DeepSeek Harness Plugin Marketplace
Explore the DeepSeek Harness plugin ecosystem powered by the Cordis microkernel. Discover official and community extensions for agent orchestration, custom tools, isolated execution sandboxes, vector memory, and private LLM adapters. Built with declarative YAML configuration, live HMR, and end-to-end Trajectory tracing for enterprise-ready AI agents.
DSH Context Full-Spectrum Context Visualizer & Multi-Agent Dashboard
dsh-context is an all-in-one context inspection and visualization suite for DeepSeek Harness. Featuring a standalone Context dashboard, browser, sidebar integration, and /context commands, it breaks down token footprints, tracks turn-by-turn evolution and pruning history, and aggregates multi-agent team session logs.
DSH Pet Interactive Desktop Companion & AI Status Pet
dsh-pet is an open-source transparent desktop pet companion for DeepSeek Harness. Synchronizing in real-time with AI agent states, it triggers reactive animations and speech bubbles during model reasoning, tool execution, code writing, or errors. Features multi-pet displays, physics dragging, customizable scaling, and DIY sprite pack pipelines.
DSH Superagent Autonomous Proactive Coding Suite
DSH Superagent is an open-source proactive coding agent prototype engineered by DeepSeek for DeepSeek Harness. Operating under a minimal human attention principle, it continuously monitors GitHub and Feishu event streams, autonomously launching isolated workspace sessions to inspect repositories, execute code modifications, submit pull requests, and deliver concise updates through an interactive human-in-the-loop dashboard.
dsh-our-free-model Keyless Free Model Gateway Plugin
dsh-our-free-model is a keyless model provider plugin for DeepSeek Harness. Requiring no account, sign-up, or API key, it provides instant access to frontier models like DeepSeek V4.1 and Kimi K3. Featuring real token budget thinking control, egress network probing, and a local OpenAI-compatible forward port, it keeps all telemetry safely on your machine.
dsh-purge Red-Team Eval & Model Plugin
dsh-purge is an open-source cybersecurity red-team evaluation plugin and harness jailbreak toolkit designed for DeepSeek Harness. Decoupling host-level runtime guardrails from intrinsic model responses, it enables custom system prompt overrides, dynamic rule set switching, and local security testbeds. Operating strictly within authorized local environments, it empowers developers to assess large language model robustness.
DSH Proactive Heartbeat & Autonomous Daemon
A production-grade asynchronous heartbeat and persistent daemon runtime for DeepSeek Harness agents. Features declarative cron scheduling, session state persistence, and event-driven wakeups for autonomous background workflows.
Open Design Component Synthesizer & Canvas Engine
A generative UI compilation engine translating developer prompts and wireframes into clean React components. Powered by Tailwind CSS, Figma AST parser, and automated design token validation.
Ruflo Swarm Distributed Agent Mesh
A high-performance multi-agent swarm orchestration framework for DeepSeek Harness. Features dynamic DAG task distribution, shared episodic memory pools, and deterministic consensus protocols.
Archify Software Topology & Architecture Visualizer
An automated architecture reverse-engineering engine transforming source code and schemas into clean Mermaid, PlantUML, and C4 model diagrams with drift detection.
Reactive Resume Semantic Parser & Career Engine
A structured resume parsing and tailored compilation pipeline for DeepSeek Harness. Extracts granular career graphs from PDFs and compiles ATS-optimized resumes targeted against job specs.
Open Viking Headless Scraper & Content Extractor
A resilient headless web scraping and markdown distillation kernel for DeepSeek Harness. Features automated bot-defense evasion, dynamic SPA rendering, and token-efficient content distillation.
DeepSeek Reasonix CoT Telemetry & Reflection Inspector
A dedicated diagnostic telemetry suite for DeepSeek-R1 and V3 reasoning models. Real-time visual tracking of `<think>` reflection streams, logical breakpoints, and hallucination alerts.
GPT Image 2 Multimodal Vision & Raster Pipeline
A unified multimodal vision synthesis and image analysis suite for DeepSeek Harness. Automates prompt enhancement, pixel-level OCR extraction, raster-to-SVG vectorization, and multi-layer compositing.
Weknora Graph RAG & Hybrid Retrieval Engine
An enterprise hybrid RAG engine combining dynamic Knowledge Graphs with dense vector retrieval. Delivers multi-hop reasoning, relationship mining, and chunk deduplication for zero-hallucination Q&A.
