openclaw
A personal AI assistant that runs on your own computer and answers through messaging channels such as Slack, Telegram and WhatsApp. Its skills cover browser automation, canvas panels, app previews and shareable diffs.
Flowy lists 269 plugins for Slack work in Claude Code. Each one bundles skills a Claude Code agent can load while you work. Every listing shows what is inside before you install, who built it, and whether it is Auto-invoked, meaning a FLOW.md router fires the right skill as you prompt instead of leaving them dormant.
A personal AI assistant that runs on your own computer and answers through messaging channels such as Slack, Telegram and WhatsApp. Its skills cover browser automation, canvas panels, app previews and shareable diffs.
Skills for the OpenClaw personal AI assistant, covering browser automation, routing requests to coding agents, presenting canvas widgets, running apps on temporary machines, and sharing diffs.
Skills and MCP servers for working in Visual Studio Code, including creating and reviewing agent customization files, custom agents, hooks, and extension canvases, plus code review, CI fixing and project setup.
Helps you build front-end pages and visuals that look intentional, and checks the UI by running it in a browser before you call it finished. Covers design, testing, and writing new skills.
Gives you working starting points for AI agents, agent skills and retrieval-augmented generation apps that you can clone, run and adapt to your own project. The examples work with several model providers, so you can switch models without rewriting the app.
Orchestrates teams of AI agents to run work like a company, with a Node.js server and React UI. Adds skills for delegating tasks, following up on results, reviewing team status, and managing Paperclip tasks from Hermes.
Gemini CLI is an open-source AI agent for the terminal that gives direct access to Google's Gemini model. It includes skills for Antigravity CLI setup and for creating new skills.
Gives you a Python library for building and training deep learning models, with tensor math that runs on GPUs and a flexible autograd system for computing gradients. Work in familiar Python and reuse libraries such as NumPy and SciPy.
Organizes your AI agents into a team that runs around the clock, handling hiring, scheduling, delegation and reporting so you can stay in charge without staying online.
Organizes your AI agents for round-the-clock operation, with tools to hire, schedule and report on your agent team. Lets you oversee the agents without staying online yourself.
Shows how a coding agent harness works by giving Claude tools, context handling and permission limits, so you can study a real agent or build your own. Its bundled skills also help you design agents, review code, build MCP servers and work with PDFs.
The open and composable observability and data visualization platform. Visualize metrics, logs, and traces from multiple sources like Prometheus, Loki, Elasticsearch, InfluxDB, Postgres and many more.
Analyzes GitHub issues and pull requests, and implements fixes for issues, for a Claude Code user working on a repository. Covers a stock analysis project's skills for triage, PR review and fix implementation.
An autonomous coding agent for editing code, usable as an SDK, an IDE extension, or a terminal CLI assistant. It supports multiple models, MCP integrations, and plan and act modes.
Gives Claude Code long-term memory through Hindsight. It recalls relevant past context before answering, retains durable facts as the agent learns them, and reflects over stored memory.
Gives developers working on the Metabase codebase ready-made skills for common backend and frontend tasks, such as adding Malli schemas to API endpoints, instrumenting Clojure code with tracing spans, adding frontend analytics events, and auditing the REST API changelog against the OpenAPI spec.
A self-hosted personal AI agent framework with skills for scheduling reminders, managing GitHub issues and pull requests, generating and editing images, searching past conversations, and installing skills from ClawHub.
An open-source personal AI assistant and agent harness that plans tasks, runs tools and skills, and keeps memory and a personal knowledge wiki. It also generates images and can create or install new skills.
Skills and agents for building, running and managing agent platforms, with tools for inspecting sources, refreshing product status and delivering summaries. Aimed at developers working on agent runtimes.
Gives Claude Code skills, agents, and commands for PostHog analytics, session replay, feature flags, error tracking, and LLM observability. Includes MCP server setup and project access checks.
Skills for building agent-native apps with CopilotKit, covering generative UI, shared state, and human-in-the-loop workflows in React, Angular, Vue, and React Native. Also includes setup help for agents in Slack and Microsoft Teams, plus the CopilotKit CLI.
Gives Claude working knowledge for scientific research, covering instrument data conversion, bioinformatics pipelines for RNA-seq and sequencing data, single-cell analysis and quality control, and research project planning. Useful for lab scientists who want consistent, standardized analysis.
