AIAny
AI Agent2026
Icon for item

Cursor plugins

Provides a manifest-driven marketplace of official Cursor plugins for developer workflows and agent integrations. Each plugin lives in its own directory with a .cursor-plugin manifest; examples include agent skills, PR review canvases, SDK integrations, CI/team tooling, and orchestration for parallel agent work.

Introduction

Most projects that embed agent behavior end up with ad-hoc scripts and brittle integrations. This repository organizes first-party Cursor integrations as a single marketplace: each plugin is a self-contained directory with a .cursor-plugin/plugin.json manifest, making plugins discoverable, versionable, and reusable across Cursor workspaces and agents. The repo collects agent skills, rules, MCP definitions, SDK helpers, and workflow automations across developer workflows.

What Sets It Apart
  • Manifest-first structure: each plugin ships a .cursor-plugin/plugin.json so tooling can enumerate capabilities, authorship, and permissions automatically — so what? it enables programmatic discovery, validation, and safer runtime loading by Cursor agents and the marketplace UI.
  • Agent-focused assets alongside CI/infra patterns: plugins include SKILL.md, rules (.mdc), and mcp.json examples — so what? teams get ready-to-adapt agent skills and server definitions instead of only UI widgets, shortening the gap between idea and deployable agent behavior.
  • Broad developer-tooling coverage: examples range from PR review canvases and docs canvases to CLI-for-agents and orchestrators — so what? it targets the full lifecycle (authoring, reviewing, CI, orchestration) rather than a single integration point, making it useful for embedding agents into real engineering workflows.
  • First-party curation: maintained by Cursor with per-plugin manifests and marketplace.json at the root — so what? consumers can assume consistent conventions and an update path aligned with Cursor platform expectations.
Who it's for and tradeoffs

Great fit if you are building or operating Cursor-based agents or developer automations and want reusable, auditable building blocks (skills, rules, MCP configs) that follow a consistent manifest schema. It helps engineering teams standardize agent behaviors, instrument PR reviews, and fan-out tasks across parallel workers.

Look elsewhere if you need plugins that target other agent platforms (non-Cursor runtimes), require provider-agnostic UI clients, or expect turnkey SaaS connectors outside the Cursor ecosystem; this repo is designed for integration within Cursor conventions and assumes adoption of Cursor SDK/agent runtimes.

Where it sits in a toolchain

This repository is best thought of as the curated plugin layer for Cursor: it sits above the Cursor SDK/runtime and provides building blocks agents and workflows consume. Use it to prototype agent skills, standardize team automations, and bootstrap orchestrations that later run on Cursor cloud agents.

Information

  • Websitegithub.com
  • AuthorsCursor
  • Published date2026/01/23

Categories

More Items

Turns fragile, implicit search progress into explicit, persistent, shared state for multi-agent information seeking — externalizes progress as Frontier Task, Evidence Graph, Coverage Map and Failure Memory, and uses pipeline-parallel scheduling plus a middleware harness to avoid repeated failed searches and improve utilization and throughput.

GitHub
AI Agent2026

Provides a lightweight Python harness that turns LLMs into working agents with tool-use, skills, persistent memory, permission controls and multi-agent coordination. Ships with a CLI/React TUI, 43+ built-in tools, a plugin/skill system and the ohmo personal-agent for chat gateways. Best for developers prototyping agent workflows and multi-agent experiments.

GitHub
AI Client2025

Turns Chromium into a local-first AI browser with an embedded assistant that can summarise pages, extract structured data, automate web tasks, and run scheduled agents. Built as an open-source Chromium fork with 53+ built-in browser tools, 40+ app integrations, and support for BYO AI keys or fully local models (Ollama / LM Studio).