State of AI 2026: Agents & Assistants

Agents & Assistants

AI tools that help throughout the development process.

链接到某一部分
Coding Agents/Assistants Experience & Sentiment

Once again Claude shows a clear lead over the competition in terms of positive sentiment, with Claude Code topping the rankings even if GitHub Copilot technically has a larger user base.

通过...分组：

根据此项排序:

1

[zh-Hans] tools.coding_agents_assistants

67.9%

30.7%

6,970

2

[zh-Hans] tools.coding_agents_assistants

62.9%

35.7%

6,972

3

[zh-Hans] tools.coding_agents_assistants

34.5%

55.2%

9.9%

6,968

4

[zh-Hans] tools.coding_agents_assistants

13.5%

53.9%

32.1%

6,958

5

[zh-Hans] tools.coding_agents_assistants

8.1%

26.4%

65.1%

6,964

6

[zh-Hans] tools.coding_agents_assistants

6.3%

20.5%

72.9%

6,958

7

[zh-Hans] tools.coding_agents_assistants

Replit Agent & Assistant

4%

36.3%

59.5%

6,929

8

[zh-Hans] tools.coding_agents_assistants

43.7%

53.4%

6,953

经验

<span aria-hidden="true">🤓</span> 用过: 使用过此项目的受访者。
<span aria-hidden="true">👀</span> 有听说过: 听说过此项目，但没有使用过此项目的受访者。
<span aria-hidden="true">🤷</span> 没听说过: 从未听说过此项目的受访者。

情绪（态度）

积极: 有兴趣了解此技术，或者愿意再次使用它的受访者
中立: 未对此技术发表看法的受访者
消极: 对此技术不感兴趣，或者使用此技术有糟糕体验的受访者

链接到某一部分
Coding Agents & Assistants Ratios Over Time

Claude Code and OpenAI Codex are neck-and-neck in terms of respondent satisfaction, but the Anthropic coding tool is actually used way more than its rival.

Claude Code

OpenAI Codex

Devin

Tabnine

GitHub Copilot

JetBrains AI

Supermaven

Replit Agent & Assistant

模式:

视图:

使用度:

使用过某个项目的受访者比例

0%

20%

40%

60%

80%

100%

2025

2026

0%

20%

40%

60%

80%

100%

链接到某一部分
Other Coding Agents/Assistants

Given its popularity, OpenCode should probably have been part of the main survey options. But it makes up for that omission by establishing a comfortable lead over the competition here, with Cursor a close second.

What other coding agents or assistants are you currently using?

(自由提问)

多选

0%

20%

40%

60%

80%

100%

01

02

03

04

05

06

Windsurf Editor

07

08

09

10

0%

20%

40%

60%

80%

100%

受访者百分比

链接到某一部分
项目数量

受访者使用过此类别中的多少项目。

0%

6%

12%

18%

24%

30%

1

0

1,121

2

1

1,607

3

2

2,195

4

3

1,551

5

4

595

6

5

149

7

6

32

8

7

4

9

8

4

0%

6%

12%

18%

24%

30%

调查对象百分比

链接到某一部分
Paid Usage

Echoing results from the Models section, Claude Code also comes in first when it comes which coding assistants developers are willing to open their wallets for.

Out of the agents & assistants mentioned here, which one do you or your company actually pay for?

多选

0%

20%

40%

60%

80%

100%

01

3,700

02

2,703

03

1,526

04

无

1,252

05

349

06

07

83

08

Replit Agent & Assistant

51

09

10

0%

20%

40%

60%

80%

100%

受访者百分比

链接到某一部分
资源推荐

AI Engineering Fundamentals

Scott Moss

Netflix

AI Engineering Fundamentals

Add an agentic chat interface to an existing application. Then establish a rigorous eval harness to systematically improve the agent through context engineering, advanced tool use, RAG, and reliable production feedback loops.

AI Agents Fundamentals, v2

Scott Moss

Netflix

AI Agents Fundamentals, v2

Learn the foundations of agent development like tool calling, agent loops, and and evals. Add human-in-the-loop approvals for higher-stakes operations.

感谢合作伙伴对我们的支持! 了解更多。