Brain knowledge base for Claude Code, with skills for ingesting content, linking and synthesizing concept pages, auditing always-loaded context, and running read-write cycles over a personal knowledge graph.
A lightweight personal AI assistant that runs its agents in isolated containers. It connects to messaging apps such as WhatsApp, Telegram, Slack, Discord and Gmail, with memory and scheduled jobs, and adds skills for converting office documents and using local models.
Distills colleague, relationship, or celebrity source material such as chat logs and emails into reusable person profiles, and also sets up an owner profile so a personal agent knows who it works for.
Gives AI coding agents a repeatable engineering loop, from brainstorming and planning through building and review, and saves what each change taught so later work can reuse it. Covers tasks like shepherding a pull request to merge.
Archon is a workflow engine for AI coding that runs repeatable YAML-defined workflows on a git repo, with tools to inspect, approve, cancel and resume runs. It also ships skills for browser testing, release creation and rule checking.
n8n-MCP is an open-source MCP server that lets Claude, ChatGPT, Cursor, and other AI assistants operate n8n: read failed executions, edit workflows in place, validate and test them, manage credentials, and build new workflows.
Skills for building GraalVM native images of Java applications with Gradle or Maven, covering build configuration, CLI options, native tests, and troubleshooting build or runtime issues.
Agent skills for working with KubeSphere, a Kubernetes management platform. They cover frontend-forge extension and FrontendIntegration resources, KubeEye cluster inspection, and read-only queries of cluster status and version.
Skills for working on OpenMetadata, an open metadata platform for data catalogs, governance and lineage. They cover building, auditing and reviewing OpenMetadata connectors against project standards, plus reviewing code changes.
A desktop workbench for Claude Code that runs many sessions side by side, with global search, branch and worktree launch, diff review, a built-in browser preview, and graphical approval of permissions. You can also choose the model and generate images from within it.
Turns documentation sites, GitHub repos, PDFs, videos, notebooks, and wikis into structured knowledge assets. Use it to build AI skills for Claude, Gemini, or OpenAI, or to feed RAG pipelines.
Prowler is an open-source cloud security platform for scanning cloud accounts and automating security and compliance checks. It includes skills for framework compliance triage, Django REST and Vercel AI SDK patterns, and GitHub agentic workflows.
A collection of Cursor plugins for coding agents covering skills and agents such as advisor checkpoints, CLI design review, plugin scaffolding and continual learning for AGENTS.md. Plugins cover developer tools, frameworks and SaaS products.
IronClaw is an Agent OS focused on privacy, security and extensibility.
Gives Claude Code users network observability for Kubernetes clusters, with skills for installing Kubeshark, writing its filter language, root cause analysis of past incidents, and security audits, backed by an MCP server for AI agents.
Gives a team one workspace that connects the systems and chat tools it already uses, with shared memory and any model or agent. Work that used to need months of setup is ready in clicks, and the data stays on local machines.
Hive is a multi-agent orchestration framework for production AI, with skills for debugging browser automation on complex sites, live queen-colony debugging, running agent integration tests, and triaging GitHub issues.
Autoharness, a self-learning skill layer for Claude Code, distills skills from your real sessions, updates them as you work, and prunes the ones that stop getting used. No daemon, no benchmark.
Skill for launching cloud VMs, Kubernetes pods, or Slurm jobs for GPU, TPU, or CPU workloads. Covers training and fine-tuning models on cloud GPUs and deploying inference servers with autoscaling.
Reference agents, skills, and data connectors for legal teams, covering AI governance work such as EU AI Act system inventories, impact assessments, and matter workspaces that keep each client's context separate.
A Claude Code plugin that runs a multi-agent office of Claude Code and Codex style agents on your laptop or in sandboxes, using your existing subscriptions. It includes skills for Chinese article illustrations and rolling date-range queries.
Configures AI coding agents such as Claude Code, Cursor, and Codex with persistent memory, skills, MCP servers, and personas. Includes skills for writing pull requests, collaboration comments, and design docs.
Open-source content platform. Self-hosted on AWS serverless. Built as a TypeScript framework you extend with code, not a closed product you configure through a UI. Runs on Lambda, DynamoDB, S3, and CloudFront inside your own AWS account. Scales automatically.
