Agentation turns UI annotations into structured context that AI coding agents can understand and act on. Click any element on your screen, add a note, and paste the output directly into Claude Code, Codex, or any AI coding tool to fix UI bugs faster. It bridges the gap between visual feedback and actionable AI instructions.

Amazon Nova Forge is AWS's enterprise LLM customization platform, launched in March 2026, that makes it easy to fine-tune and adapt Amazon Nova foundation models to domain-specific data without the usual complexity of dependency management or recipe configuration. It supports pre-training, supervised fine-tuning (SFT), and reinforcement fine-tuning (RFT), and includes a responsible AI toolkit for safety and content moderation settings. Nova Forge is accessible through Amazon Bedrock and SageMaker AI.

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.

Anthropic is agentic coding assistant that lives in your terminal. It understands your codebase, edits files, runs commands, and helps you code faster through natural language commands.

Deploy AI agents by chatting with one. Natural language interface for building and managing AI workflows without coding.

OpenAI Codex desktop application for coordinating AI coding agents across development projects. A dedicated app that helps developers manage AI coding workflows, automate software development tasks, and coordinate multiple AI agents.

Cursor Automations is the latest AI coding agent feature from Cursor, launched in March 2026, that enables always-on background agents triggered by code changes, Slack messages, or timers. Built on Cursor's AI-powered VS Code fork, it lets developers delegate entire implementation tasks to autonomous agents while focusing on higher-level direction. Supports multi-step agentic workflows, MCP apps, and cloud-based agent management.

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.

Cognition AIs autonomous AI software engineer released February 24, 2026. The major update features multi-agent operation capability where AI agents dispatch tasks to other agents, plus self-assessed confidence evaluation that asks for clarification when unsure.

AI tool that generates complete web applications from natural language prompts. Users describe what they want to build and Fabricate creates functional apps with frontend, backend, and database integration.

Gemma 4 is Google DeepMind's most capable open-source AI model family, released in April 2026 under the Apache 2.0 license. It features Dense and Mixture-of-Experts (MoE) architectures in four sizes (E2B, E4B, 26B, and 31B), purpose-built for advanced reasoning, coding, and agentic workflows. The E2B and E4B variants are specifically optimized for on-device inference on smartphones and edge hardware like Raspberry Pi, with deep collaboration from Qualcomm and MediaTek.

z.AI's flagship open-weight model released February 2026 with 744B total parameters (40B active). Designed for complex systems engineering and long-horizon agentic tasks. Integrates DeepSeek Sparse Attention for efficient long-context workloads. Strong in reasoning and code generation.

Jules is Google's autonomous AI coding agent that asynchronously handles software development tasks so developers can focus on what they love. It reads your codebase, writes tests, fixes bugs, builds features, and integrates with GitHub, providing audio changelogs of its work.

Goose is an open-source AI coding agent developed by Block (formerly Square) that performs multi-step software tasks autonomously in your terminal. It supports any LLM provider — including Claude, Codex, and Gemini via ACP (Agent Client Protocol) — and offers macOS sandboxing, MCP extension support, and a rich CLI for automated development workflows.

OpenAI's specialized model for agentic coding and AI workforce management, designed to help companies deploy autonomous AI agents for complex development workflows.

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.

Kimi Code is an open-source AI coding agent developed by Moonshot AI, powered by the Kimi K2.5 multimodal model. It runs in your terminal and integrates with IDEs like VSCode, Cursor, and Zed, allowing you to use text, images, and videos as coding input. Launched in January 2026, it rivals Claude Code and Gemini CLI with strong SWE-Bench performance.

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.

Xiaomi's ultra-fast open-source LLM with 309B total parameters (15B active). Features Mixture-of-Experts architecture, Hybrid Sliding Window Attention, and Multi-Token Prediction. Supports 256K context window and achieves 150+ tokens per second inference speed. Excellent for reasoning, coding, and agentic workflows.

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.

NousCoder-14B is an open-source competitive programming model by Nous Research, post-trained on Qwen3-14B via reinforcement learning. It achieves 67.87% Pass@1 accuracy on LiveCodeBench v6, competing directly with proprietary models like Claude Code and GitHub Copilot. Available free to download and run on Hugging Face.

An AI-powered full-stack app builder that lets non-developers ship production-ready web and mobile apps by describing what they want in plain language. NxCode competes with Lovable, Bolt.new, and v0 and offers free credits, a vibe coding workflow, and a built-in SaaS pricing calculator.

OpenMolt is an open-source Node.js/TypeScript library for building production-grade programmatic AI agents that think, plan, and act using tools, integrations, and persistent memory — directly from your codebase. It provides a unified interface for major LLM providers and is designed for developers who want full programmatic control over their agent workflows without vendor lock-in. MIT licensed and free to use.