Reference view

AI Coding Landscape

A structured view of the AI coding products currently verified in iilib. The table is generated from entity and relationship records rather than maintained as a separate market list.

Category verified Oct 3, 2026 · coverage reflects the current iilib graph, not the entire market.

Coding products

Open source

Terminal-capable

Published comparisons

Product graph

Verified coding products

Model and API counts reflect explicit relationships currently stored in iilib. A zero means no such relationship is currently mapped, not that the product cannot use models or APIs.

Aider

Independent / project

Tool

CliOpen source

Models3

APIs8

Amazon Q Developer

Amazon Web Services

Tool

WebIdeCli

Models0

APIs0

Amp

Amp Frontier Corporation

Agent

LocalCloudBrowserDesktop

Models5

APIs5

Claude Code

Anthropic

Agent

CliIdeCloud

Models3

APIs1

Cline

Cline Bot

Agent

LocalCliIdeOpen source

Models5

APIs7

Codex CLI

OpenAI

Agent

LocalCliOpen source

Models2

APIs1

Cursor

Anysphere

Tool

WebMacosWindowsLinux

Models7

APIs3

Devin

Cognition

Agent

CloudBrowser

Models2

APIs0

Devin CLI

Cognition

Agent

LocalCliIde

Models5

APIs0

Devin Desktop

Cognition

Tool

MacosWindowsLinux

Models3

APIs0

Droid

Factory

Agent

LocalCloudBrowserDesktop

Models4

APIs5

Gemini CLI

Google

Agent

LocalCliOpen source

Models1

APIs1

GitHub Copilot

GitHub

Tool

WebIdeCli

Models10

APIs0

Junie

JetBrains

Agent

LocalCliIde

Models0

APIs5

Kiro

Amazon Web Services

Tool

WebMacosWindowsLinux

Models2

APIs0

OpenCode

Anomaly

Agent

LocalCliDesktopIdeOpen source

Models4

APIs8

OpenHands

All Hands AI

Agent

LocalCloudBrowserCliOpen source

Models1

APIs6

Earendil Works

Agent

LocalCliOpen source

Models0

APIs8

Qwen Code

Alibaba Cloud

Agent

LocalBrowserDesktopCliOpen source

Models1

APIs7

Replit Agent

Replit

Agent

CloudBrowser

Models1

APIs0

Tabnine

Tricentis

Tool

IdeCli

Models0

APIs0

Zed

Zed Industries

Tool

MacosWindowsLinuxOpen source

Models2

APIs7

Product	Type	Provider	Surfaces	Open source	Models	APIs
Aider	Tool	Independent / project	Cli	Yes	3	8
Amazon Q Developer	Tool	Amazon Web Services	Web, Ide, Cli	No	0	0
Amp	Agent	Amp Frontier Corporation	Local, Cloud, Browser, Desktop, Cli, Ide	No	5	5
Claude Code	Agent	Anthropic	Cli, Ide, Cloud	No	3	1
Cline	Agent	Cline Bot	Local, Cli, Ide	Yes	5	7
Codex CLI	Agent	OpenAI	Local, Cli	Yes	2	1
Cursor	Tool	Anysphere	Web, Macos, Windows, Linux, Cli, Ide	No	7	3
Devin	Agent	Cognition	Cloud, Browser	No	2	0
Devin CLI	Agent	Cognition	Local, Cli, Ide	No	5	0
Devin Desktop	Tool	Cognition	Macos, Windows, Linux	No	3	0
Droid	Agent	Factory	Local, Cloud, Browser, Desktop, Cli	No	4	5
Gemini CLI	Agent	Google	Local, Cli	Yes	1	1
GitHub Copilot	Tool	GitHub	Web, Ide, Cli	No	10	0
Junie	Agent	JetBrains	Local, Cli, Ide	No	0	5
Kiro	Tool	Amazon Web Services	Web, Macos, Windows, Linux, Ios, Cli, Ide	No	2	0
OpenCode	Agent	Anomaly	Local, Cli, Desktop, Ide	Yes	4	8
OpenHands	Agent	All Hands AI	Local, Cloud, Browser, Cli	Yes	1	6
Pi	Agent	Earendil Works	Local, Cli	Yes	0	8
Qwen Code	Agent	Alibaba Cloud	Local, Browser, Desktop, Cli, Ide	Yes	1	7
Replit Agent	Agent	Replit	Cloud, Browser	No	1	0
Tabnine	Tool	Tricentis	Ide, Cli	No	0	0
Zed	Tool	Zed Industries	Macos, Windows, Linux	Yes	2	7

