Agent Skills & Prompts

Microsoft's zero-code-change RL trainer for AI agents

Agent Lightning is Microsoft Research's open-source framework that makes AI agents trainable through reinforcement learning with virtually zero code changes. Supports RL, Automatic Prompt Optimization, and Supervised Fine-tuning across any agent framework including LangChain, OpenAI Agents SDK, AutoGen, and CrewAI. 14K+ GitHub stars, ranked among Microsoft's top 50 most-starred projects.

Open standard for portable skills across AI agents

Agent Skills is the open SKILL.md folder specification for packaging reusable instructions, scripts, references, and assets that compatible AI agents load through progressive disclosure. Originally developed by Anthropic and released as an open standard, it defines the portable format itself—not an example library, marketplace, or hosted agent product.

Transparent AI agent framework with 100+ skills and real-time visibility

Agent Zero is an open-source general-purpose AI agent framework with 16,700+ GitHub stars that uses the computer itself as a tool. Unlike structured orchestration frameworks, it provides full transparency where every thought, action, and tool call is visible and editable in real time, supporting 100+ extensible skills.

Browser-based autonomous AI agent platform

AgentGPT is an open-source browser-based platform with 36K+ GitHub stars for creating and deploying autonomous AI agents without any setup or installation. Give an agent a name and goal in plain language, and it autonomously decomposes the objective into subtasks, executes them, and iterates toward completion. Built with Next.js and supports multiple LLM providers. Features include web search, code execution, and task chaining. No technical expertise required to create functional AI agents.

Email API service that gives AI agents their own inboxes and identities

AgentMail is a YC S25 startup that provides email infrastructure specifically designed for AI agents. It gives each agent its own email address and inbox, enabling agents to send, receive, and manage email conversations independently. With $6 million in seed funding from General Catalyst and Paul Graham, and over 500 B2B customers, AgentMail solves the identity and communication gap that arises when organizations deploy autonomous agents that need to interact via email.

Production-ready multi-agent platform by Alibaba

AgentScope is an open-source multi-agent platform with 22K+ GitHub stars developed by Alibaba. Designed for production-ready multi-agent applications with built-in distributed execution, fault tolerance, and agent-to-agent messaging. Features memory management with compression, a drag-and-drop workstation for visual agent building, multi-modal support, and flexible pipelines for sequential, parallel, and conditional agent orchestration. Supports all major LLM providers.

TypeScript AI agent standard library

Standard library of AI tools and integrations for TypeScript-based agents. Works with any AI SDK and includes ready-made integrations for search, web scraping, email, and other common tool patterns. Saves developers from rebuilding common agent capabilities from scratch, providing well-tested, type-safe building blocks for rapid AI agent development.

AI-driven development workflow template

A template system that bootstraps AI-driven development workflows for your projects. Provides structured workflows, templates, and configurations for integrating AI agents into your development process. Reduces setup time by giving teams a proven starting point for organizing AI-assisted coding, task management, and quality assurance in new and existing repositories.

Non-agent approach to automated software engineering via localize-and-repair

Agentless takes a deliberate non-agent approach to LLM-powered software engineering. Instead of autonomous agents making tool calls, it uses a structured localize-then-repair pipeline: first narrowing down which files and functions are relevant, then generating targeted patches. Achieved competitive SWE-Bench results at $0.34 average cost per issue. Adopted by OpenAI for o3 evaluations. 3,000+ GitHub stars, MIT licensed. A counterpoint to the agent-heavy trend in AI coding tools.

Cloud browser infrastructure for AI agents

Anchor Browser provides secure cloud-managed browser infrastructure for computer-use agents. Deploy humanized Chromium instances that access any website while maintaining bot-detection evasion and authentication support. Features OmniConnect for authentication lifecycle management, Web Action Cache for deterministic workflows, and built-in VPN infrastructure. Includes free tier and paid plans supporting millions of concurrent browser sessions for scalable agent automation.

Official SDK for building Claude-powered agentic applications

Anthropic's official SDK for building agents with Claude. Provides high-level abstractions for tool use, multi-turn conversations, computer use, and agent loops on top of the Claude API. Simplifies the development of production-grade agents by handling common patterns like retry logic, context management, and tool orchestration in a well-tested library.

Official Claude Agent Skills examples, spec, and plugin marketplace for reusable agent capabilities

Anthropic Agent Skills is Anthropic's official reference repo and Claude Code plugin marketplace for reusable Skill folders. It packages example SKILL.md workflows, document skills, a Claude API skill, templates, and the Agent Skills spec so teams can turn repeatable instructions, scripts, and resources into on-demand Claude capabilities instead of copying prompts across sessions.

