Audit each finished assistant turn with an independent reviewer model and steer the agent to fix failed output, with at most 2 review rounds per turn.
dsh plugin add CAI-MH/dsh-quality-review
Reviewed DeepSeek Harness extensions — filter by category, search by capability, and jump straight to each plugin's public source.
Audit each finished assistant turn with an independent reviewer model and steer the agent to fix failed output, with at most 2 review rounds per turn.
dsh plugin add CAI-MH/dsh-quality-review
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.
dsh plugin add FuRongJun-1999/dsh-memory
Evidence-driven goal verification plugin for DeepSeek Harness. Locks goals via /ultragoal and verifies completion against command exit codes and generated artifacts, preventing the model from falsely reporting task completion.
dsh plugin add Jonah-Wu23/dsh-gungnir#dsh-plugin
Filter by category or keyword — every listing is a public GitHub project.
Commands follow the upstream list; check each repo's README for exact package names.
Plugins run third-party code with your permissions — read the source first.
This directory is a snapshot of the community-maintained awesome-dsh-plugin list (updated 2026-09-07). Listings link to the authors' repositories; inclusion is not an endorsement or a security review. Missing a plugin? Contribute to the upstream list.