{
  "id": 18920832,
  "title": "Entire's Git Forge Rethinks Git Collaboration for Coding Agents",
  "url": "https://urgent.news/2026/11/08/entires-git-forge-rethinks-git-collaboration-for-coding-agents",
  "topic": "tech",
  "section": "Tech",
  "published": "2026-11-08T11:00:00.000Z",
  "source": {
    "name": "InfoQ",
    "slug": "infoq",
    "url": "https://www.infoq.com/news/2026/11/entire-git-forge-coding-agents/"
  },
  "original_language": "en",
  "account": "Entire, a new Git forge designed for collaboration between human developers and AI coding agents, is challenging the status quo of software development infrastructure. Its creators, notably former GitHub CEO Thomas Dohmke, argue that traditional pull request (PR) models are inadequate when AI agents are involved in code generation, review, and iteration. Entire's approach centers on asynchronous orchestration, versioning, and auditing of AI agents working alongside humans.\n\nOne of Entire's core components is \"trails,\" which replaces the traditional PR timeline as an audit log that developers can read. Instead, trails feature eval scores, updated on every push, that help developers gauge whether a PR has reached a stable state or requires further iteration by AI agents. These scores are based on factors like code quality, security, and whether human review is necessary.\n\nDevelopers can initiate a trail from a bug report, feature request, or manually, and trails can span multiple repositories. Whenever new code is pushed, a review agent in a cloud sandbox evaluates the changes and provides a score and rationale for code quality, security, and the need for human review. If the slop score is orange, developers can prompt their coding agent to improve the code and push a new change, creating a new iteration.\n\nEntire's architecture allows for pushes up to 89 times faster than GitHub. Continuous memory, an innovative feature, preserves all accumulated knowledge in the repository so that AI agents can reuse it across sessions. This is achieved through two open-source tools: entire-graph, which builds a precomputed map of the Git repository, and entire-brain, a persistent memory layer created by combining the codebase map with previous agent sessions and information from Git history.\n\nThe platform also supports integrations with CI platforms like Buildkite and Depot. Entire's focus on addressing the issue of reasoning being thrown away between developers and code artifacts is a key differentiator. As noted by Entire's Haimantika, this issue stems from poor commit messages and documentation, which lack the necessary context. Entire aims to fix this by providing agents with the \"why\" behind every code change.",
  "summary": "Entire is a Git forge designed specifically for collaboration between human developers and AI coding agents. Its premise is that traditional software development infrastructure, particularly the pull request (PR) model, is not well suited to an environment where AI agents generate, review, and iterate on code at high speed. By Sergio De Simone",
  "key_points": [
    "Entire, a new Git forge, rethinks collaboration for coding agents",
    "Trails replace traditional PR timeline as audit log with eval scores",
    "Entire's continuous memory preserves AI agent knowledge across sessions"
  ],
  "editors_take": null,
  "illustration": null,
  "coverage": {
    "outlets": 1,
    "also_reported_by": []
  },
  "ai_generated": true,
  "disclaimer": "Summaries, key points and the editor’s take are written by software from other outlets’ reporting and may contain errors — always check the linked original."
}