Skip to content
Sıfırıncı Dakika
Breaking

Former GitHub CEO launches rival platform built for AI coding agents

AINew2 min read

In brief

Entire, the startup led by former GitHub CEO Thomas Dohmke, unveiled a platform for storing, reviewing and shipping code written by AI agents. It replaces pull requests with Trails, a dashboard where AI agents score each change, and pitches itself as an alternative to GitHub.

  • Trails: review dashboard scored by AI agents instead of pull requests
  • Private repository hosting in the US, Europe, India and Australia
  • Build and test pipeline partnerships with Buildkite and Depot
  • Continuous Memory: agents search past sessions for context
  • Optional human sign-off and mandatory automated tests

What replaces the pull request?

Entire, led by former GitHub CEO Thomas Dohmke, announced a platform for storing, reviewing and shipping code written by AI agents. The company calls it a "Git forge": a service for hosting code, reviewing changes and running builds, the core of what GitHub does.

The biggest change is Trails, Entire's replacement for the pull request, the standard way developers propose and review code changes. According to Dohmke, the pull request "has become an audit log that only the agent reads." In Trails, developers see a dashboard of scores from multiple AI agents evaluating each update instead of reading every changed line.

Human sign-off stays optional

Entire says teams can still require a person's sign-off or passing automated tests before code is merged, so full automation is not forced.

The platform lets developers host private code repositories directly on Entire in the US, Europe, India and Australia. Based on its own benchmarks, the company says its service can handle up to 89 times as many code pushes per second as GitHub. It is partnering with Buildkite and Depot on build and test pipelines so teams can move off GitHub Actions. Public repositories and self-hosting are on the roadmap.

Memory for agents

Entire is also adding Continuous Memory, which lets AI agents search past coding sessions for the context behind earlier changes. The company says one part of it, a map of the codebase, cut token use by up to 71% in its testing.

Why now?

GitHub is straining under the load from AI agents. The platform has had several significant outages in recent months, including one in August that lasted nearly eight hours. GitHub is moving from its own data centers to Microsoft's Azure cloud to add capacity. According to GitHub, developers and agents made 7.38 billion commits on the platform in September alone.

Entire isn't alone: AI coding company Cursor launched its own code-hosting service, Origin, in August, and Anthropic recently described building its own source control system as the number of code changes it merged each day grew from about 2,500 in May to more than 30,000 in September. Microsoft acquired GitHub for $7.5 billion in 2018. Microsoft's venture arm M12 was among the backers of Entire's $60 million seed round in February.

Why it matters

As AI agents speed up code writing, review becomes the bottleneck; this shows one of the first serious alternatives to GitHub in the code-hosting market.

Sources

Related stories