Agent Skills & Prompts

Official MCP server for GitHub repo operations

GitHub MCP Server is the official Model Context Protocol server from GitHub that connects AI assistants to repositories, issues, pull requests, workflows, and code search. It exposes 100+ operations with toolset filtering, permission scoping, and audit logging, available in both remote-hosted and self-hosted Docker deployment modes.

Official open catalog of Model Context Protocol servers

The official, community-run registry for discovering and publishing Model Context Protocol (MCP) servers — an open index that MCP clients read to find available servers.

Up-to-date docs for AI code editors via MCP

Context7 is an MCP server developed by Upstash that injects up-to-date, version-specific documentation directly into AI code editors and coding assistants. By typing 'use context7' in prompts, developers get accurate library documentation instead of hallucinated or outdated API references. It pulls from official source documentation and serves it through the Model Context Protocol, solving the common problem of LLMs generating code with incorrect or nonexistent API calls.

Apache-2.0 Python framework for repeatable LLM, RAG, agent, MCP, and safety evaluation workflows.

DeepEval is an Apache-2.0 Python framework for evaluating LLM apps, RAG systems, agents, MCP workflows, and safety behavior with repeatable test cases. It works locally and in CI/CD, then connects to Confident AI for hosted reports, observability, red teaming, and governance when teams need shared evidence instead of ad-hoc prompt reviews and manual QA.

Turn websites into LLM-ready structured data

Firecrawl is a Y Combinator-backed API that crawls websites and converts them into clean, LLM-ready Markdown or structured JSON. Handles JavaScript rendering, pagination, sitemaps, and anti-bot measures automatically. Designed for RAG pipelines, AI agents, and data extraction workflows. Features batch crawling, scheduled scraping, webhook notifications, and custom extraction schemas. Processes content for direct ingestion into vector databases and LLM context windows.

Virtual engineering team as Claude Code skills by YC CEO Garry Tan

GStack transforms Claude Code into a structured virtual engineering team through 23 opinionated slash command skills created by Y Combinator CEO Garry Tan. It assigns specialist roles including CEO product review, engineering manager architecture oversight, designer visual audit, QA lead with real browser testing, and release engineer deployment. Each skill enforces focused workflows with clear decision principles for running parallel coding sessions.

Zig-built headless browser engineered for AI agent workloads

Open-source headless browser written in Zig for AI agents, crawling, and automation. Lightpanda omits graphical rendering, keeps DOM and JavaScript execution, exposes CDP for Puppeteer/Playwright/chromedp, and adds Agent, PandaScript, and MCP workflows. Current public benchmarks claim about 9x faster execution and 16x less memory than Chrome.

Intelligent memory layer for AI agents and assistants

Mem0 is an open-source intelligent memory layer for AI agents with 51K+ GitHub stars providing persistent, adaptive memory across sessions. It manages working, short-term, and long-term memory types, enabling personalized AI experiences that improve over time. Features automatic memory extraction from conversations, semantic search over stored memories, multi-format support, and integration with 100+ frameworks. Simple API for adding memory to any LLM-powered application or agent.

Multi-agent orchestration plugin for Claude Code

Oh My ClaudeCode (OMC) is a plugin for Claude Code that adds multi-agent orchestration with 19 specialized agents, smart model routing between Haiku and Opus, and execution modes such as Autopilot, Team, Ralph, Ultrawork, and Deep Interview. It provides lifecycle hooks, a real-time HUD statusline, and source-backed Claude Code workflows that turn one session into a coordinated AI development team.

Official Chrome DevTools MCP server for coding agents

chrome-devtools-mcp is the Chrome DevTools team's official MCP server that lets coding agents control and inspect a live Chrome browser with first-party Chrome DevTools Protocol fidelity. It exposes Network inspection, Performance traces, Lighthouse audits, console output, and structured DOM snapshots as typed MCP tools, so agents can debug real pages and ship reliable web performance investigations without resorting to brittle DOM scraping.

Open-source Docker gateway for containerized MCP server orchestration

Docker MCP Gateway is Docker's open-source orchestration layer for Model Context Protocol servers. It gives MCP clients one gateway, launches catalog servers in isolated containers on demand, injects credentials, applies runtime restrictions, and routes tool requests. Catalogs and profiles let teams reuse approved server collections across clients, while Docker Desktop can run the gateway automatically with MCP Toolkit enabled.

Secure cloud sandboxes for AI agents

E2B provides secure cloud sandboxes that let AI agents execute code, run terminal commands, and interact with filesystems in isolated environments. Each sandbox spins up in ~150ms with its own OS, giving agents a safe space to run untrusted code. Supports Python, JavaScript, and any language via custom Dockerfiles. Used by AI coding assistants, data analysis agents, and code interpreters. SDK available for Python and JavaScript with a simple API for programmatic sandbox control.

