# Coding Agents Index

> Independent measurement of coding-agent usage from output you can verify: commits and pull requests on public GitHub that carry an agent's signature, tracked daily since Claude Code launched in February 2025.

This is the machine-readable version of https://amplifying.ai/coding-agents. Every count is a floor; numbers update on the same schedule as the site.

## How to read this

Each agent's output carries a visibility class, and they are not equal:

- **Exact**: visible through the agent's own bot or workflow, counted exactly.
- **Estimate**: inferred from public signals, either attribution the agent declares (large counts can swing 30 to 40 percent between runs) or the pull requests a cloud service opens (well-covered for the cloud path, blind to local CLI work).
- **No public signature**: the agent works through the developer's own identity and leaves nothing public to attribute. Absence means invisible, not low usage.

Coverage limits: public repositories only; private-repo work is not counted. Squash-merges and disabled attribution further undercount. Treat every figure as a floor and a proxy for the ecosystem, not a census. Output snapshot as of 2026-06-09.

## Rankings (attributed public output)

Total tracked attributed output: 136.1M commits and pull requests across 22 agents.

| # | Agent | Company | Attributed output | Signal | npm demand/wk | Channel |
| - | ----- | ------- | ----------------- | ------ | ------------- | ------- |
| 1 | Claude Code | Anthropic | 104.9M | Estimate | 8.2M | Native preferred |
| 2 | Cursor | Anysphere | 10.7M | Estimate | n/a |  |
| 3 | Replit Agent | Replit | 8.8M | Estimate | n/a |  |
| 4 | OpenAI Codex | OpenAI | 5.1M PRs | Estimate | 10.9M | npm primary |
| 5 | GitHub Copilot | GitHub / Microsoft | 4.1M | Exact | 1.5M | CLI/package channel |
| 6 | Jules | Google | 1.2M | Exact | n/a |  |
| 7 | Aider | Aider AI | 613K | Estimate | n/a |  |
| 8 | Devin | Cognition | 285K | Exact | n/a |  |
| 9 | Gemini CLI / Antigravity CLI | Google | 231K | Estimate | 721K | npm primary |
| 10 | Qwen Code | Alibaba / Qwen | 99K | Estimate | 83,956 | npm primary |
| 11 | opencode | Anomaly | 96,745 | Estimate | 1.5M | npm primary |
| 12 | OpenHands | All Hands AI | 58.5K | Estimate | n/a |  |
| 13 | Amp | Sourcegraph | 49.2K | Estimate | 36,970 | npm primary |
| 14 | Warp | Warp | 29.9K | Estimate | n/a |  |
| 15 | Roo Code | Roo Code | 19.1K | Estimate | n/a |  |
| 16 | JetBrains Junie | JetBrains | 9,602 | Estimate | n/a |  |
| 17 | Cline | Cline | 5,907 | Estimate | 65,236 | npm primary |
| 18 | Google Antigravity | Google | 4,863 | Estimate | 664K | Legacy npm / Antigravity native |
| 19 | Crush | Charm | 2,844 | Estimate | 3,013 | npm primary |
| 20 | Kiro | AWS | 2,369 | Estimate | n/a |  |
| 21 | Amazon Q Developer | AWS | 2,218 PRs | Exact | n/a |  |
| 22 | Codebuff | CodebuffAI | 1,205 | Estimate | 9,365 | npm primary |

Full table with filters: https://amplifying.ai/coding-agents

## Trends: weekly agent-marked PRs

Latest complete week per charted agent.

| Agent | PRs, latest week | Week over week |
| ----- | ---------------- | -------------- |
| Claude Code | 514K | +1% |
| Copilot agent | 13,954 | -7% |
| Cursor agents | 89,205 | +6% |
| Devin | 7,845 | -15% |
| Jules | 22,843 | -3% |
| Codex | 172K | -9% |

Live flow sample: of the 600 most recent public PRs, 21% carry an agent signal (Claude Code alone 18%), dependency bots another 19%.

