Self-evolving Context Database for AI Agents. Unify Agent Memory, Knowledge RAG and Skills.
View plugin → 
volcengine
dsh-memento
Bounded, layered, approval-gated, auditable cross-session memory for DeepSeek Harness (capability seam: ctx.memory + SQLite provider + memory tool + frozen snapshot injection)
Plugin facts
GitHub stars 124
LicenseApache-2.0
Primary languageJavaScript
Last push2026-09-25T01:35:00Z
MaintainerPerryLink
Added to this directory2026-09-26
Screenshots
About this plugin
Bounded, layered, approval-gated, auditable cross-session memory for DeepSeek Harness (capability seam: ctx.memory + SQLite provider + memory tool + frozen snapshot injection)
Install this DSH plugin
Copy the command below and run it in your DeepSeek Harness terminal.
dsh plugin add github:PerryLink/dsh-memento Plugins run with the permissions of your dsh process and may execute code at install time. Review the source repository and its license before installing. Pin the commit hash for reproducible installs. Plugin safety →
Related guides
Learn how to choose, install, and use memory plugins.
About this plugin: dsh-memento
What is dsh-memento?
dsh-memento is a memory plugin maintained by PerryLink. Bounded, layered, approval-gated, auditable cross-session memory for DeepSeek Harness (capability seam: ctx.memory + SQLite provider + memory tool + frozen snapshot injection)
How do I install dsh-memento?
Run dsh plugin add github:PerryLink/dsh-memento in your DeepSeek Harness terminal. The dsh CLI resolves the plugin from GitHub and installs it into your active profile. For reproducible installs, pin a commit hash: dsh plugin add github:PerryLink/dsh-memento#commit.
Is dsh-memento free?
dsh-memento is a community open-source project released under the Apache-2.0 license. You can inspect its source and install it for free.
Related plugins
Open-source LLM knowledge platform: turn raw documents into a queryable RAG, an autonomous reasoning agent, and a self-maintaining Wiki.
View plugin → 
Tencent
Self-evolving memory OS for LLM & AI Agents: ultra-persistent memory, hybrid-retrieval, and cross-task skill reuse, with 35.24% token savings and DeepSeek Harness support.
View plugin → 
MemTensor