DSH Marketplace
中文

The catalogue

Agents & AGI

Synced from the community registry and the dsh-plugin GitHub topic. Star counts and last-push dates come straight from GitHub.

1 plugin

99% install-verified

SortStarsUpdatedNewA–Z

dsh-memory

FuRongJun-1999

29

White-box AGI architecture exploration: metacognition (self-cognition loop), continual learning (knowledge flywheel), world model (condition space, spatiotemporal memory graph), self-improvement (bootstrap discipline), zero-LLM white-box pipeline, and auditable trust guardrails.

Installed cleanly when we ran it

npm packageTypeScript9d ago

AI review

dsh-memory

What it is — This plugin provides AGI long-term memory infrastructure for DeepSeek Harness agents.

Who it is for — It is suitable for multi-agent cross-session scenarios where DeepSeek Harness agents need self-continuity. Users who have simple memory needs can skip it because it is not a simple memory plugin but an AGI long-term memory infrastructure.

Watch out — Sandbox test passed: it was installed in a new profile and registered into the profile by harness. No obvious issues found. The Python subprocess runs without issues.

The verdict — I would install it because it provides auditable trust guardrails that help maintain behavior boundaries in long-term interactions.

Generated by grok-4.6, and a starting point rather than a verdict. Where it says a plugin installs or does not, that is from a real run in a clean profile — everything else is read off the repository. Trust the source over this.Read the source
1Source