Claude Code Agents — 76+ Best AI Agents for Development (2026)
By PopularAiTools.ai
Best Claude Code Agents Directory (2026)
Discover and install the best Claude Code agents. Browse 76 curated agents with one-click installation.
Claude Code Agents are autonomous AI-powered workflows that can handle complex, multi-step tasks with minimal
human intervention. Unlike simple skills that augment a single interaction, agents orchestrate entire
workflows — from analyzing a codebase and planning changes to implementing, testing, and deploying solutions.
Agents represent the cutting edge of AI-assisted development. Each agent in this directory is designed for a
specific domain: frontend development, backend architecture, security auditing, data science, or full-stack engineering.
They combine multiple skills, tools, and decision-making logic into cohesive automated workflows.
Browse the best Claude Code agents available in 2026. These agents have been tested by the
community and rated for reliability, code quality, and real-world effectiveness. Sort by popularity or filter by
category to find the right agent for your needs.
Setting up an agent is as simple as installing a skill. Run the install command, configure any required settings,
and let the agent handle the heavy lifting. Agents work with your existing codebase, respect your project’s
conventions, and produce production-ready output.
The agent ecosystem is evolving fast, with new specialized agents being developed for niche use cases.
From automated code migration to intelligent test generation, agents are changing how teams
approach software development. Submit your own agent to share it with the community.
🔍
⭐ Popular
🕑 Newest
🔤 A – Z
76 agents found
Sorted by Popular
FullStack 🤖
Accessibility Expert
You are a world-class expert in web accessibility who translates standards into practical guidance for designers, developers, and QA. You ensure products are inclusive, usable, and aligned with WCAG 2
You are an expert in architectural documentation, this agent creates well-structured, comprehensive Architectural Decision Records that document important technical decisions with clear rationale, con
This skill provides a persistent, searchable memory bank that automatically syncs with project documentation. It runs as an MCP server to allow reading/writing/searching of long-term memories.
Send and receive cryptographically signed messages between AI agents. AMP works **locally by default** — no external dependencies needed for basic messaging. Part of the [AI Maestro](https://github.c
Create, manage, and orchestrate multiple AI agents through a unified CLI. Handles the full agent lifecycle: create, hibernate, wake, rename, export/import, and plugin management. Part of the [AI Maest
You help developers integrate Apify Actors into their projects. You adapt to their existing stack and deliver integrations that are safe, well-documented, and production-ready.
Autonomous multi-agent coding framework for Claude Code (Claude Agent SDK) that integrates the full SDLC – "plans, builds, and validates software for you". Features a slick kanban-style UI and a well-
This mode serves as a code-first orchestration layer, enabling Claude to write, edit, test, and optimize code autonomously across recursive agent cycles.
Claude Squad is a terminal app that manages multiple Claude Code, Codex (and other local agents including Aider) in separate workspaces, allowing you to work on multiple tasks simultaneously.
A specialized tool to manage context isolation and focused task execution with Claude Code, solving the critical challenge of context length limitations and task focus when working with Claude on comp
Pre-commit verification agent that runs 10 automated checks before every git commit. If any check fails, the commit is blocked and the issue is reported for resolution.
Flows provide event-driven orchestration with precise control over execution paths, state management, and conditional branching. Use Flows when you need more control than Crews provide.
When you have multiple unrelated failures (different test files, different subsystems, different bugs), investigating them sequentially wastes time. Each investigation is independent and can happen in
Spawn and control multiple Claude Codes in parallel from your phone or desktop. Happy Coder runs Claude Code on your hardware, sends push notifications when Claude needs more input or permission, and
Language Specialists are your expert guides for specific programming languages and their ecosystems. These subagents bring deep knowledge of language idioms, best practices, performance optimization t
Schmidt – Yet Another Claude Orchestrator – a collection of agents, commands, etc., for shipping production code – but I like this because it's comprehensive, well-written, and one of the few resource
A Rust CLI tool that lets you delegate development tasks to AI agents running in sandboxed Docker environments. Multiple agents work in parallel, returning git branches for human review.
> Design patterns for building autonomous coding agents, inspired by [Cline](https://github.com/cline/cline) and [OpenAI Codex](https://github.com/openai/codex).
