写小说的工作区。这个项目也是DSH写的。
Pack Agent
sakikoTGW
Agent Modpack — 像装 MC 整合包一样,装你的 agent。
Deepseek Harness
d-wwei
DeepSeek Harness / Agent V1.0 提案
Learn Deepseek Harness
qinchen1314
项目旨在学习deepseek新出的harness,为agent开发扩展新的视野,具有前端可视化