Entire launches a distributed Git network built for AI coding agents

Entire, the developer-platform startup founded by former GitHub CEO Thomas Dohmke, launched a preview of a distributed Git network designed to handle the heavy read traffic from AI coding agents. The network mirrors repositories across regions to offload concurrent clones and pulls, preventing rate limits and central server strain. Entire also introduced a semantic memory layer and features like Entire Blame and Entire Review to log agent sessions and improve code review.

Entire https://entire.io , the developer-platform startup founded by former GitHub chief executive Thomas Dohmke, has launched a preview of a distributed Git network built for the age of AI coding agents. The pitch is to spread code hosting across regions rather than lean on a single central provider. The reasoning is a familiar strain in the agent era. As more coding agents https://thenextweb.com/news/cursor-anysphere-2-billion-funding-50-billion-valuation-ai-coding clone and pull code at once, central hosts start to buckle, a pressure GitHub itself felt when it froze new Copilot sign-ups https://thenextweb.com/news/github-copilot-signup-pause-agentic-ai-usage-limits as agentic usage broke its economics. Entire’s answer is a mirror. The preview, open under a waitlist with active regions in the US, EU and Australia, lets a developer mirror an existing GitHub repository in one step, leaving the code where it is while agents clone and pull from a regional Entire copy instead. The point is to offload heavy, concurrent read traffic so agents can keep working without hitting rate limits. In the coming months, the company says, it will let developers host new public and private repositories natively. The longer-term ambition is fuller decentralisation. Entire plans to build out a network of interconnected nodes that would let teams keep code in-region for data residency and sovereignty while remaining part of a single global system. Dohmke frames it as a return to first principles. “By design, Git was always meant to be distributed,” he said, arguing that centralised hosting has become a fundamental constraint now that billions of agents and developers are hammering the same servers. He is not the only one making that bet. Dohmke has personally backed Tangled https://thenextweb.com/news/europes-tangled-raises-e3-8m-from-byfounders-and-githubs-ex-ceo , a separate decentralised Git effort, and the idea of routing around a single provider has been gathering momentum across the developer world. To back the performance claims, Entire published a set of benchmarks from its own testing. It says it sustained roughly 570,000 clones an hour from a single repository, 586 pushes a second, and about 470 combined clone-and-push operations a second on one repo, using scripts of simulated agents. The mixed test is the one meant to mirror how an agent actually works, cloning a repository, pushing a handful of changes, then repeating in a tight loop. Entire says it held that pattern at roughly 50 to 60 milliseconds of median latency. Those figures are the company’s own, not independently verified. Entire says it will open-source the Git backend and the benchmark suite behind them, which would let outsiders test the numbers for themselves. The network sits on top of the product Entire launched in February, a semantic memory layer meant to stop agents repeating past mistakes. It now plugs into major coding tools including Claude Code, Codex, Cursor, Factory AI and GitHub Copilot, storing each session, prompt and tool call in the repository alongside the code. New features build on that history. Entire Blame shows not just who changed a line but the agent session and prompt behind it, while Entire Review sends a branch to several agents at once for an intent-aware read of the diff. A search feature, meanwhile, lets developers and agents query not just how code changed over time but why it was written. Dohmke argues the logs matter as much as the code. “Session logs are now the second most important artifact in software development, and they belong in the repository alongside the code,” he said, casting the memory layer as a way to cut wasted tokens and speed up review. The company has grown to more than 40 people spread across nine countries, with plans to reach 60 by the end of the year. It is doing so on the back of a record $60m seed round, raised in February at a $300m valuation, that gave the venture one of the largest launches in developer tools to date. Get the TNW newsletter Get the most important tech news in your inbox each week.