AI Agent Hub

DeepSeek Harness Plugins · Model Inference

Plugins that extend DeepSeek Harness (DSH) with vision, workflows, memory, web tools and more.

dsh-advisor preview
dsh-advisor
omdsh-dev/dsh-advisor

A standalone DSH plugin that gives each session an independent reviewer model to observe the primary transcript and inject severity-ranked advisory feedback without interfering with the primary loop.

Model Inference 2026.08.26 ★ 14
🤖
DSH-Think-zh
Len7183/DSH-Think-zh

Injects a mandatory Simplified Chinese reasoning directive so the model always thinks in Chinese while replying in the user's language and keeping code unchanged.

Model Inference 2026.08.26 ★ 14
dsh-vision-opencode preview
dsh-vision-opencode
poiuyjie/dsh-vision-opencode

Add a configurable vision model to text-only main models, converting chat images to text for replies and supporting OCR, charts, and screenshots.

Model Inference 2026.08.25 ★ 13
dsh-docs preview
dsh-docs
Sqhao-O/dsh-docs

Offline local document intelligence for PDFs, Office files, and scanned images, converting them to Markdown, plain text, or JSON without Docker or API keys.

Model Inference 2026.08.25 ★ 13
oh-my-dsh preview
oh-my-dsh
amplifthq/oh-my-dsh

oh-my-dsh is a curated DeepSeek Harness distribution that provides an opinionated coding environment with LSP navigation, lazy MCP activation, and approval-gated skills.

Model Inference 2026.08.25 ★ 13
🤖
dsh-search-boost
Mr-remon219/dsh-search-boost

A DeepSeek Harness bundle plugin that upgrades built-in search and fetch with fused multi-engine search, X search, focused fetching, deep research, and parallel research.

Model Inference 2026.08.25 ★ 13
dsh-thinking-effort preview
dsh-thinking-effort
hytime/dsh-thinking-effort

Adds configurable reasoning effort levels to hand-declared llm-pi-ai models and sets a default reasoning effort for subagents.

Model Inference 2026.08.26 ★ 13
dsh-drop-to-path preview
dsh-drop-to-path
loudMore/dsh-drop-to-path

Automatically converts dragged or pasted images and files into workspace paths for text-only models, bypassing native attachment limits while preserving the native UI experience.

Model Inference 2026.08.25 ★ 12
🤖
dsh-compaction-instant
TsFreddie/dsh-compaction-instant

An instant, near-lossless context compaction drop-in replacement for DeepSeek Harness that uses deterministic text processing to achieve zero-cost, millisecond compression without LLM calls.

Model Inference 2026.08.26 ★ 11
🤖
dsh-miraculous-standard
rinDBeans/dsh-miraculous-standard

Unified agent preset for DeepSeek V4 Pro/Flash, anchoring RL-aligned states with full Standard tools, dual-channel support, and long-session stability.

Model Inference 2026.08.26 ★ 11
🤖
toolshrink
unclecode/toolshrink

Intelligently shrinks agent tool outputs based on semantic shape and meaning, preserving critical errors and summaries to prevent silent data loss from naive truncation.

Model Inference 2026.08.25 ★ 11
🤖
dsh-plugin-codegraph
CC19990113/dsh-plugin-codegraph

Provides structural code analysis tools for DeepSeek Harness, enabling the agent to accurately query declarations, call chains, and impact scopes via a symbol graph instead of inefficient text search or LSP.

Model Inference 2026.08.25 ★ 11