imsai-sh/awesome-deepseek-harness-plugins

DeepSeek Harness plugin store, marketplace and hub — 11,000+ dsh plugins with search, rankings, install commands and a free public API. DeepSeek Harness 插件市场 / 插件商店：自动收集与格式校验，免费搜索 API。deepseek1024.com

What it solves

This project provides a centralized, community-driven directory for DeepSeek Harness (dsh) plugins. It solves the problem of discoverability and quality control by automating the collection, verification, and indexing of thousands of community-made plugins, ensuring users can find reliable extensions without manual searching.

How it works

It operates as a robust pipeline rather than just a static list. The system automatically discovers GitHub repositories tagged with dsh-plugin, performs static code analysis to verify the presence of required configuration files (like package.json and dsh.bundle.patch), and syncs valid plugins to a searchable database. It never executes repository code during this process. Users can browse the directory via an online marketplace, or install a dedicated plugin that brings the marketplace directly into the DeepSeek Harness interface.

Who it’s for

This is for DeepSeek Harness users who want to extend their environment with community plugins, as well as developers who want to share their own plugins or build their own plugin marketplace using the provided open-source infrastructure.

Highlights

  • Automated Discovery & Verification: Plugins are collected automatically and must pass strict static syntax checks before being listed.
  • Integrated Marketplace: Users can search, filter, and install plugins directly from within the DeepSeek Harness app.
  • Open-Source Infrastructure: The entire marketplace stack—including the website, CLI, and API—is open-source and can be self-deployed.
  • Public API: Provides free, anonymous access to the plugin directory data for external tools or integrations.
  • Community-Driven: Supports easy plugin submission via Pull Requests or automated Agent Skills.

Related

  • Project
    hkr04/cpp-mcp

    A C++ implementation of the Model Context Protocol (MCP) that allows AI models and agents to interact with tools, resources, and services through a standardized interface.

  • Project
    anvie/evonic

    Evonic is an open‑source, Python‑based framework for building LLM‑powered agents that can run on local machines, remote SSH servers, or via a custom tunnel (Evonet). It provides first‑class support for multi‑agent communication, safety heuristics, knowledge‑graph‑backed KBs, hybrid memory, and ready‑made channel adapters (Telegram, WhatsApp, Discord). The platform lets you define agents with custom prompts, models, tools, skills, and workplaces, then orchestrate them as swarms for use‑cases ranging from customer‑service bots to DevOps automation, all while optionally archiving exact LLM I/O for fine‑tuning datasets.

  • Project
    mcncarl/agent-memory-vault

    Agent Memory Vault is a Python toolkit that provides a local, Git‑backed Markdown vault with SQLite (and optional vector) search, enabling Claude Code, Codex and similar AI agents to share durable, auditable long‑term memory across sessions.

  • Project
    neutree-ai/openapi-to-skills

    A tool that converts large OpenAPI specifications into modular, agent-friendly markdown files, allowing AI agents to load only the specific API documentation they need to perform tasks.