Model layer

12 connected models

18 coding products currently have at least one explicit model relationship in the graph.

Claude Fable 5.1 Claude Opus 5.5 Claude Sonnet 5.5 DeepSeek V4 Pro Gemini 3.8 Flash GPT-5.6 Luna GPT-5.6 Sol GPT-5.6 Terra GPT-6 Astra GPT-6.1 Sol Grok 4.7 Qwen3-Coder-Plus

API layer

9 connected APIs

14 coding products currently have at least one explicit API integration relationship in the graph.

Alibaba Cloud Model Studio API Claude API DeepSeek API Gemini API Groq API Mistral API OpenAI API OpenRouter API xAI API

Comparison coverage

Published comparisons involving this graph

All comparisons →

Compare

Aider vs Cline

Aider and Cline are open-source coding tools that can edit repositories and work with multiple model providers. Aider is terminal-centered with repository-map and Git workflows, while Cline spans IDE, CLI, and desktop surfaces with browser and MCP tooling.

Compare

Amp vs Claude Code

Amp and Claude Code are coding agents with terminal workflows. Amp uses multi-model routing and can run work locally or in cloud orbs; Claude Code is Anthropic's coding agent built around Claude models and Anthropic-managed product surfaces.

Compare

Claude Code vs Codex CLI

Claude Code and Codex CLI are coding agents with local terminal workflows. Claude Code also has Anthropic-managed IDE and web surfaces, while Codex CLI is the open-source local command-line client in the Codex family.

Compare

Claude Code vs Cursor

Claude Code is Anthropic's coding agent across terminal, IDE, web, and managed integrations. Cursor is a standalone code editor with local and cloud agent workflows plus CLI and web access.

Compare

Cursor vs GitHub Copilot

Cursor is a standalone editor from Anysphere. GitHub Copilot runs across GitHub, supported IDEs, and the command line. Both include agent workflows.

Compare

DeepSeek API vs OpenAI API

DeepSeek API and OpenAI API both support the OpenAI Responses request style. DeepSeek additionally documents an Anthropic-compatible base URL, while OpenAI exposes a broader first-party set of realtime and media endpoints.

Compare

DeepSeek V4 Pro vs GPT-6.1 Sol

DeepSeek V4 Pro and GPT-6.1 Sol are current reasoning models used in coding and agent workflows. DeepSeek documents a larger maximum output, while GPT-6.1 Sol accepts image input and has a slightly larger context window.

Compare

Devin Desktop vs Cursor

Devin Desktop, formerly Windsurf, combines an IDE with a command center for local and cloud agents. Cursor is an AI code editor with integrated agent and cloud-agent workflows.

Compare

Droid vs Devin

Droid and Devin are software-development agents that can carry out multi-step engineering work. Droid is exposed across local, desktop, CLI, web, and managed cloud surfaces; Devin is centered on Cognition-managed cloud environments.

Compare

Gemini 3.8 Flash vs GPT-6.1 Sol

Gemini 3.8 Flash and GPT-6.1 Sol both target coding and agent workflows. Gemini 3.8 Flash accepts a broader set of native media inputs, while GPT-6.1 Sol has a larger documented maximum output.

Compare

Gemini API vs OpenAI API

Gemini API and OpenAI API both expose multimodal models, streaming, tool use, batch processing, and official SDKs. Their primary request primitives and authentication schemes differ.

