Entire Inc., the developer-platform startup founded by former GitHub Chief Executive Thomas Dohmke, has launched a preview of a distributed Git network built to let artificial intelligence coding agents clone and push code without running into the rate limits of centralized hosting. The preview, opened on July 8, 2026, is available by waitlist with active regions in the United States, European Union, and Australia.
The core idea is straightforward: developers can mirror an existing GitHub repository onto Entire in a single step. The code stays on GitHub while an AI agent clones and pulls from a regional Entire mirror, offloading the heavy concurrent read traffic that agents generate so they can keep building without hitting caps. For the latest developments in AI tooling and developer platforms, readers can follow our AI industry coverage at the homepage.
The Problem: Centralized Git as a Bottleneck
Dohmke argues that centralized Git hosting has turned into a fundamental constraint as AI agents scale. The strain of large numbers of agents and developers hitting a single server shows up as rate limits, high latency, or even outages. He ran Microsoft-owned GitHub for four years before leaving in August 2025 to build Entire.
By design, Git was always meant to be distributed, Dohmke explained. In the era of agents, centralized Git hosting has become a fundamental constraint, as the strain of billions of agents and developers hammering a central server shows up in the form of rate limits, high latency, or even outages. Today, he said, we begin to return Git to its original promise, with a distributed and soon fully decentralized and open-sourced network of interconnected nodes around the world.
Benchmark Results: Hundreds of Thousands of Operations per Hour
Entire said it rebuilt the Git back end specifically to handle simultaneous, high-volume agent activity, and the early testing numbers are striking. In one test, the network sustained approximately 570,000 clones per hour from a single repository, with 200 simulated clients shallow-cloning across Frankfurt, Paris, London, and Dublin.
A separate push test held 586 pushes per second, or roughly 2.1 million per hour, to a single repository. A mixed test that looped cloning and pushing the way an agent runs in practice sustained about 470 operations per second. The company plans to open-source both the Git backend and the benchmark suite behind these figures.
Agent-Aware Features: Blame, Review, and Semantic Search
Beyond raw throughput, Entire has built features that draw on the reality that AI agents now write and review significant portions of code. The platform includes a semantic memory layer that captures each agent session, prompt, and tool call, filing them in the repository alongside the code itself.
Entire Blame surfaces the agent session, prompt, and decision behind a specific line of code, extending the traditional Git blame concept to the agentic era. Entire Review sends a branch to multiple agents in parallel for an intent-aware code review. A code and semantic search feature lets developers query why code was written, not just what changed.
Dohmke argues that session logs have become the second most important artifact in software development and belong in the repository next to the code. Keeping that memory tied to the repo, he says, stops agents from repeating mistakes and lets developers verify what was built and why.
Integrations and Company Background
Entire now integrates with major coding agents including Claude Code, Codex, Cursor, Factory AI, and GitHub Copilot. The company is just five months old, having launched in February 2026 with a $60 million seed round on a $300 million valuation.
The startup now employs more than 40 people across nine countries, including the United States, Australia, Germany, India, and the Netherlands. It expects to reach 60 employees by year's end. Native hosting for new public and private repositories is due in the coming months, and Entire also wants to fully decentralize the network so code can sit in-region, which it says will help developers meet data residency and sovereignty rules.
A Broader Shift Toward Agent-Native Infrastructure
Entire's launch reflects a broader industry shift toward building infrastructure that assumes AI agents are first-class users of developer tools. As coding agents from Anthropic, OpenAI, Cursor, and others increasingly handle tasks from writing features to reviewing pull requests, the systems that support them are being rethought from the ground up.
The tension between centralized platforms and the distributed origins of Git is not new, but the scale of agent-driven traffic gives it fresh urgency. Whether Entire can compete with GitHub's entrenched network effects remains an open question, but the company's focus on agent-native features and open-source commitment positions it as a notable new entrant in the developer tools landscape.
Stay Ahead of AI
The Entire distributed Git network preview is open by waitlist. For more breaking AI news and developer tooling coverage, visit AI Buzz Wire.
Read more AI news →
