Coding AI tools

AI-first code editor built on VS Code. Multi-file editing, intelligent refactoring, and a built-in chat that understands your entire codebase. A favorite among developers for complex projects.

OpenAI's most capable frontier model, built for complex multi-step reasoning, agentic tool use, and deep coding tasks. Powers ChatGPT and Codex with up to 272K context.

Anthropic's coding agent, running in the terminal, IDEs, Slack, the web and mobile, with parallel subagents and scheduled routines.

Next-gen AI IDE that blends copilot and agent modes. Wave 13 introduced autonomous multi-step workflows, letting the AI plan, code, test, and iterate across your entire project.

AI-powered UI generator that turns text prompts or screenshots into production-ready React components using shadcn/ui and Tailwind CSS.

AI code reviewer that posts inline, context-aware feedback on every pull request across GitHub, GitLab, Azure DevOps, and Bitbucket.

Open-weight AI models specializing in code generation, math, and complex reasoning at a fraction of closed-model API pricing.

The most widely adopted AI coding assistant. Multi-model completions, agentic coding, code review, and deep IDE integration — now with a free tier.

Describe what you want in natural language and Replit Agent builds the full application — frontend, backend, database, and deployment. No local setup required, everything runs in the cloud.

AWS-backed AI assistant for code generation, transformation, security scanning, and deep cloud infrastructure integration.

Rust-built code editor with native AI agents, edit prediction, and real-time collaboration — all at native speed that makes Electron editors feel sluggish.

OpenAI's coding agent across a CLI, an IDE extension, a cloud environment, ChatGPT and GitHub code review, powered by the GPT-5.6 family.

Runs open-weight models on your own machine with one command, and optionally spills over to Ollama's cloud when the model is too big for local hardware.

In-browser AI coding environment by StackBlitz that builds full-stack web apps from natural language prompts. No local setup needed.

Open-weight 744B-parameter frontier model from Zhipu AI built for coding, reasoning, and long-horizon agentic work, with a 1M-token context and an MIT license.

Prompt-to-app builder that turns natural language into live, functional web applications. Chat-based interface outputs real code with backend logic, perfect for rapid prototyping.

Open-source command-line AI coding partner that edits code directly in your local git repo. Bring your own API key, pay only for what you use.

Codebase-aware AI coding assistant from Sourcegraph with chat, autocomplete, and inline edits powered by your full repository context.

Free AI code completion and chat tool for individuals, with enterprise-grade privacy. Works across 70+ IDEs with fast, accurate suggestions.

Autonomous AI software engineer that can plan, code, debug, and deploy entire projects in its own sandboxed environment.

Open-weight 33B MoE coding model from Poolside AI with only 3B active parameters. Hits 68.2% on SWE-bench Verified and runs locally on a single GPU or Mac with 36GB RAM.

Cohere's open-source 218B Mixture-of-Experts LLM built for agentic coding workflows, multilingual tasks, and document processing — runs on as few as 2 H100s.

Open-weights multimodal model with 1M token context that matches frontier coding benchmarks at 5-10% of GPT-5.5 pricing.

Desktop app for running open-weight models locally, with a GGUF and MLX runtime, an OpenAI-compatible local server, a CLI and Python and TypeScript SDKs.

Open-source agent runtime from DeepSeek. Every piece — models, tools, sandboxes, UI — is a plugin. MIT-licensed developer preview launched August 13, 2026.

xAI's terminal coding agent, now defaulting to Grok 4.6. Plan mode, subagents, skills, MCP, and sandboxed runs from your shell.

Open-source AI coding agent from Block that runs locally on your machine. Supports any LLM provider, extends via MCP, and keeps your code private by default.

Cohere's open-source 30B/3B MoE coding model with 256K context, interleaved thinking, and strong SWE-Bench scores — all under Apache 2.0.

Meta's multimodal reasoning model built for agentic coding, tool use, and computer control, with a 1M-token context window.

Open-source CLI from OpenAI that scans Git repositories for vulnerabilities, tracks findings across runs, and verifies fixes inside CI/CD.

AI code assistant built for enterprise teams with personalized completions, chat, and zero data retention privacy guarantees.

Open-source multi-agent framework that turns AI coding agents like Claude and Codex into autonomous red-teaming tools for vulnerability hunting.

Open-source, native local LLM server for Apple Silicon Macs — runs models on-device via MLX with an OpenAI-compatible API for private coding and automation.