The full matrix · 2026
All 9 AI coding tools, side by side
Every major AI coding tool in 2026, compared across the criteria that actually matter for picking one: interface, model, pricing, agent depth, MCP + skills support, open source, voice mode.
| Tool | Vendor | Launched | Interface | Default model | Pricing | Agent mode | Sub-agents | Scheduled | Autocomplete | MCP | Skills | Open source | Voice |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Claude Code | Anthropic | Oct 2024 | Terminal + IDE plugins (VS Code, JetBrains, Zed) | Claude Opus 4.7 / Sonnet 4.6 | Bundled with Claude Pro $20/mo or Max $100, $200/mo | Best in 2026, sub-agents + scheduled tasks | ✓ Yes | ✓ Yes | Limited | First-class | Native | Proprietary | ✓ Yes |
| Cursor | Anysphere | 2023 | VS Code fork | Claude, GPT, Gemini (selectable) | $20/mo Pro | Composer + agent mode (mature) | , No | , No | Best-in-class | Native | Via skills-hub CLI | Proprietary | , No |
| Antigravity 2.0 | May 2026 (I/O) | Desktop app + Go CLI + SDK | Gemini 3.5 Flash | Free tier + Google AI subscription | Native multi-agent architecture | ✓ Yes | ∼ Via skills | Strong | Native | Via MCP | SDK only | ✓ Yes | |
| GitHub Copilot | GitHub / Microsoft | 2021 (Copilot) | VS Code / JetBrains / Visual Studio / Neovim extension | GPT, Claude, Gemini (selectable) | $10/mo individual, $19+/user team, $39/user Enterprise | Copilot Workspace (beta) | , No | , No | Best-in-class | Native | Via MCP | Proprietary | , No |
| Windsurf | Codeium | Jun 2025 | VS Code fork | Claude, GPT, Codeium models | $15/mo Pro | Cascade flows | ∼ Via Cascade | , No | Strong | Native | Via MCP | Proprietary | , No |
| Codex CLI | OpenAI | Mar 2025 (open-source) | Terminal CLI | GPT-5 / GPT-5.5 | Bundled with ChatGPT Pro/Plus $20, $200/mo | Strong terminal agent | , No | , No | Limited | Native | Native | ✓ Open | , No |
| Cline | Cline Bot Inc. | Sep 2025 (1.0) | VS Code extension | Any (BYO API key) | Free (BYO API key) | Per-step approval agent | , No | , No | Limited | Native | Via MCP | ✓ Open | , No |
| AWS Kiro | AWS / Amazon Bedrock | Jan 2026 | VS Code-based IDE | Amazon Bedrock (Claude, Llama, Titan) | Pay-as-you-go via AWS Bedrock | Spec-driven loop | ∼ Via Cascade | , No | Strong | Via Bedrock AgentCore | Via MCP | SDK only | , No |
| Gemini CLI | 2025 | Terminal CLI | Gemini 2.5 Pro / 3.5 Flash | Free for individual use | Strong terminal agent | , No | , No | Limited | Native | Via MCP | ✓ Open | , No |
How to read this matrix
- Sub-agents = native parallel isolated agents with their own context windows. Currently only Claude Code and Antigravity 2.0 have first-class support.
- Scheduled = cron-style background runs. Only Claude Code's /loop is native; others require external cron or skills.
- Autocomplete = inline tab completion quality. "Best" = best-in-class; "Strong" = comparable to leaders; "Limited" = not the tool's focus.
- MCP = Model Context Protocol support quality. First-class = native + first-party servers; Native = full client support; Via Bedrock = routed through AWS AgentCore.
- Skills = SKILL.md (Agent Skills standard) support. Native = recognized as a first-class concept; Via MCP = available through MCP prompts; Via skills-hub CLI = installs via npx into the right per-tool directory.
Need a recommendation?
5-question quiz that recommends the right tool for your stack and workflow.
Take the quiz →Want head-to-head?
31 pairwise comparison pages, Claude Code vs Cursor, Cursor vs Windsurf, Antigravity vs Kiro, and more.
All comparisons →One skills catalog, all 9 tools
Skills follow the open Agent Skills standard. Install once, use in any tool above.
Browse 4,900+ skills →