Gives product managers professional frameworks for PRDs, roadmaps, pricing and stakeholder work, so an AI agent produces documents stakeholders trust and engineers can act on. It also explains the reasoning behind each framework, so you can adapt and teach it.
Gives a machine learning team one place to define features and serve them consistently, so training data and live predictions use the same values. Covers the offline store, online store and feature server.
Runs an autonomous loop that modifies code, verifies the result against a mechanical metric, and keeps or discards each change, for iterative improvement, debugging and ship-readiness checks in Claude Code.
A pixel desktop pet that watches Claude Code, Codex, Cursor & other AI coding agents, so you don't have to.
Expert Claude Code skills for building flawless n8n workflows using the n8n-mcp MCP server.
Skills for installing, configuring and operating the vLLM Semantic Router on Docker or Kubernetes, changing its routing contracts, calibrating routing recipes against live model backends, and handling maintainer issue and release work.
A Claude Code plugin with skills for building durable backend AI agents with the eve framework, plus skills to investigate issue reports, look up agent runs, and run security and correctness audits of code diffs.
Gives AI agents a way to connect to outside tools and services through MCP servers, so they can act on your accounts and data without you wiring each integration by hand. Also includes a documentation lookup skill that answers questions about libraries and frameworks with code examples.
A self-hostable personal AI assistant that connects any model provider, builds a knowledge base from your own documents, and lets agents browse the web, run code and call MCP tools for you. Its skills cover notes, reminders, secrets and feed monitoring on macOS.
A visual canvas for designing AI agent workflows that exports them as Markdown for Claude Code. Also includes skills for Jira-driven planning and autonomous development loops.
Gives Hermes users a governing layer that frames each request, picks the workflow and evidence checks, and records honestly what happened. It covers planning, research, coding handoffs, operations and project memory.
Generates, polishes, reviews, amends and publishes command-line tools for AI agents, so they can run with fewer wasted steps and tokens. Includes skills for importing and publishing CLIs from a shared library.
Gives your coding agent skills to watch or audit another agent's work, babysit a pull request through review and checks, and run heavy research and coding on cheaper subagents.
Skills for IT access requests, decoding encoded messages, and computing totals over a sales ledger workbook. Covers the skills that ship in this plugin.
A command line tool that searches files semantically using natural language queries, covering code, images, and PDFs. It can also replace built-in search tools in Claude Code and keep an index updated in the background.
Redpanda Console (previously known as Kowl) is a web application that helps you manage and debug your Kafka/Redpanda workloads effortlessly.
An open source take on Claude Cowork that connects Claude to many SaaS apps, with skills for brand guidelines and Remotion video projects, plus tools for browser automation and task scheduling.
A coding agent harness whose agents keep memory and identity across sessions, so they learn and improve over time. You can run it in a terminal, in the browser, or through Telegram, Slack and Discord.
Gives Claude Code a bash-style interface to files and directories mounted from cloud storage, databases, and APIs in one virtual filesystem. Includes skills for working with mounted data and for building custom adapters for new data sources.
Rewrites prose so it reads less like AI output, repairing a story's structure before its word choice. Each professional document type, such as release notes or postmortems, gets rules suited to its format, and you can write, review, lightly edit or fully rewrite.
Connects an AI agent to everyday chat apps such as WeChat, Feishu, Slack and Discord, so you can talk to it from your phone and keep it running around the clock. Runs locally and works with multiple models.
A Claude Code plugin with skills for Apple Notes, Apple Reminders, Bear notes, RSS and blog monitoring, and 1Password CLI secret handling. Its listed features include persistent memory and offline learning.
A provider-neutral agent skill for designing, auditing, refactoring, and explaining agentic harnesses in any domain, including generating MVP blueprints. The harness validates, authorizes, executes, and records actions the model proposes.
Generates and edits selfie images from a reference photo using Grok Imagine, then sends them to messaging channels through OpenClaw. Aimed at users who want a consistent visual persona in chat.
A Pi-native shell for controlled development with skills for opening review-sized pull requests, writing clear docs and collaboration comments, and delegating work to focused subagents with test-first habits.
A desktop app that runs an AI agent for you on Windows and macOS, so you can create and edit Word, Excel, PowerPoint and PDF files, automate desktop apps and browsers, and control it remotely from Feishu or Slack, without writing code. It runs inside an isolated sandbox.
