Coding Agents IndexPreviewThis index is in active development: we are still adding agents, refining attribution signatures, and verifying data against sources. The date in the header is when key figures were last re-checked. Numbers can move as coverage improves.
Index of what coding agents are doing in public repos: PRs opened, commits attributed, merge outcomes, and review patterns.
New · Research reportState of the Coding Agent Market, June 2026Rankings
Filter by surface, pricing, security posture, and model support. Open any row for sources and caveats.
| 1 | Claude Codeest. Anthropic | 1.5M | 4.2M | 16M | 63M+25.6% | $2.5B+rev | $20-$200 | Retail token equivalent | CLIIDEDesktopWebCloudMobile | |
| 2 | OpenAI Codexest. OpenAI | 555K | 5.1M+1.2% | n/a | 31.3K | 5M+ weeklyusers | $20-$200 | Token rate card | CLICloudDesktopIDEWebMobile | |
| 3 | Julesexact | 222K | 1.2M | 78.3K | 1M+2.2% | n/a | n/a | $0-$249.99 | Task quota | CloudWebCLI |
| 4 | Cursorest. Anysphere | 105K | 614K | 1.4M | 5.7M-27.6% | $4Brev | n/a | $20-$200 | Credit proxy | IDECLICloudWeb |
| 5 | GitHub Copilotexact GitHub / Microsoft | 104K | 1.9M | 175K | 3.8M+1.4% | 4.7M paidusers | $10-$100 | Token rate card | IDECLICloudCode reviewWebMobile | |
| 6 | Devinexact Cognition | 35.4K | 161K | 19.2K | 256K+5.5% | $492Mrev | n/a | $20-$200 | Credit proxy | CloudWebCLIIDECode review |
| 7 | Aiderest. Aider AI | n/a | n/a | 464 | 613K+36% | n/a | n/a | $0 | BYOK/API retail | CLI |
| 8 | Gemini CLI / Antigravity CLIest. | n/a | n/a | 11.9K | 219K+6.1% | n/a | $0-$199.99 | Task quota | CLI | |
| 9 | Qwen Codeest. Alibaba / Qwen | n/a | n/a | n/a | 99K+4% | n/a | $0 | BYOK/API retail | CLIIDE | |
| 10 | opencodeest. Anomaly | n/a | n/a | 3K | 79K+4.5% | 7.5M monthly | $0 | BYOK/API retail | CLIDesktop |
Trends: Weekly Agent-Marked PRs
All trendsPull requests created each week with a public agent signal.
Weekly, 2025-02-03 to 2026-06-08. Full analysis · Segments: who codes what · Methodology
Business Evidence
Public market signals behind the agent table.
Help us make this better
Email team@amplifying.ai with ideas, data, a missing agent, a correction, or anything we got wrong or left out. Or read the methodology for how every number is measured.
Reading this with an agent? There is a machine-readable Markdown version of the full index.