RealZST/HarnessKit

More than a skill manager — manage skills, MCP servers, plugins, hooks, CLIs, configs, memory & rules across every AI coding agent. 🌟 Star if you like it!

What it solves

AI coding agents (like Cursor, Claude Code, and Copilot) often store their configurations, extensions, and rules in scattered directories using different formats. HarnessKit provides a unified interface to manage these disparate settings and extensions across multiple agents from a single location, eliminating the need to manually hunt for config files or handle format differences between agents.

How it works

HarnessKit operates directly on the agents' native directories without creating shadow copies. It automatically discovers global and project-specific config files, memory, and rules for 13 supported agents. It provides a desktop app, a CLI (hk), and a web interface for managing these files.

Who it’s for

Developers who use multiple AI coding agents and want a centralized way to organize their extensions, audit their security, and synchronize settings across different projects.

Highlights

  • Unified Extension Management: Manages Skills, MCP Servers, Plugins, Hooks, and Agent-first CLIs across various agents.
  • Security Auditing: Built-in static analysis engine that assigns Trust Scores to extensions based on 18 rules and surfaces permission transparency.
  • Cross-Agent Deployment: Deploy extensions to multiple agents with one click, with HarnessKit handling the format conversions (JSON, TOML, etc.).
  • Librarian-style Marketplaces: Integrated access to registries like skills.sh and Smithery for discovering and installing new capabilities.
  • Kits: Ability to bundle skills, MCP servers, and rules into portable .hk-kit.zip files for easy reuse across projects.
  • In-Place Management: Modifies native directories directly, ensuring zero lock-in and no sync conflicts.

Related

  • Project
    ntd4996/agentpet

    AgentPet is a cross‑platform desktop app that monitors the live state of AI coding agents and gamifies the experience with a tamagotchi‑style pet that levels up based on token usage and completed sessions. It works offline, supports many agents, offers per‑project dashboards, and provides optional web sync and leaderboards.

  • Project
    Lamatic/AgentKit

    AgentKit is an open‑source SDK that provides a catalog of 70 ready‑made “kits” (full apps, pipelines, or templates) for building, testing and deploying AI agents. Kits are defined by a simple config file, can be edited in a visual flow studio, and are shipped as Next.js apps that run server‑less. The collection covers support triage, code review, RAG chat, hiring assistants, legal/medical bots, and many other business‑focused agents, making it a turnkey platform for creating reliable, enterprise‑grade AI agents.

  • Project
    codejunkie99/agentic-stack

    agentic‑stack is an open‑source toolbox that gives a portable “brain” (memory, skills, protocols) to many code‑generation agents (Claude Code, Cursor, Copilot CLI, Gemini CLI, etc.). The brain lives in a hidden `.agent/` folder, enabling agents to retain preferences, lessons, and reusable skills across tool switches. It provides bounded agentic loops, a review‑by‑human protocol, a local dashboard for token‑cost/KPI monitoring, and export utilities that turn approved runs into trace records or training‑ready JSONL. Installable via Homebrew or a simple script, it supports optional external long‑term memory (the `brain` server) and a beta full‑text memory search.

  • Project
    OpenSource03/harnss

    A cross-platform desktop app that provides a unified interface to run and manage multiple AI coding agents like Claude Code and Codex without losing context.

  • Project
    whitelonng/dshcode

    A free, open-source desktop application for macOS and Windows that packages the DeepSeek Harness AI Agent framework into an easy-to-install app with a graphical user interface.