Tool platform for AI agents

Arcade AI is an MCP runtime platform for secure agent authorization, reliable tool execution, and governance. It enables enterprises to deploy authenticated AI agents across Gmail, Slack, Salesforce, and 100+ other services without managing OAuth complexity or token refresh cycles. Arcade provides a centralized authorization layer that handles authentication, permission scoping, and compliance for every tool call an agent makes.

AI agent that builds other AI agents

Archon is an open-source AI meta-agent created by Cole Medin that autonomously builds, refines, and optimizes other AI agents. Now evolving into Archon OS, it serves as a knowledge and task management backbone for AI coding assistants. The system uses an agentic coding workflow with framework knowledge bases for Pydantic AI, LangGraph, and other agent frameworks, enabling developers to describe what they need and let Archon generate the agent code, test it, and iterate until it works.

Official Asana remote MCP server for project and task workflows.

Asana MCP Server is Asana's official hosted MCP endpoint for connecting compatible AI clients to Asana work data. It lets authenticated users search workspace objects, inspect and manage tasks or projects, create work items, and generate project summaries through OAuth-backed Streamable HTTP access while preserving existing Asana permissions and admin app-management controls.

Agentic IM chatbot platform with multi-platform LLM integration

AstrBot is an open-source agentic chatbot infrastructure that connects multiple instant messaging platforms including Telegram, Discord, Slack, WeChat, QQ, Feishu, and DingTalk to AI language models. It supports multi-provider LLM integration, MCP protocol, knowledge bases, persona management, multimodal input, and a plugin ecosystem with over 1,000 community extensions. Features include a web management UI, sandbox code execution, and auto-context compression for efficient conversations.

Official remote MCP server for Jira and Confluence

Atlassian's official remote MCP server connects Jira and Confluence to LLM clients, IDEs, and agent platforms over OAuth, so Claude, Cursor, and other MCP-aware tools can search issues, read pages, and post updates inside the same permission boundaries users already have. As a vendor-hosted reference implementation, it standardizes the Atlassian side of remote Model Context Protocol deployments.

Build AI agents like LEGO — modular and predictable

Atomic Agents is a lightweight Python framework by BrainBlend AI that applies Atomic Design principles to AI agent development. Each component — agents, tools, context providers — is a single-purpose, reusable building block with Pydantic-enforced input/output schemas for type safety. Built on Instructor for structured LLM outputs, it prioritizes predictability and developer control over the autonomous-but-unpredictable behavior of larger frameworks like LangChain or CrewAI.

Open-source autonomous AI agent platform

AutoGPT is an open-source autonomous AI agent platform with 183K+ GitHub stars that breaks goals into subtasks and executes them independently. Features a visual Agent Builder for creating workflows without coding, persistent cloud-based agents running on triggers, a marketplace of pre-built agents, and a plugin system. Agents can browse the web, write code, manage files, and call tools autonomously while maintaining memory across sessions.

AI agents running automated research

Autonomous research framework by Andrej Karpathy that lets AI agents plan and execute machine learning experiments end-to-end. Agents design experiments, run training loops, analyze results, and iterate on hypotheses with minimal human oversight. Runs efficiently on single-GPU setups and applies agentic patterns beyond software development — bringing autonomous agent workflows to the research process itself.

Curated collection of agent skills and capabilities

An opinionated project scaffolding tool that generates AI-ready codebases with pre-configured CLAUDE.md files, git hooks, and CI/CD templates. Ensures new projects follow best practices for AI-assisted development from day one, including structured prompts, context files, and workflow configurations that help AI coding agents understand and navigate the codebase effectively.

Curated Claude Code resources

Official Anthropic-curated list of Claude Code tips, CLAUDE.md templates, hooks, MCP servers, and community tools. Essential reference for Claude Code users looking to optimize their workflow. Covers everything from initial setup and configuration best practices to advanced patterns like custom hooks and multi-agent orchestration with the Claude Code CLI.

Type-safe LLM function builder

BAML is a domain-specific language by BoundaryML for building reliable AI workflows and agents through schema engineering. It turns prompt engineering into a structured, type-safe discipline by letting developers declaratively define function schemas, validate LLM responses, and version prompts without fragile JSON parsing or boilerplate. BAML reframes prompt engineering as schema definition, making AI workflows testable and maintainable across models.

Markdown-based project management for AI agents

A tool for managing project collaboration between humans and AI agents in a git ecosystem. Uses markdown files as the source of truth for backlogs, tasks, and progress tracking. Keeps everything version-controlled and transparent, making it easy to assign work to AI agents and review their contributions alongside human commits.

