Gemma 4

Cursor Composer 2 is an advanced agentic coding model built into the Cursor IDE, released March 19, 2026. With a 200,000-token context window, it autonomously plans and executes complex, multi-file coding tasks across an entire codebase — handling file edits, terminal operations, and tool use at frontier-level performance. It is used by over 50,000 businesses including Stripe.

GStack is an open-source Claude Code workflow system created by Y Combinator CEO Garry Tan, designed to encode specialized AI roles for planning, code review, QA, and shipping. Built with Bun and Playwright, it uses route-aware QA and structured release workflows to connect code changes with actual application behavior. Enables developers to achieve 10,000+ lines of quality code per week.

Kilo Code is an open-source AI coding agent for VS Code, JetBrains, and CLI that generates code from natural language, automates complex tasks, and runs terminal commands. It supports 500+ AI models at provider rates and features an Orchestrator mode that breaks complex tasks into coordinated subtasks across planner, coder, and reviewer agents. With 1.5M+ users and 25T+ tokens processed, it's the #1 coding agent on OpenRouter.

Low-code AI builder for agentic and RAG applications. Build and deploy AI agents and MCP servers with a visual drag-and-drop interface, supporting all major LLMs, vector databases and a growing library of AI tools.

Amp is an agentic coding platform that combines a powerful code review agent, composable extensions, and a unique 'oracle' reasoning layer powered by GPT-5.4 for complex analysis tasks. It offers a free ad-supported tier alongside paid smart plans, with the code review agent now composable and extensible for team workflows. Amp is one of the fastest-growing AI coding tools of early 2026.

A terminal-native, open-source AI coding agent from Mistral AI, powered by the Devstral 2 model. Mistral Vibe provides natural language code automation directly in your command line, with multi-file orchestration, smart codebase references, IDE extensions, and async agent workflows. It's up to 7x more cost-efficient than comparable models.