Apache-2.0 Python framework for building MCP servers, clients, apps, and deployable agent tool surfaces.

FastMCP is an Apache-2.0 Python framework for building MCP servers, clients, and apps with decorators, type hints, transports, auth patterns, deployment docs, and telemetry hooks. The project now resolves to PrefectHQ/fastmcp, with Prefect Horizon available as a separate enterprise MCP gateway for identity, RBAC, audit, monitoring, and server governance.

Open-source AI agent framework with persistent memory, reusable skills, tools, and messaging gateways

Hermes Agent is an open-source AI agent framework with persistent memory, reusable skills, 40+ tools, cron jobs, and messaging gateways.

Open-source LLM engineering platform for observability

Langfuse is an open-source LLM engineering platform with 29K+ GitHub stars for tracing, evaluating, and monitoring AI applications. Acquired by ClickHouse, it provides detailed traces of LLM calls, prompt management with versioning, dataset-based evaluation, user feedback collection, and cost tracking. Framework-agnostic with native integrations for LangChain, LlamaIndex, OpenAI SDK, and Vercel AI SDK. Offers both self-hosted deployment and a managed cloud service.

Data framework for LLM applications

Leading Python framework for building LLM-powered applications with focus on data-aware and agentic workflows. Provides tools for RAG (Retrieval-Augmented Generation), document indexing, vector store integrations, query engines, and multi-agent orchestration. 150+ data connectors for various sources. Works with OpenAI, Anthropic, local models, and more. Includes LlamaHub for community tools and LlamaCloud for managed RAG pipelines. 50K+ GitHub stars.

Memory engine and context API for AI assistants

Supermemory is a memory and context platform for AI assistants and agents. It ranks #1 on LongMemEval, LoCoMo, and ConvoMem, supports MCP for Claude/Cursor-style clients, provides plugins for developer tools, and combines memory extraction, user profiles, hybrid search, connectors, and RAG in one API.

Build AI-powered web apps

Open-source TypeScript toolkit by Vercel for building AI-powered apps with streaming chat UIs, structured outputs, tool calling, and agent workflows. Framework-agnostic core with integrations for React, Next.js, Svelte, Vue, and Nuxt. Supports a broad AI SDK v6 provider catalog including OpenAI, Anthropic, Google, xAI, Mistral, Bedrock, Groq, and OpenAI-compatible providers. Includes useChat and useCompletion hooks for rapid UI development. The standard SDK for adding AI features to web apps.

Open-source sandboxes and SDKs for AI agents that control desktops

Open-source computer-use infrastructure for agents that need to drive desktop environments in the background. CUA includes Cua Driver, Sandbox, Run, Bench, and Verified Data across Linux, Windows, macOS, and Android, with MCP and CLI surfaces for screenshots, accessibility trees, keyboard/mouse actions, shell commands, task evaluation, and fleet execution.

Stateful agent orchestration framework by LangChain

LangGraph is LangChain's framework for building stateful, multi-actor AI agent applications as controllable graphs. It models workflows as nodes and edges, enabling cycles, branching, and human-in-the-loop patterns that simple chains cannot express. Features built-in persistence for conversation memory, streaming support, and fault tolerance. Provides fine-grained control over execution flow while supporting single-agent and multi-agent architectures with shared or independent state.

TypeScript AI agent framework

TypeScript-native framework for building AI agents and workflows with great developer experience. Provides primitives for agents with tool calling, RAG pipelines, workflow orchestration with branching/parallel steps, and integration connectors. First-class TypeScript support with type-safe tool definitions. Local dev server with playground UI for testing. Growing as a LangChain alternative for TypeScript developers building AI apps.

Command center for Claude Code and Codex — monitor, steer, and voice-control your AI agents from any device.

Omnara is a command center for Claude Code and Codex sessions across desktop, web, mobile, and Apple Watch. Its public site supports cross-device supervision, parallel agents, worktrees, Git, and session-continuity language, with free-offer metadata; teams should verify detailed pricing, relay, privacy, and enterprise controls before standardizing it.

Official Python SDK for OpenAI agents

OpenAI's Python framework for building multi-agent AI applications with GPT models. Provides primitives for creating agents with tool calling, handoffs between specialized agents, guardrails for input/output validation, and tracing for observability. Supports building complex workflows where agents collaborate on tasks. Includes built-in tools for file search, code execution, and web browsing. Designed for production agent systems with structured output and error recovery patterns.

LLM testing and evaluation toolkit

Promptfoo is an OpenAI-owned open-source toolkit for evaluating, red-teaming and securing LLM applications. It supports config-driven prompt/model tests, CI regression gates, red-team scans, guardrails, model security workflows, MCP Proxy, code scanning and evaluations across prompts, agents and RAG pipelines.