Python and TypeScript framework for production multi-agent systems

BeeAI Framework is an Apache-2.0 toolkit for building production-ready AI agents and multi-agent systems in Python and TypeScript. Its docs cover agents, tools, RAG, memory, workflows, backend providers, serving, and A2A/MCP integration surfaces, making it a vendor-neutral option for teams comparing LangGraph, CrewAI, Mastra, and related agent runtimes.

50x faster LLM gateway with MCP support, built in Go

Bifrost is a high-performance open-source AI gateway built from scratch in Go. Unifies access to 15+ providers and 1,000+ models through a single OpenAI-compatible API with only 11 microsecond overhead per request at 5K RPS — 50x faster than LiteLLM. Features automatic failover, load balancing, semantic caching, and functions as both MCP client and MCP server. Apache 2.0 licensed.

Connect Blender to AI through Model Context Protocol

BlenderMCP bridges Blender and AI assistants like Claude through the Model Context Protocol, enabling natural language control over 3D modeling workflows. Artists and developers can create, modify, and manipulate 3D scenes, objects, materials, and animations by describing what they want instead of navigating complex menus. The tool exposes Blender's Python API through MCP, supporting operations from mesh creation to shader editing and physics simulations.

Automate local Chrome browser via MCP

BrowserMCP is an MCP server that enables AI agents to automate a local Chrome browser — navigating pages, clicking elements, filling forms, extracting content, and taking screenshots. It gives coding agents the ability to interact with web applications the way a human would, directly from Claude Desktop, Cursor, or any MCP client.

Open-source agentic browser that runs local AI agents in your browsing workflow.

BrowserOS is a privacy-first, open-source agentic browser for running AI assistants locally inside real browsing sessions instead of handing every task to a remote cloud browser.

State machine framework for AI agent tracking

Burr is an open-source Python framework for building applications as state machines with built-in observability and persistence. Designed for AI agents, chatbots, and RAG pipelines where tracking state transitions, debugging decisions, and replaying execution is critical. Features automatic state persistence, a visual UI for inspecting execution flows, time-travel debugging, and integration with LangChain, OpenAI, and any Python code. Apache 2.0 licensed by DAGWorks.

Persistent structured memory layer for AI coding agents

ByteRover CLI provides a persistent, structured memory layer for AI coding agents. It lets you curate project knowledge into a context tree that syncs to the cloud and shares across tools and teammates. Supports 20+ LLM providers with 24 built-in agent tools for code execution, file operations, and memory management. Achieves 96.1% accuracy on the LoCoMo benchmark. SOC 2 Type II certified.

Multi-agent framework for finding scaling laws of agents

CAMEL-AI is an open-source multi-agent framework with 16,500+ GitHub stars, built by a research community of over 100 researchers focused on finding the scaling laws of agents. It supports role-playing agent societies, synthetic data generation pipelines, large-scale social simulations with up to 1M agents via the OASIS platform, and real-world task automation through the OWL project accepted at NeurIPS 2025. CAMEL works with OpenAI, Anthropic, Gemini, Mistral, and local models.

Multi-agent software company simulation for automated development

ChatDev simulates an entire virtual software company through multi-agent collaboration where LLM-powered roles including CEO, CTO, programmer, tester, and designer work together to produce complete software. With 32,000+ GitHub stars and a NeurIPS 2025 accepted paper, it offers a novel approach to automated software development through role-based agent orchestration.

Official agent SDK by Anthropic

Anthropic's Python SDK for building agentic AI applications powered by Claude models. Provides primitives for creating agents with tool use, multi-step reasoning, guardrails, handoffs between specialized agents, and structured output. Supports building complex agent workflows with tracing and observability. Designed for developers building production AI agents that interact with external systems, databases, and APIs using Claude as the reasoning backbone.

Claude's inline code and document generation tool

Claude's built-in capability to generate and render interactive artifacts — code, documents, SVGs, React components, and HTML — directly inline within the conversation. No setup required. Turns Claude from a text-only assistant into a creative tool that can produce runnable applications, visualizations, and interactive prototypes during natural conversation.

Heads-up display plugin for Claude Code

Real-time visibility layer for Claude Code sessions that surfaces context window usage, active tools, token consumption, and task status directly in your terminal. Turns the opaque agentic loop into a transparent, monitorable process. Particularly useful during long-running agent sessions where understanding resource consumption and progress helps you decide when to intervene, redirect, or let the agent keep working.

