No red flags found in any of the 11 categories — no credential harvesting, no data exfiltration, no curl-pipe-shell installer. Scanned against the SlowMist agent-security taxonomy, refreshed every 8 hours. Full audit →
by omdsh-dev · Agent Tool · ★ 122
Last updated: · Indexed by AgentSkillsHub · Auto-synced every 8h
🔒 Is dsh-mnemon safe to install? View the security audit →
dsh-mnemon English · 简体中文 Local, layered, supervised memory for DeepSeek Harness—with cross-agent sharing through Mnemon. integrates Mnemon with DeepSeek Harness (DSH). It brings hot memory needed every turn, full project Documents, and on-demand long-term Memory Spaces into one workbench. Other agents can share DSH's long-term memory when they also integrate Mnemon and use the same accessible local Mnemon storage. Local first: memory stays in local SQLite, JSON, and Markdown; no remote memory service is required. Cross-agent sharing: Mnemon-enabled agents can read and reuse DSH's Mnemon Memory Spaces. Three cooperating tiers: Runtime Memory, Project Documents, and Memory Spaces retain information at the right granularity. Supervised writes: isolated memory subagents make semantic decisions; the Host enforces paths, permissions, capacity, locks, and revisions. Native DSH experience: a Sidebar workbench by default, t
| Stars | 122 |
| Forks | 7 |
| Language | TypeScript |
| Category | Agent Tool |
| License | MIT |
| Quality Score | 68.5025210263104/100 |
| Open Issues | 1 |
| Last Updated | 2026-08-19 |
| Created | 2026-08-10 |
| Platforms | browser, node |
| Est. Tokens | ~16k |
These tools work well together with dsh-mnemon for enhanced workflows:
Looking for a dsh-mnemon alternative? If you're comparing dsh-mnemon with other agent tool tools, these 6 projects are the closest alternatives on Agent Skills Hub — ranked by topic overlap, star count, and community traction.
A portable memory protocol for AI agents — load it as standing rules; a curation discipline + reference spec +
LLM-supervised persistent memory for AI agents — graph-based recall, cross-session knowledge, single binary. W
Structural memory for AI coding agents. Bi-temporal graph, MCP-native, zero LLM calls. Cursor · Claude Code ·
Open-source governed, local-first memory control plane for AI agents and teams. arXiv:2608.08253
Give Claude Code photographic memory in ONE portable file. No database, no SQLite, no ChromaDB - just a single
Local-first persistent agentic memory powered by Recursive Memory Harness (RMH). Open source must win.
Explore other popular agent tool tools:
dsh-mnemon is Three-tier memory control plane for DeepSeek Harness: persistent runtime context, searchable project documents, pluggable long-term memory, smart routing, supervised agent workflows, WebUI, and headle. It is categorized as a Agent Tool with 122 GitHub stars.
dsh-mnemon is primarily written in TypeScript. It covers topics such as agent-memory, context-management, cross-session-memory.
You can find installation instructions and usage details in the dsh-mnemon GitHub repository at github.com/omdsh-dev/dsh-mnemon. The project has 122 stars and 7 forks, indicating an active community.
dsh-mnemon is released under the MIT license, making it free to use and modify according to the license terms.
The top alternatives to dsh-mnemon on Agent Skills Hub include engramory, mnemon, memtrace-public. Each offers a different approach to the same problem space — compare them side-by-side by stars, quality score, and community activity.