AI coding assistants & agents: top picks for 2026

MCP server and CLI letting AI agents reverse engineer native binaries, Electron apps, .NET assemblies and websites.

A skills framework and software development methodology that guides coding agents through brainstorming, planning, TDD, and reviewed subagent-driven implementation.

A collection of agent skills for coding assistants like Claude Code and Codex, covering grilling sessions, TDD, bug diagnosis, planning and code review.

A prompt-based skill that makes AI coding agents write only the code a task needs, favoring reuse and minimal solutions over large implementations.

A large collection of role-specific AI agent prompt files (engineering, design, marketing, sales, security and more) that install into tools like Claude Code, Cursor and Gemini CLI.

Turns a codebase, its docs, schemas and PDFs into a queryable knowledge graph for AI coding assistants, built locally with tree-sitter AST parsing.

A minimal, extensible AI agent harness with a unified multi-provider LLM API, agent runtime, terminal UI, and a coding agent CLI.

A set of production-grade engineering workflow skills, packaged as Markdown, that guide AI coding agents through spec, plan, build, test, review, and ship.

Local-first, open-source AI design agent workspace that turns briefs into prototypes, decks, dashboards, images and videos using your own coding agent.

Agent Skills that make coding agents design distinctive frontends, using art direction, real photos and a browser self-check instead of generic AI landing pages.

Desktop app for running multiple coding agents side by side, each in its own git worktree, with a mobile companion for monitoring.

An agent skill that turns ideas, plans, or codebases into interactive HTML diagrams for Claude Code, Codex, Cursor and OpenCode.

CLI proxy that filters and compresses shell command output before it reaches an AI coding agent's context, cutting token use.

Design guidance for AI coding agents, with a design skill, 24 commands, live browser iteration and 61 deterministic detector rules for AI-generated frontend UI.

Self-hostable MIT AI gateway that exposes one OpenAI-compatible endpoint to hundreds of model providers, with quota-aware auto-fallback and token compression.

Compresses tool outputs, logs, files and RAG chunks before they reach an LLM, as a library, proxy or MCP server.

A spec-driven development workflow for AI coding assistants that agree on proposals, specs and tasks before any code is written.

A self-hosted, all-in-one software development service written in Go, covering Git hosting, code review, issues, packages and CI/CD.

An agent skill that makes editorial diagrams as one self-contained HTML + SVG file, with 45 diagram types and brand matching.

A free, open-source Chinese-language book on AI Agent design principles and engineering practice, with 109 companion experiments and downloadable PDF/EPUB.

A Rust terminal workspace that runs coding agents in persistent panes, tracks which ones are working, blocked, or idle, and lets agents control it via CLI and socket API.

Anthropic-managed marketplace of curated, vetted plugins that extend Claude Code with commands, agents, skills and MCP servers.

A marketplace of 94 plugins, 202 agents, 185 skills and 105 commands for Claude Code, Codex CLI, Cursor, OpenCode, Copilot, Antigravity and Pi.

A terminal coding agent with built-in LSP, debugger, browser and subagent tools, supporting 60+ model providers.

An open-source coding agent that reads your project, edits files and runs tests from your terminal, desktop, browser or editor.

GitHub's official MCP server that lets AI assistants read repositories, manage issues and pull requests, and work with GitHub Actions.

A local code knowledge graph that gives AI coding tools precise review context over MCP and a CLI.

A coding-agent skill that runs multi-phase security audits with isolated agents, independent verification, and machine-readable findings.

A design skill for Claude Code, Cursor, and Codex that guides AI coding agents toward UI that doesn't look AI-generated.

An MCP server that gives coding agents IDE-level symbol search, semantic editing and refactoring over a codebase.

Persistent memory for AI coding agents that captures sessions automatically and injects relevant context into later sessions across Claude Code, Cursor, Codex and other MCP clients.

A native macOS terminal built on libghostty, with vertical tabs, agent-aware notifications and a scriptable CLI for running AI coding agents in parallel.

A mobile, web and desktop app that runs Claude Code, Codex and Grok sessions from one place, using your existing subscriptions.

A macOS menu bar app that shows usage limits, reset times, and spend for 100+ AI coding and API providers, without storing passwords.

An open-source coding and research agent built on a persistent Python REPL, with subagents, a self-refining harness, and support for long-running tasks.

Desktop, mobile, web and CLI app for running and orchestrating multiple coding agents such as Claude Code, Codex and OpenCode in parallel worktrees.

A hands-on Vibe Coding course that teaches non-programmers and developers to build real AI-assisted products from idea to launch.

A curated, community-maintained list of plugins for DeepSeek Harness (dsh), a coding agent built on a plugin-based framework.

Go-based workspace manager that coordinates multiple AI coding agents such as Claude Code, Copilot and Codex, persisting their work state in git-backed hooks.

A browser built for AI agents and you to share: agents run tasks in isolated Spaces while your own tabs and logins stay untouched.

A local proxy that lets Codex, Claude Code, Claude Desktop and Grok Build run any LLM provider.

A local gateway and menu bar app that lets Claude Code, Codex, Gemini CLI and other coding agents use any model from any provider or subscription.

Official AI agent skills that teach coding assistants to use the GSAP animation library correctly, covering core API, timelines, ScrollTrigger and plugins.

A CLI and agent skill that scans React codebases for state, performance, security, accessibility and maintainability issues.

An agent skill for Claude Code and Codex that turns your product pages into cinematic promo videos, built with Remotion code rather than generative AI.

Layout rules and templates that let AI agents export documents as PDF, PNG and editable PowerPoint.

Local CLI and desktop app that breaks down your AI coding token spend and cost by tool, model, project and task.

A CLI and TypeScript SDK from OpenAI for scanning code for security vulnerabilities, validating findings, and generating fixes.

Long-term memory for AI coding agents that carries project context and handoffs across Claude Code, Codex, Cursor and other agent CLIs.

Source control for coding agents: links each commit to the agent session that produced it, and lets multiple agents share one project memory.

A GitHub Action that runs Claude Code on PRs and issues to answer questions, review changes, and implement code.

A local browser-based review surface that lets you annotate agent plans, markdown, HTML and code diffs, then send feedback back to coding agents.

A collection of Agent Skills and plugins that let coding agents work with Google Stitch design projects through the Stitch MCP server.

Z.ai's AI coding workspace offering a desktop app, browser UI, and terminal agent, built on a shared TypeScript codebase.

A TypeScript CLI and terminal UI for defining, launching and running persistent teams of Claude Code and Codex agents in tmux.

A desktop app to manage, sync, and organize AI agent skills across Claude Code, Codex, Cursor, Copilot, Gemini CLI and other coding tools.

An agent skill that teaches AI coding assistants like Claude Code and Codex to write modern, correct SwiftUI code.

An Agent Skill that guides AI agents to generate simple, rounded, cute IP mascot images with a solid background color.

A macOS notch companion (plus Windows, Linux and phone apps) that shows live sessions from AI coding agents like Claude Code and Codex and lets you approve their requests.

A collection of Claude Code skills from HumanLayer for research, design, PR review visuals, and agentic coding workflows.