ZDNET’s key takeaways
- Quite a GitHub rival is built around coding agents.
- The platform is designed to remove coding bottlenecks.
- AI-written code has changed what developers spend time on.
AI has accelerated the pace of coding, placed new demands on infrastructure, and changed developers. Ganz, a developer platform from former GitHub CEO Thomas Dohmke, aims to be the solution to these changes.
Also: ServiceNow and Nvidia launch Arc, a new AI agent for enterprise
The platform, available for use today, is built on the entire decentralized Git network, announced in July, which is designed to withstand the sharp increase in AI coding activity that caused the mounting GitHub outbreak.
Which makes it very different
The first change it makes to the standard coding experience is that it replaces pull requests with what it calls trails.
“Unlike the classic pull request model to verify code changes with a diff, Trails developers offer a heads-up display similar to an airline pilot, with personalized evaluations fired by agents on each code push,” the company said.
Also: Gartner’s 2027 tech trends just dropped — and they’re about AI
“All data is available not only on Entire’s web interface, but also via the open-source Entire CLI. This allows coding agents to address findings in a loop while the human developer validates progress. Once all evals are satisfied, they can merge the code without looking at the code itself.”
Quite simply, the agents running this process are customizable, and each trail shows how the agents spend tokens.
“With Trails, Entire treats the idea, the agent trace, and the result of developer sessions as first-class artifacts for review alongside the code,” said Dohmke. “It uses multiple agents to generate evals that verify the quality and success of AI-generated code so developers can confidently merge without having to review every line in the difference.”
The company also claims it offers Git hosting “up to 89x faster than GitHub” and six times faster than Cursor origin, thanks to the aforementioned decentralized network. The platform lets developers create, migrate, and host private repositories in multiple locations around the world, currently starting with the US, India, Australia, and the EU.
Also: PHP2Shell: Haven’t you patched yet? Take these steps now to reduce
Another differentiating factor is Continuous Memory, which keeps developer session logs alongside the code in the repo as a data source. Agents can use them to search for answers, which, in short, helps them use up to 71% fewer tokens. This is similar to other memory features in AI chatbots that reduce the time spent gathering context by using past conversations or other agent interactions, if provided, to speed up query response time. In short, Continuous Memory consists of a codebase graph and an “agentic brain” that uses previous sessions and prompts as lessons, so that agents do not repeat mistakes.
Totally available for all developers to try today.