ModLens Code Intelligence & AST Semantic Grepper
An advanced AST-powered code intelligence suite for DeepSeek Harness. Delivers lightning-fast symbol resolution, deep call graph tracing, static anti-pattern audits, and clean refactoring patches.
PicGo Cloud Asset Pipeline & Storage Driver
A unified cloud asset pipeline bridging autonomous agents with AWS S3, Cloudflare R2, Aliyun OSS, and Tencent COS. Features automated deduplication, CDN cache warmup, and signed URLs.
Distilly Context Distiller & Prompt Pruning Optimizer
A context compression and token economizer engine for DeepSeek Harness. Leverages semantic relevance scoring to prune redundant prompt tokens, deduplicate chat logs, and reduce latency by up to 70%.
NocoBase Headless Data Engine & Dynamic Schema Driver
A headless relational database and dynamic schema middleware for DeepSeek Harness agents. Integrates NocoBase metadata APIs to automate database modeling, dynamic CRUD synthesis, and RBAC control.
Voyager Web Automator & Playwright Testing Suite
A Playwright-powered autonomous web browsing and E2E testing framework for DeepSeek Harness. Equips agents with full DOM interaction, multi-tab orchestration, visual regression, and form submission.
Awesome DSH Dynamic Registry & Tool Marketplace
A decentralized plugin discovery and runtime injection registry for DeepSeek Harness. Features semantic capability matching, automated dependency resolution, and zero-downtime hot mounting.
Harness Engineering Interactive Sandbox & Testing Lab
An interactive engineering playground for mastering DeepSeek Harness and Cordis microkernel mechanics. Features 30+ hands-on labs covering event buses, state machines, and agent sandboxing.
EverOS Distributed Agent Kernel & Process Supervisor
A UNIX-like virtual process manager and distributed scheduling substrate for DeepSeek Harness. Delivers POSIX pipes, shared-memory IPC, process isolation, and dynamic cgroups.
MemOS Long-Term Memory & Cross-Session Graph Store
A persistent cognitive memory and cross-session graph store for DeepSeek Harness. Combines working memory, episodic traces, and semantic networks with automated forgetting curves.
Gungnir Hardened Container Sandbox & Isolation Jail
A zero-trust hardened container sandbox for executing untrusted AI code. Powered by Linux namespaces, strict seccomp syscall filters, and read-only rootfs with sub-millisecond cold starts.
Showing 24 of 52 plugins
Want to author and publish your own Cordis Plugin?
DeepSeek Harness fully embraces the open Cordis architecture. Using the standard CLI scaffold, any developer can build, debug, and publish plugins to the community in minutes.
npx create-cordis-plugin my-dsh-pluginCordis Plugins & Ecosystem FAQ
Frequently asked questions about DeepSeek Harness plugin architecture, installation, sandbox safety, and custom development.
What is the DeepSeek Harness plugin system, and how does it differ from traditional agent tools?
Built on the Cordis microkernel, Harness plugins decouple tools, sandboxes, and state machines, enabling models to invoke tools via the bus or write programmatic TypeScript scripts (PTC) to batch-orchestrate workflows.
How do I install and activate a specific Cordis plugin in my project?
You can install plugins with 'npx @deepseek-ai/dsh add [package-name]' or declare the package and configuration directly in 'cordis.yml'. Harness supports live Hot Module Reloading (HMR), applying new plugins without restarting the host agent daemon.
How is runtime safety guaranteed when executing agent plugins?
Harness enforces multi-layered sandbox isolation. High-risk shell commands and builds run inside disposable Docker containers or WebAssembly environments with strict CPU, RAM, and read-only filesystem limits. AST static code scanning and security interceptors are also provided.
How can I integrate existing community MCP tools into Harness?
Harness includes a built-in MCP bridge plugin. Simply configure the MCP server launch command or SSE endpoint in 'cordis.yml'. Harness automatically performs JSON-RPC handshakes, discovers tools, and mounts them as native Cordis services.
How can developers build and publish custom Cordis plugins?
Run 'npx create-cordis-plugin my-plugin' to scaffold a TypeScript project. Implement the standard 'apply(ctx, config)' lifecycle function, publish to npm or GitHub, and leverage TypeScript declaration merging for full intellisense.
How does Harness handle plugin errors, exceptions, or timeouts?
Harness relies on a deterministic state machine and Fiber lifecycle controller. If a plugin throws an exception or times out, error interceptors trap the failure, execute self-healing rollbacks, and inject sanitized error logs into the next reasoning step without crashing the agent process.