Frequently Asked Questions about Claude Code Agents
Claude Code Agents are autonomous AI workflows that handle complex, multi-step development tasks. Unlike simple commands, agents can plan, execute, test, and iterate on solutions with minimal human oversight.
Skills provide expertise for a single interaction, while agents orchestrate entire workflows. An agent might analyze your codebase, plan a refactoring strategy, implement changes across multiple files, write tests, and verify everything works — all autonomously.
Agents are designed to work safely with your codebase. They respect git branching, create isolated changes, and include safety checks. However, we always recommend reviewing agent-generated changes before merging into production branches.
Most agents are language-agnostic and work with any language Claude Code supports. Some specialized agents are optimized for specific languages or frameworks. Check the agent’s description for language compatibility details.
After installation, agents typically read your project’s configuration files (package.json, pyproject.toml, etc.) to understand your tech stack. Some agents offer additional configuration options via their settings file.
Yes, you can create custom agents by combining skills, MCP servers, and workflow logic. The Claude Code agent SDK provides tools for building, testing, and distributing your own agents to the community.
{
“@context”: “https://schema.org”,
“@type”: “FAQPage”,
“mainEntity”: [
{
“@type”: “Question”,
“name”: “What are Claude Code Agents?”,
“acceptedAnswer”: {
“@type”: “Answer”,
“text”: “Claude Code Agents are autonomous AI workflows that handle complex, multi-step development tasks. Unlike simple commands, agents can plan, execute, test, and iterate on solutions with minimal human oversight.”
}
},
{
“@type”: “Question”,
“name”: “How do agents differ from skills?”,
“acceptedAnswer”: {
“@type”: “Answer”,
“text”: “Skills provide expertise for a single interaction, while agents orchestrate entire workflows. An agent might analyze your codebase, plan a refactoring strategy, implement changes across multiple files, write tests, and verify everything works — all autonomously.”
}
},
{
“@type”: “Question”,
“name”: “Are agents safe to use on production code?”,
“acceptedAnswer”: {
“@type”: “Answer”,
“text”: “Agents are designed to work safely with your codebase. They respect git branching, create isolated changes, and include safety checks. However, we always recommend reviewing agent-generated changes before merging into production branches.”
}
},
{
“@type”: “Question”,
“name”: “Can agents work with any programming language?”,
“acceptedAnswer”: {
“@type”: “Answer”,
“text”: “Most agents are language-agnostic and work with any language Claude Code supports. Some specialized agents are optimized for specific languages or frameworks. Check the agent’s description for language compatibility details.”
}
},
{
“@type”: “Question”,
“name”: “How do I configure an agent for my project?”,
“acceptedAnswer”: {
“@type”: “Answer”,
“text”: “After installation, agents typically read your project’s configuration files (package.json, pyproject.toml, etc.) to understand your tech stack. Some agents offer additional configuration options via their settings file.”
}
},
{
“@type”: “Question”,
“name”: “Can I create a custom agent?”,
“acceptedAnswer”: {
“@type”: “Answer”,
“text”: “Yes, you can create custom agents by combining skills, MCP servers, and workflow logic. The Claude Code agent SDK provides tools for building, testing, and distributing your own agents to the community.”
}
}
]
}
(function() {
var activeCat = ‘all’;
window.ecoFilter = function() {
var query = document.getElementById(‘eco-search’).value.toLowerCase().trim();
var cards = document.querySelectorAll(‘#eco-grid > div[data-name]’);
var visible = 0;
cards.forEach(function(card) {
var name = (card.getAttribute(‘data-name’) || ”).toLowerCase();
var desc = (card.getAttribute(‘data-desc’) || ”).toLowerCase();
var cat = (card.getAttribute(‘data-cat’) || ”).toLowerCase();
var matchSearch = !query || name.indexOf(query) !== -1 || desc.indexOf(query) !== -1;
var matchCat = activeCat === ‘all’ || cat === activeCat.toLowerCase();
if (matchSearch && matchCat) {
card.style.display = ”;
visible++;
} else {
card.style.display = ‘none’;
}
});
document.getElementById(‘eco-count-num’).textContent = visible;
document.getElementById(‘eco-no-results’).style.display = visible === 0 ? ‘block’ : ‘none’;
};
