What does 17.9 billion pushes tell us about how developers work now?

The surge that bent the curve in June

Commits across all repositories climbed to 34.3 billion. That is more than three times the count from two years ago. Merged pull requests more than tripled to 1.3 billion, an average of 3.5 million a day. GitHub Actions ran a job 1,440 times every second. This equals 124 million times a day and is more than three times last year's total. Developers merged more than 30 million Dependabot pull requests to keep dependencies current, about double 2025's pace. Push protection scanned for exposed secrets 5.8 billion times, nearly four times 2025's pace. Activity climbed steadily from January, then surged around June. Right around then, a cluster of industry-wide shifts landed: better underlying models, the harnesses built around them, and the agents running on both.

Agents become the first move for four in ten pull requests

By September 2026, more than 40% of pull requests on GitHub started with an agent's first draft, up from 17% in March. That is 110 million in September alone, about six times March's volume. Agent-started pull requests also more often change multiple files: about 87%, compared with 79% of pull requests without detected agent involvement. They are landing quickly too. In February, 83% of agent-involved pull requests merged within two weeks, a touch behind the roughly 86% for pull requests without detected agent involvement. By September, agent pull requests were at 90%, while the comparison group held at about 86%. Among GitHub Copilot's monthly active users, 55% now use agentic features, up from 35% a year ago. The steepest growth is in the most hands-off mode. Copilot cloud agent, where a developer assigns a task and an agent works on it independently, grew 230% year over year, against 85% for agent chat. Developers still ask agents questions, and increasingly they hand over whole tasks.

Model choice spreads across 47 options

In September 2026, 61% of GitHub Copilot users who selected a model themselves used more than one model across their sessions, up from 50% four months earlier. Developers on paid GitHub Copilot plans used 29 distinct models in May and 47 in September. No single model carried more than 25% of requests that month. Out of every 100 developer-selected requests, 38 went to general purpose models. Another 37 went to deep reasoning and planning models, and 25 to fast and lightweight models. Developers spread their choices across models and functionality. New releases are used heavily before most developers have tried them. In their first weeks, most new models take a larger share of requests than the portion of developers who have tried them. Early adopters use a model heavily before the rest follow. Developers keep a model in rotation after leaning on it less.

Growth reaches industries that barely used code before

GitHub now serves more than 225 million developers. The United States (38.3 million) and India (32 million