Entire launches GitHub alternative with Trails agentic code review

Entire, the startup founded by former GitHub CEO Thomas Dohmke, launched a GitHub alternative on Monday that replaces the traditional pull request model with an agentic code review system called Trails. The company has been releasing parts of its platform since it announced a $60 million seed round in February. With this launch, Entire is offering a full GitHub alternative for what it describes as the agentic era.

Trails and code review

Trails is Entire's reinvention of the pull request. Instead of relying on manual code review, it gives developers a dashboard with customizable evals scored by agents. Those evals can assess factors such as the risk of a code change or how much intent drift occurred during a long LLM-driven development session. Entire says the evals run on every push, and findings are available through its web interface and open-source CLI. Coding agents can use that feedback to address problems and push another revision while the developer validates progress. The original request, the agent's session history, and the resulting code all become part of the review. Entire provides preset review agents by default, and developers can define their own configurations in a JSON file and choose among supported Claude and OpenAI models.

Git hosting and CI

At launch, Entire supports native hosting for private repositories. Public repositories and self-hosted Git nodes are still on the roadmap. The platform is built around Entire's Git-compatible distributed source control server, which the company says can push up to 89 times faster than GitHub and six times faster than Cursor's Origin. Entire was also built from the outset to offer private repositories in specific regions, including the U.S., Europe, India, and Australia. Customers choose a primary region and can add mirrors elsewhere, with Entire handling synchronization. For CI, Entire is partnering with Buildkite and Depot. Developers can convert existing GitHub Actions workflows using Buildkite's bk pipeline or Depot CI, then connect the repository in Entire.

Memory, pricing and business model

Continuous Memory is Entire's third pillar. It syncs AI agent sessions into a project's repository and makes them available to agents for future use. Entire says the system combines a codebase graph that helps agents find relevant code with an agentic brain that turns previous sessions and prompts into memories they can query. The platform is free, and Dohmke says customers pay only for the tokens the review agents consume. Entire is currently giving all users a $100 starter credit. After users run out of credits, they pay market rates for the model of their choosing. Dohmke also said Entire is working with partners, including model vendors, on ideas for open-source projects, and hinted that more help may come.

Sources: The New Stack