Fully managed RAG-as-a-Service platform for enterprise AI applications

Ragie is a managed retrieval-augmented generation platform that handles document ingestion, indexing, and retrieval so developers can build grounded AI applications without managing vector databases or chunking pipelines. It connects to Google Drive, Notion, Slack, Confluence, and other enterprise data sources with simple APIs for hybrid search and entity extraction.

Pack your entire codebase into a single AI-friendly file

Repomix packages entire repositories into single AI-optimized files for feeding to LLMs like Claude, ChatGPT, and Gemini. It outputs XML, Markdown, JSON, or plain text with token counting, security scanning via Secretlint, and Tree-sitter-based code compression. Works as CLI, MCP server, or Chrome extension for GitHub. Supports Claude Agent Skills generation. 26K+ GitHub stars, MIT licensed, with a web interface at repomix.com for zero-install usage.

LSP-powered semantic coding agent via MCP

Serena is a free, open-source coding agent toolkit that provides IDE-like semantic code retrieval and editing capabilities to any LLM via the Model Context Protocol (MCP). Built on Language Server Protocol (LSP) integration, it enables symbol-level navigation, cross-file refactoring, and relational code understanding across Python, TypeScript, Go, Rust, Java, PHP, and more — without requiring file-level reads or text-based search.

Workflow automation with AI nodes

n8n is a source-available workflow automation platform for connecting apps, APIs, data, and AI models through visual workflows and code. It supports self-hosted deployments and n8n Cloud, with integrations across communication, databases, CRM, project management, and model providers. Teams can combine deterministic automation with AI-powered steps and agent workflows while retaining control over deployment and data.

AI agent framework for web browser automation

Browser Use is an open-source AI agent framework with 99K+ GitHub stars enabling LLMs to control web browsers via natural language. Y Combinator-backed, it lets agents navigate sites, fill forms, extract data, and complete multi-step tasks autonomously. Built on Playwright with vision-based element detection, multi-tab management, cookie persistence, and self-correcting actions. Supports OpenAI, Anthropic, and local models with a simple Python API for building custom browser agents.

Open data platform wrapping any SQL database with instant APIs

Directus is a database-first open data platform that wraps any existing SQL database with instant REST and GraphQL APIs, a no-code admin dashboard, and built-in authentication. Unlike traditional headless CMS platforms that impose their own data model, Directus introspects your existing schema and works on top of it — supporting PostgreSQL, MySQL, SQLite, MS SQL, MariaDB, and CockroachDB out of the box.

Graph RAG code knowledge graph for repository exploration

GitNexus is a code-knowledge-graph and Graph RAG app for exploring repository structure before humans or AI coding agents make changes. Write-time source checks support graph/RAG and local-server signals, but not hard local/server-architecture, 14-language, MCP, pricing, or licensing claims; evaluate privacy, scale, and integrations directly.

Official authenticated remote MCP endpoint for Linear issues, projects, comments, and coding-agent workflows.

Linear MCP Server is Linear’s official authenticated remote MCP endpoint for agent access to issues, projects, and comments. It gives Claude, Codex, Cursor, VS Code, Windsurf, Zed, and other clients a centrally hosted way to find, create, and update Linear work items through OAuth-backed MCP without maintaining a local connector or brittle API glue.

Official Python SDK for building MCP servers

The official Python SDK for the Model Context Protocol, enabling developers to build MCP servers and clients with asyncio support. Provides type-safe tool definitions, resource management, and all standard MCP transports. The most popular Python package for MCP development with comprehensive documentation.

Python agent framework by Pydantic team

Agent framework built on Pydantic for type-safe AI applications. Provides structured outputs, dependency injection, and multi-model support. Created by the Pydantic team, it brings the same validation and typing philosophy that made Pydantic essential for Python APIs to the world of AI agents, ensuring reliable data flow between LLMs and application logic.

AI-powered web browser automation with Playwright

Stagehand is an open-source browser-agent SDK from Browserbase that combines deterministic browser automation with AI primitives such as act(), extract(), observe(), and agent(). Instead of relying only on brittle selectors, developers can use natural-language actions, Zod-backed structured extraction, page observation, action caching, and Browserbase cloud-browser infrastructure for production web automation.

Agentic skills framework for disciplined coding-agent workflows

Superpowers is an MIT-licensed agentic skills framework and software-development methodology for coding agents. It packages repeatable workflows such as brainstorming, specs, implementation plans, TDD execution, subagent-driven development, and structured review so teams can move from ad hoc prompting to disciplined agent-assisted software delivery.