A Japanese writing skill that rewrites AI-drafted work documents such as meeting minutes, reports, technical articles and PR descriptions so they read naturally, without adding facts or certainty the original lacked.
Emulates developer APIs such as Vercel, GitHub, Google, Slack, Apple, AWS and Twilio locally, so integrations can be built and tested in CI or without network access. Includes skills for each service and for building custom emulators.
A penetration testing automation CLI that uses AI agents to plan scans, run security tools, analyze findings and write reports. It is meant for security testers doing authorized assessments.
Open-source skills for public relations work, covering angle generation for company news, writing that AI answer systems can retrieve and cite, and building AI visibility tracking panels.
A local-first control layer for AI coding agents such as Claude Code, Codex CLI, and Cursor. It provides agent listing, messaging, orchestration, and setup skills so agents can coordinate work from one place.
Give your AI agent n8n superpowers. 537 nodes with full schemas, 7,700+ templates, Git-like sync, and TypeScript workflows.
Gives Claude Code a shared team and org memory through Activeloop's Deeplake, with skills for tracking team goals and querying the local code graph of functions, classes, calls and imports.
Lets your AI agent answer data questions against your warehouse accurately, using approved metric definitions, joinable columns and company knowledge, so it stops re-exploring tables and inventing its own numbers. Ingests dbt models and wiki pages to keep that context current.
A plugin for automating routine work with AI models, with approval gates, scheduled routines, and a builder for small local microapps to manage the results. Open source and local-first.
Lets a supervisor AI coding assistant hand tasks to specialist agents running in parallel or in sequence, so you stop coordinating several coding CLIs by hand. Includes skills for routing tasks to the right agent and managing sessions.
Builds reusable AI agents and multi-agent teams for Claude Code, with skills for creating single agents, packaging existing agents, and auditing team packages with orchestrators, workers, and handoffs.
Deploys and operates a self-hosted OpenTag setup for Slack, pairing a local runner with a GitHub-connected Control Plane so an engineering channel gets an AI teammate that stays reachable even when its computer is offline.
A self-evolving second brain that stores your notes as plain markdown files in Obsidian under Git version control, with AI agents for research, capture, daily journaling, and content creation. No database or vendor lock-in.
Runs Claude Code as a background assistant that executes scheduled tasks and replies to messages on Telegram, Discord and Slack. It can also transcribe voice commands and connect to other services you use.
Gives you one terminal that shows every running, waiting or finished AI coding agent session across your projects, so you can switch between them with a single keystroke. It also records what each session was for, so you can find and hand off past conversations.
Creates a reusable SkillPack from a successful research, coding, analysis, or content task so it can be shared as a local agent. Lets teams run these agents in their own environment and use them from Slack and Telegram.
A library of bioinformatics skills for AI coding agents, covering genomic analysis, variant annotation, pharmacogenomics, GWAS, proteomics and reproducible research workflows, run locally.
Connects Jira, Confluence, Jira Service Management, Bitbucket, and Compass to AI tools such as Claude and Cursor through a remote MCP server, with sign-in via OAuth or API tokens.
Core runtime for the Zylos agent, providing communication bridging to external channels, session and context management, scheduling, health monitoring with auto-restart, and component installation. Useful for developers running a persistent Claude agent.
Adds frontend observability to a browser app with the Grafana Faro Web SDK, covering error tracking, Web Vitals, session monitoring and distributed tracing. Telemetry can be sent to Grafana Alloy, Grafana Cloud or a custom receiver.
Gates a coding agent's claim of done by running the repo's real test suite and refusing completion if tests newly fail or tests or CI config were deleted. Useful for developers working in repos that have tests.
Autonomous coding agent that turns a task or issue into a pull request and checks it against the repo's tests. Its loki-seal skill blocks declaring a task done while tests newly fail or test or CI config was deleted.
Relay lets Claude Code agents message each other and coordinate work through workflow patterns like fan-out, pipeline, and hub-spoke, instead of copying output between sessions. It also bundles skills for browser testing with screenshots and for creating agents, hooks, and rules.
Skills for working on the arcade-mcp Python framework, which builds MCP servers and tools. They cover writing new error adapters for provider integrations and preparing changes for review by filling the repository PR template.