AI-powered task management for agentic coding workflows

Claude Task Master is an AI-powered task management system designed for agentic development workflows in IDEs like Cursor, Windsurf, Lovable, and Roo. It breaks complex projects into structured task trees with dependencies, priorities, and complexity scores so AI coding agents can execute work methodically. The MCP server integration enables direct task operations from any compatible client, while tagged task lists support multi-context management across branches and environments.

Persistent memory plugin for Claude Code with automatic context injection

Claude-Mem is a persistent memory plugin for Claude Code with 44,000+ GitHub stars that captures session context and injects it into future sessions. It features progressive disclosure with token cost visibility, automatic compression, and privacy controls with private tags to manage what gets remembered across coding sessions.

Build and deploy AI agents on Cloudflare's edge network

Cloudflare Agents is an open-source SDK for building and deploying AI agents that run on Cloudflare's global edge network. It provides durable state, scheduled tasks, WebSocket communication, and browser rendering capabilities within Workers. Agents persist across requests using Durable Objects and can orchestrate multi-step workflows with built-in MCP server support. Over 7,000 GitHub stars.

MCP integration for Cloudflare Workers and edge services

Cloudflare MCP Server connects AI coding agents to Cloudflare's edge platform through the Model Context Protocol. It enables agents to manage Workers, KV stores, R2 storage, D1 databases, and other Cloudflare services directly from AI assistants, streamlining edge application development and deployment workflows.

Knowledge graph memory engine for AI agents

Cognee is an open-source knowledge engine that builds persistent memory for AI agents by combining vector search with graph databases. It ingests data from 38+ source formats, structures information into a knowledge graph with embeddings, and enables semantic and relational queries through its ECL pipeline. Its cognitive science-inspired architecture provides superior cross-document entity identification compared to traditional RAG approaches.

Workflow orchestration engine

Netflix-originated workflow orchestration platform with JSON and code-based workflow definitions, human-in-the-loop support, and AI agent orchestration capabilities. With 18k+ GitHub stars, Conductor handles complex distributed workflows at massive scale, offering built-in retry logic, event-driven triggers, and visual workflow monitoring for microservice coordination.

Context engineering patterns for AI coding assistants

Context Engineering Intro is an open-source repository by Cole Medin providing structured context engineering patterns for AI coding assistants. Built around Claude Code, it includes .claude command files, PRP templates, and the WISC framework for managing AI context in coding sessions. The repo shows how to structure project context and rules so AI assistants produce reliable, architecture-aware code. With 13K+ GitHub stars, it is a go-to reference for context-first AI coding.

Full-stack framework for building AI copilots with generative UI

CopilotKit is an open-source full-stack framework for building AI-native applications with generative user interfaces. It provides React and Angular SDKs that enable agents to dynamically generate and render UI components, synchronize state between frontend and backend in real time, and implement human-in-the-loop workflows. Supports integration with LangChain, LangGraph, CrewAI and protocols including AG-UI, MCP, and A2A for standardized agent interaction.

Full-lifecycle AI agent optimization and monitoring

CozeLoop is an open-source AI agent optimization platform from ByteDance's Coze ecosystem providing full-lifecycle management from development to production monitoring. It enables developers to debug agent prompts, evaluate agent performance across test cases, optimize reasoning processes, and monitor deployed agents in real-time. Built on Go and React with SDKs for Go, Python, and Node.js, CozeLoop is designed for enterprise-grade AI agent development and operation.

The 5MB open-source agent daemon that hides nothing

CrabTalk is a lightweight five-megabyte daemon that streams every AI agent event to your client in real time including text deltas, tool calls, and thinking steps. It provides complete transparency into agent operations with one-curl installation and bring-your-own-model support. Designed as the observable alternative to opaque agent runtimes where you cannot see what the AI is actually doing.

Community cursor rules directory

Community-maintained collection of .cursorrules files that customize Cursor IDE's AI behavior for specific frameworks, languages, and project types. Define coding conventions, preferred libraries, architectural patterns, and style guidelines that the AI follows consistently. Popular rules exist for Next.js, React, Python, TypeScript, Tailwind, and more. Hosted on cursor.directory with 1-click installation. Essential for getting consistent, project-aware AI completions in Cursor.

OpenAI's custom chatbot builder and GPT Store

Create personalized GPT assistants with custom instructions, knowledge files, and tool integrations including browsing, DALL-E, and code interpreter. Publish to the GPT Store or keep private with no coding required. Enables anyone to build specialized AI assistants for specific domains, workflows, or audiences using OpenAI's consumer-friendly builder interface.