Out-of-tree dsh provider plugin: a DeepSeek gateway route that claims image input and transparently describes pasted images through a configured vision-language model (e.g. Qwen-VL) before the text-only DeepSeek wire sees them.
DSH plugin shell for dsh-feishu-bridge: spawns and supervises the Feishu (Lark) channel bridge's Python process as a managed child of the DSH Host. The bridge itself is unchanged Python — this package only adds the dsh.bundle install path.
Agent collaboration · Integrations
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:wz-heng/dsh-feishu-bridge
Gungnir Adaptive Loop Runtime — a drop-in replacement driver for the DSH default agent loop. Lock the goal. Adapt the loop. Prove the hit. (ADR-0012; internal package name @gungnir/agent-loop, npm release name candidate dsh-gungnir-loop.)
Agent collaboration
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:Jonah-Wu23/dsh-gungnir#7857cf4a4744235a5ea2393e069590e5d6222344&path:packages/agent-loop
Design document & plan claim verification — enumerate claims, verify against codebase facts, then escalate to state-machine verification (S1-S8/A1-A12, including budget/worst-case path-cost checks) and data-model verification (DS/DA/DD) for behavioral claims. Supports before/after regression, idempotency/monotonic/sequence/leads-to/atomicity constraints, and concurrency risk mining. Ships a native DeepSeek Harness (dsh) bundle that injects the claim-verification gate into the first model step.
Skills · Agent collaboration · Financial data · Developer tools
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:AmethystLuna/logicprobe
Global proxy for DeepSeek Harness: route agent tools, model requests and web fetches through the Windows system proxy or a custom proxy with one persistent toggle, an editable settings card, agent-visible status and a bypass-aware prompt section
Agent collaboration
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:LucienLL/dsh-plugin-proxy
Native DeepSeek Harness tools for an Obsidian wiki vault: wiki_query, wiki_write, and wiki_lint implement the mechanical core (path routing, delta tracking, index/log bookkeeping, health checks) of the wiki skill suite.
Memory and knowledge · Skills · Agent collaboration
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:Lion-1209/dsh-plugin-wiki-tools
A reproducible science workbench plugin for the DeepSeek Harness: agent-driven cells, inline figures with feedback/rerun, manifest provenance, and environment snapshots.
Agent collaboration
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:poplarity/dsh-science-workbench
Manage DeepSeek Harness sessions from the Web UI: drag & drop or menu-move a session to another folder (workspace), permanently delete a session, and AI-rename a session by summarizing its conversation. Also exposes agent tools for each operation.
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:baosfeng/my-dsh-plugins#cc837f22ecaa841de7d263346073dc44c55d50ee&path:plugins/dsh-task-reliability
Find the right plugin, then get started
Search by task
Use a feature keyword or category, then sort by recent updates or GitHub stars.
Explore capabilities
Read the description, AI analysis and original README to understand what a plugin does.
Check and install
Review compatibility, dependency ranges and instructions, then copy the available install command.
Questions about DSH Hub
What is DSH Hub?
DSH Hub is a community plugin directory for DeepSeek Harness, bringing together descriptions, source links and installation instructions to help you discover and compare extensions.
Does inclusion mean a plugin is tested and compatible?
No. Detail pages show recorded compatibility and dependency ranges. Unknown does not mean compatible; check the project documentation before installing.
How do I install a plugin?
Open its detail page and check the installation section. Copy the command into your Harness environment when available, or follow the project README.