AI coding agents · scenario rankings

Terminal / command-line agents

Most Popular Terminal-Based AI Coding Agents

Dispersedunstable definition

Measured 2026-09-22 · 12-seat model panel · 10 scenarios · methodology #2 v2026-09-22.1

Download image (with QR code)Share on X Share on LinkedIn

WeChat: save the image and long-press the QR code in a chat.

The ten

Rank	Entity	Mention rate (of answers)	Wilson 95% interval	Seats that mentioned it	Seats with stable coverage
1	Aider	99.3%	[97.9%, 99.8%]	12 of 12	12 of 12
2	GitHub Copilot	69.0%	[64.4%, 73.3%]	12 of 12	12 of 12
3	Gemini CLI	63.2%	[58.4%, 67.7%]	11 of 12	8 of 12
4	Amazon Q Developer	61.0%	[56.2%, 65.6%]	12 of 12	8 of 12
5	Claude Code	61.0%	[56.2%, 65.6%]	12 of 12	9 of 12
6	Cursor	56.8%	[52.0%, 61.5%]	12 of 12	7 of 12
7	Goose	53.9%	[49.1%, 58.7%]	9 of 12	6 of 12
8	OpenAI Codex CLI	40.2%	[35.6%, 45.1%]	10 of 12	5 of 12
9	Continue.dev	39.5%	[34.9%, 44.3%]	11 of 12	4 of 12
10	Cline	37.8%	[33.2%, 42.6%]	12 of 12	4 of 12

How it is counted: mention rate = answers naming it ÷ 410 (7 phrasings × 5 repeats × 12 seats = 420 calls, 410 valid); the last two columns count seats, and "stable coverage" means more than half of that seat's 34 answers. Different denominators, so 12 of 12 next to a rate below 100% is not a contradiction.

The sample behind this cell

Valid samples / calls expected: 410 / 420
Completeness: 97.6%
Effective entities (effN): 22.1
Entities mentioned at least once: 97

How this cell was asked

This cell used 7 phrasings, each asked 5 times. Every call asked for the ten names only — no reasons, no scores.

Most Popular Terminal-Based AI Coding Agents
Terminal-based AI coding agents — what are the options right now?
What are the alternatives to Claude Code for agentic coding in the terminal?
I live in the terminal and want an AI agent that can edit code and run commands from the shell. What do people use?
I'm using Claude Code today; which other CLI coding agents are worth trying?
best ai coding cli 2026
List some AI coding agents that run in the command line.

Where this page stops

This is one measurement, not a trend line. The next run of the same phrasings comes next quarter.
Each call collected ten names at most. Anything past the tenth name is invisible in this cell, which is not the same as being absent.
Mention rate is the share of samples in this cell where a name came up. It is not market share, and it is not a judgement about the product.
Read this cell for who is present, not for the order.

Methodology: the panel, the phrasings and how completeness is counted

You can also query this data from Claude, Cursor or another agent, with the same reading rules attached. For agents →