Compare

Gemini CLI vs Codex CLI

Gemini CLI and Codex CLI are Apache-2.0 terminal coding agents. Gemini CLI is centered on Google's Gemini ecosystem and includes built-in web tools, while Codex CLI is OpenAI's local Codex client with configurable approval controls.

Compare

GitHub Copilot vs Junie

GitHub Copilot is a coding assistant across GitHub, supported IDEs, and the command line. Junie is JetBrains' coding agent for JetBrains IDEs and the command line, with project instructions, skills, MCP, and custom model access.

Compare

GPT-6.1 Sol vs Claude Sonnet 5.5

GPT-6.1 Sol and Claude Sonnet 5.5 are current general-purpose models with strong coding and agent-workflow support. Their standard API input/output prices are both USD 2 and USD 10 per million tokens.

Compare

GPT-6 Astra vs Claude Opus 5.5

GPT-6 Astra and Claude Opus 5.5 are high-capability models from OpenAI and Anthropic. Both support text and image input, reasoning, tool-based workflows, and long contexts.

Compare

Grok 4.7 vs GPT-6.1 Sol

Grok 4.7 and GPT-6.1 Sol are current multimodal models used for coding and agent workflows. Grok 4.7 has lower standard output-token pricing, while GPT-6.1 Sol has a larger documented context window.

Compare

Groq API vs OpenRouter API

Groq API and OpenRouter API both expose OpenAI-compatible model access. Groq runs a selected model catalog on its inference cloud, while OpenRouter routes requests across many model providers.

Compare

Kiro vs Cursor

Kiro and Cursor both combine code editing with agent workflows. Kiro spans IDE, CLI, web, and mobile surfaces, while Cursor centers on its editor with local and cloud agent workflows.

Compare

Mistral Medium 3.5 vs Claude Sonnet 5.5

Mistral Medium 3.5 and Claude Sonnet 5.5 both target coding and agentic work. Mistral Medium 3.5 is released as open weights, while Claude Sonnet 5.5 is served as a proprietary Anthropic model.

Compare

OpenAI API vs Claude API

OpenAI API and Claude API both provide model access, streaming, tool use, and official SDKs. They differ in API surface, model catalog, authentication details, and supported media and realtime endpoints.

Compare

OpenCode vs Claude Code

OpenCode is an open-source, provider-agnostic coding agent with terminal, desktop, and IDE surfaces. Claude Code is Anthropic's coding agent with terminal, IDE, web, and other Claude product integrations.

Compare

OpenHands vs Devin

OpenHands and Devin both target multi-step software-development work. OpenHands is an MIT-licensed platform that can run locally, in its hosted service, or self-hosted; Devin is a proprietary cloud agent from Cognition.

Compare

OpenRouter API vs OpenAI API

OpenRouter API is a multi-provider routing layer with an OpenAI-compatible interface, while OpenAI API is OpenAI's first-party platform for its own models and developer services.

Compare

Qwen Code vs Gemini CLI

Qwen Code and Gemini CLI are Apache-2.0 coding agents that run from the terminal. Qwen Code supports multiple provider protocols and additional desktop, browser, and editor surfaces; Gemini CLI is centered on Google's Gemini ecosystem.

Compare

Replit Agent vs Devin

Replit Agent is built around creating, testing, and deploying applications inside Replit's hosted workspace. Devin is a cloud software-engineering agent designed for delegated engineering work across repositories and team workflows.

Compare

xAI API vs OpenAI API

xAI API and OpenAI API both expose Responses-style and OpenAI-compatible developer workflows, with different model catalogs, server-side tools, media endpoints, and transport options.

Compare

Zed vs Cursor

Zed is an open-source editor with native, external, and terminal-backed agent paths. Cursor is a proprietary editor centered on its own agent workflows and cloud agents.

Method

Inclusion follows the AI Coding category criteria. Product, provider, model and API facts come from indexed entity records and verified relationship records. Editorial comparison notes remain separate from graph-derived counts.