AI-driven task management for agentic coding

Taskmaster AI is an open-source task management system for AI-driven development that turns PRDs into structured, dependency-aware coding tasks. It runs as an MCP server inside Cursor, Claude Code, Windsurf, Lovable, and Roo, giving AI agents a disciplined workflow instead of ad-hoc code generation. Supports multiple AI providers with configurable main, research, and fallback models.

Microsoft’s public-preview runtime governance toolkit for policy, identity, sandboxing, audit, and MCP security around AI agents.

Agent Governance Toolkit is Microsoft’s MIT-licensed public-preview toolkit for governing AI agent runtimes. It adds policy enforcement, zero-trust identity, execution sandboxing, audit, reliability, and MCP security-gateway patterns around tool calls and autonomous actions, helping platform teams move beyond prompt-only guardrails while preserving architecture review requirements.

Headless browser cloud built for AI agents

Browserbase is cloud infrastructure that runs headless Chromium browsers on demand for AI agents and automation workflows, exposing Playwright, Puppeteer, and Selenium endpoints with built-in session replay, residential proxies, CAPTCHA solving, and stealth fingerprints. It also hosts Stagehand and a Model Gateway, letting teams build browser-using agents without maintaining their own fleet of Kubernetes-managed Chromium instances.

Codebase knowledge graph MCP server for AI coding agents

Codebase Memory MCP is an MIT-licensed MCP server that turns a repository into a persistent code knowledge graph for AI coding agents. It gives Claude Code, Cursor, Codex-style agents, and other MCP clients structural queries for functions, classes, call chains, routes, and architecture, helping them explore large projects without repeatedly rereading files or relying only on broad search.

Real-time web search and retrieval via MCP

Exa MCP Server provides AI coding agents with real-time web search and content crawling capabilities through the Model Context Protocol. It leverages Exa's neural search API for semantic understanding of queries, returning clean, structured results with full page content extraction. Supports both remote hosted MCP endpoints and local client configurations.

MCP server that gives coding agents structured Figma context for design-to-code work

Figma Context MCP is an MCP server for giving coding agents structured access to Figma design context during implementation. Instead of copying screenshots or hand-written design specs into prompts, teams can expose layout, component, and context information to agents such as Cursor, Claude Code, and other MCP-compatible coding workflows. It is a strong design-to-code bridge for teams trying to reduce hallucinated UI details and tighten handoff between designers and AI-assisted developers.

Web scraping and crawling via MCP for AI agents

Firecrawl MCP Server is the official MCP integration for Firecrawl, giving Cursor, Claude, Windsurf, and other MCP clients scrape, crawl, map, search, extract, and agent-style web research tools. It now supports a hosted remote endpoint, keyless rate-limited scrape/search/interact use, API-key/OAuth access for the full tool set, and self-hosted Firecrawl deployments.

AI IDE and collaboration platform for BYOK coding agents

HumanLayer is an AI IDE and collaboration platform for software-factory workflows with coding agents. Current positioning emphasizes tasks, artifacts, worktrees, multi-agent sessions, and BYOK Claude/Codex/API subscriptions rather than only human approval gates. Treat public code and product terms separately when evaluating open-source claims.

Always-on cloud engineer that lives in Slack and ships verified PRs

Roomote is a Slack-first cloud coding agent from RooCodeInc that takes prompts end-to-end across GitHub, Linear, Notion, Sentry, and your own dev environment, then opens self-verified pull requests for review. It is the team behind 24K+ star Roo Code going all-in on cloud agents: mention it in Slack, let it run in an isolated environment, and review the PR through your normal GitHub flow.

Go implementation of the Model Context Protocol SDK

mcp-go is a Go implementation of the Model Context Protocol, providing both server and client SDKs for building MCP integrations in Go. It supports stdio and SSE transports, resource management, tool registration, and prompt templates. Designed for Go developers building MCP servers for DevOps tools, CLI applications, and backend services. Over 8,000 GitHub stars.

Build and deploy AI chatbots and agents visually

Botpress is a conversational AI platform founded in 2017 that combines a visual Agent Studio with LLM-native architecture for building chatbots and autonomous agents. It offers a drag-and-drop flow builder, knowledge base indexing from documents and websites, an Autonomous Engine for generative AI workflows, and deployment across web chat, WhatsApp, Telegram, Slack, and other channels. Botpress runs as a cloud SaaS or self-hosted via Docker with pricing starting at $0/month pay-as-you-go.

Cloud browser automation via MCP for scalable testing

Browserbase MCP Server gives MCP clients a hosted or self-hostable browser through Browserbase and Stagehand. It exposes tools for starting sessions, navigating, acting, observing, extracting, and taking screenshots, with a hosted Streamable HTTP endpoint for easiest setup and local STDIO/Docker options for teams that want to run the Apache-licensed server themselves.