The official Microsoft Work IQ plugin collection for GitHub Copilot Extend the power of GitHub Copilot with Work IQ plugins, MCP servers, skills, and tools that connect AI assistants to your Microsoft 365 data.
OpenLoomi is an open-source AI coworker that connects your work tools, understands your context, and tells you what needs attention and what to do next. It runs local-first with skills for data analysis, persistent learning, and Composio app integrations.
Lets a lead agent hand goals to worker agents such as Claude Code or Codex, each running in an isolated container. Shared memory, schedules and review gates keep the work going across sessions.
OpenTabs lets Claude Code call web app APIs through your existing browser session, instead of clicking through the interface. Its skills scaffold, build, test and version-bump plugins for that bridge.
A markdown-based second brain for product managers and product leads. It stores plain markdown notes in a local folder that Claude reads before answering and updates afterward, with a weekly review sweep.
Runs a consistent marketing strategy process across every brand in a portfolio, producing the same planning files in the same order so agencies and in-house teams can audit depth and catch compliance gaps. Covers SEO audits, ad copy, A/B test planning and AI search visibility.
Agent skills for founders and indie operators covering decisions, research, company knowledge bases, monthly CFO close, business idea pressure-testing, and domain hunting.
Assigns issues from your Linear, GitHub, GitLab or Slack to an agent that works each one in its own Git worktree and reports progress back as it goes. Bring your own model keys or subscriptions.
A workflow layer that adds agents for building, shipping, and operating software projects to Hermes, with roles for CTO, designer, developer, operations, QA, and security.
Lets Claude Code find, connect, and install MCP tools and skills from the catalog through its command line. Also includes a skill for building a web app that connects to MCP servers.
Sends desktop alerts with sounds and webhooks when Claude Code needs your attention or reaches a milestone during long-running work. Clicking a notification brings the matching window back into focus, on macOS, Linux, and Windows.
A 3D isometric office where AI agents do real work on your own Claude login. Six departments, thirty-five agents at their desks, a task bar that routes what you type to the right agent, and a Brain at the centre that is your own folder of notes.
Gives a product manager ready-made AI skills for the full product lifecycle, from framing a problem and forming a testable hypothesis to mapping customer jobs and ranking features with standard prioritization methods. Each skill comes with a worked example to guide the output.
Skills for Claude Code that add motion, micro-interactions and design systems to web, Android (Jetpack Compose) and Apple (SwiftUI) interfaces, with an interaction plan you approve before any code is written.
Multi-agent coordination for Claude Code that breaks big tasks into smaller ones and runs agents in parallel, with skills for worker spawning, file reservations and progress tracking.
Gives your AI coding agent the playbooks of a marketing team, covering SEO, content, email, ads, analytics and growth. It writes and runs the work itself, so you stop doing the marketing tasks by hand, and it runs locally on your machine.
Helps developers build, configure and debug Microsoft Teams bots, apps and AI agents, so Teams questions get answered in the context of their own project.
Skills for operating the Pilot daemon, which turns tickets into pull requests, along with a branch audit tool for safe local git branch cleanup and debugging help for stuck executor runs.
Gives you a self-hosted runtime for running autonomous AI agents and swarms that delegate work, keep durable memory, and run on schedules. It connects to Claude, GPT, Gemini, Ollama and other model providers.
Gives your AI agent ready-made instructions for marketing and growth work, such as finding cold-email addresses, writing blog cover images, naming a brand, and mining app reviews for copy ideas. Install the skills you need so you stop doing these tasks by hand.
Gives a marketing team AI-agent skills for planning a period's marketing, building content calendars, writing campaign briefs, diagnosing weak campaign numbers, and drafting short-form video scripts. Covers US, EU, SEA and LATAM markets in Vietnamese and English.
Connects Claude Code to WhatsApp and Instagram Business messaging through the OpenBSP platform, with tools for managing allowed contacts, webhooks and account setup.
Avibe is a local-first agent workbench that lets you drive Claude Code, Codex and OpenCode from your browser or chat apps. Its skills cover durable delegation, background watches, secure credential use and prompt auditing.
Chat-driven biomedical research assistant for Claude Code that runs bioinformatics, RNA-seq, drug discovery and clinical analysis workflows, with a live dashboard and Feishu rich-card reporting for progress updates.