Plugin

dsh-memento

PerryLink1443Updated 3d ago

Bounded, layered, approval-gated, auditable cross-session memory: typed ctx.memory seam, zero-dependency SQLite provider, memory tool and frozen snapshot injection, plus the dsh-memory-protocol v1 rehearsal with an adapter registry and a conformance suite.

agent-memory ai-agent ai-agents approval audit cordis deepseek-harness developer-tools dsh dsh-plugin llm memory sqlite 状态持久化

Practical score

86 / 100

Setup

Ready to use

License

Apache-2.0

Language

JavaScript

Install

Quick start

Copy the command, or hand the whole task to your harness agent.

git clone https://github.com/PerryLink/dsh-memento.git

DSH versionDSH 0.2.2-rc.1

Install with your agent

Please install the DeepSeek Harness plugin "dsh-memento" for me. - GitHub repository: PerryLink/dsh-memento (https://github.com/PerryLink/dsh-memento) - Type: a Cordis plugin (installed into a DSH profile) - The plugin declares a DSH version requirement of 0.2…

From the README

A cleaned excerpt from the project's own documentation.

dsh-memento 让模型跨会话记住该记的事，同时每一次写入都过审批门、留审计痕。一个类型安全的 ctx.memory 接缝 + 本地 SQLite 提供方 + memory 工具 + 冻结快照注入：别的记忆插件卖仓库，这个插件卖接缝、写审批门与会话可重建的审计。安装 · 配置 · FAQ · 简体中文 · English · Español · Português · हिन्दी [ ](https://github.com/PerryLink/dsh-mem…

Open on GitHub

Project details

Repository: PerryLink/dsh-memento
by: PerryLink
License: Apache-2.0
stars: 144
Forks: 3
Updated: Nov 9, 2026
Created: Aug 13, 2026
Language: JavaScript
Indexed from: awesome-0xsline · topic

Visit homepage

Related entries

Similar tools from the same corner of the ecosystem.

View all

Plugin

dsh-auto-review

PerryLink

Second-model AI auto-review on the approval answerer chain: a read-only reviewer subagent returns structured allow/deny verdicts with reasons, fail-closed by default.

ai-agentai-agentsai-safety

248Needs setup

83/100

Plugin

dsh-research-report

PerryLink

Verifiable research-report engine for DeepSeek Harness: content-addressed evidence ledger (claim-to-snapshot binding, tamper-evident) and versioned sealed reports with per-claim verification verdicts and a manifest SHA-256 seal.

ai-agentai-agentsaudit

213Ready to use

86/100

Plugin

dsh-permission-rules

PerryLink

Declarative allow/deny/ask permission rules on the tools/pre-execute waterfall: tool/argument/path/agent matching, session-log audit, dry-run mode, hot reload.

ai-agentai-agentsai-safety

136Ready to use

86/100