Detail and daily view: https://amplifying.ai/coding-agents/trends

## Autonomy and trust

Across 268 merged agent PRs in significant repos (org-owned or 10+ stars, 2026-07-16 to 2026-08-14), 45.5% had a human GitHub reviewer and 54.5% merged with none.

| Agent | Human-reviewed (significant repos) | Median time to merge | Touches tests |
| ----- | ---------------------------------- | -------------------- | ------------- |
| GitHub Copilot | 79.5% | 25 min | 20.8% |
| Cursor | 70.7% | 47 min | 40% |
| Claude Code | 44.4% | 20 min | 47.5% |
| OpenAI Codex | 32% | 20 min | 62.5% |
| Devin | 32% | 22 min | 40.8% |
| ZCode | 13.3% | 13 min | 55.8% |

Note: "reviewed" means a non-author, non-bot GitHub reviewer. A high merge rate with a low review rate means the agent self-merges, not that a human signed off. Detail: https://amplifying.ai/coding-agents/autonomy

## Merge rates (settled window)

| Agent | PRs merged |
| ----- | ---------- |
| Claude Code | 92% |
| ZCode | 91% |
| OpenAI Codex | 87.5% |
| Amazon Q Developer | 71.6% |
| GitHub Copilot | 68.4% |
| Cursor | 64.6% |
| Devin | 60.3% |
| Jules | 47.9% |

## Weekday vs weekend

Across tracked agents, weekend PR volume runs 10.7% below weekdays. The size of the dip is an enterprise-versus-consumer tell.

| Agent | Weekday/day | Weekend/day | Weekend change |
| ----- | ----------- | ----------- | -------------- |
| Copilot agent | 3,017 | 2,331 | -22.7% |
| Devin | 1,256 | 1,041 | -17.1% |
| Cursor agents | 7,294 | 6,205 | -14.9% |
| Codex | 23,142 | 20,656 | -10.7% |
| Claude Code | 71,034 | 63,600 | -10.5% |
| Jules | 6,002 | 5,924 | -1.3% |

Detail: https://amplifying.ai/coding-agents/trends#weekday-weekend

## Claude Code model mix

Which Claude model appears in public Claude Code runs (2026-06-29 to 2026-08-23):

- Opus: 74%
- Sonnet: 25.1%
- Haiku: 0.9%

## npm install demand (CLI agents)

Weekly npm downloads as an install-demand floor, not an active-user count. CLI agents only; IDE and web agents do not appear here.

| Agent | Demand/wk | Channel |
| ----- | --------- | ------- |
| OpenAI Codex | 10.9M | npm primary |
| Claude Code | 8.2M | Native preferred |
| GitHub Copilot | 1.5M | CLI/package channel |
| opencode | 1.5M | npm primary |
| Pi | 1.1M | npm primary |
| Gemini CLI / Antigravity CLI | 721K | npm primary |
| Google Antigravity | 664K | Legacy npm / Antigravity native |
| Qwen Code | 83,956 | npm primary |
| Cline | 65,236 | npm primary |
| Kilo Code | 50,329 | npm primary |
| Amp | 36,970 | npm primary |
| Codebuff | 9,365 | npm primary |
| Crush | 3,013 | npm primary |

Detail: https://amplifying.ai/coding-agents/npm

## Languages (agent penetration)

Share of all public PRs in each language that carry an agent mark, 2026-07-01 to 2026-07-31.

| Language | Agent-marked share | Leader |
| -------- | ------------------ | ------ |
| Swift | 37.6% | Claude Code |
| TypeScript | 26.7% | Claude Code |
| Dart | 25.3% | Claude Code |
| HTML | 24.8% | Claude Code |
| Python | 23.9% | Claude Code |
| JavaScript | 22.6% | Claude Code |
| Rust | 22.3% | Claude Code |
| PHP | 18% | Claude Code |
| Kotlin | 17.5% | Claude Code |
| Shell | 16.1% | Claude Code |
| C# | 14.5% | Claude Code |
| Go | 13.9% | Claude Code |
| C | 13.3% | Claude Code |
| C++ | 11.6% | Claude Code |
| Vue | 10.1% | Claude Code |
| PowerShell | 9.4% | Claude Code |

Detail: https://amplifying.ai/coding-agents/languages

## Industries (where sampled agent work lands)

Sampled agent PRs by industry, 2026-08-03 to 2026-08-23.

| Industry | Share of classified | Leader |
| -------- | ------------------- | ------ |
| AI/ML | 38.3% | Devin |
| Devtools | 11% | GitHub Copilot |
| Finance | 6.5% | Devin |
| Gaming | 5.7% | Jules |
| Security | 5.3% | Devin |
| Media | 4.8% | Jules |
| Data/Analytics | 3.6% | Devin |
| Crypto/Web3 | 3.3% | Cursor |
| Healthcare | 3.1% | GitHub Copilot |
| Robotics | 2.9% | Devin |

Detail: https://amplifying.ai/coding-agents/industries

## More

- Methodology and coverage: https://amplifying.ai/coding-agents/methodology
- State of the Coding Agent Market (analysis): https://amplifying.ai/research/state-of-coding-agents
- Compare agents: https://amplifying.ai/coding-agents/compare
- Contact: team@amplifying.ai