Today for AI
HOT RADAR
toolsHEAT 0.0°

AI CURATED HOT STORY · 10/14/2026

Anthropic Replaces Git with Custom Scion VCS to Handle 30k Daily AI Agent Merges in Five Months

11 reports archived0 independent sourcesupdated 10/16/2026, 22:34:47
Synthesis & Latest Updates

Anthropic's engineering team completed a five-month migration of its entire Monorepo from Git to a custom version control system named Scion, addressing infrastructure bottlenecks caused by AI agents. As models like Claude autonomously iterate code, daily merge volumes surged 12-fold from ~2,500 to over 30,000, overwhelming traditional Git workflows designed for human-scale development.

Cross-verified reports indicate Scion discards Git's offline-centric 'full copy' mechanism, optimizing instead for high-frequency cloud interactions. It introduces 'Antique Change Requests' to replace Pull Requests, enhancing efficiency for massive parallel submissions. This shift marks a fundamental transition in toolchain priorities from human experience to machine throughput and automated integration.

This event highlights the paradigm shift required in the Agentic Coding era. With coding no longer the bottleneck, CI/CD and version control become limiting factors. Anthropic's case demonstrates that legacy DevOps tools cannot sustain AI-driven extreme throughput, signaling an urgent industry need for native infrastructure adapted to machine-led development scales.

LATEST/Anthropic has solidified Scion as its core infrastructure, sparking industry debate on GitHub's stability under high-concurrency AI loads. As AI-generated code share rises, more tech firms are evaluating custom VCS solutions to handle similar merge pressures, accelerating the shift toward AI-native development toolchains.

Coverage timeline

Total 11 reports · Latest first
  1. Hacker News AIT2·78 pts

    Anthropic Builds Custom Git Alternative to Handle AI-Generated Code Surge

    • AI-assisted development increased Anthropic's merge frequency by over 10x in months, exposing toolchain limits.
    • Anthropic designed a new change request abstraction layer instead of merely optimizing Git for high-frequency automated flows.
    • The case signals that DevOps infrastructure must shift from human-machine collaboration to machine-to-machine high-throughput paradigms as AI becomes the primary code producer.
  2. IT之家 · 智能时代T2·78 pts

    Anthropic Replaces Git with Server-Side VCS Scion, Cutting Resource Usage by 200x

    • Scion shifts all version control logic (commits, merges, rebases) to the server, leaving clients with only lightweight caching and local change tracking.
    • Designed for 'always-on' AI agents, it removes Git's offline advantages to minimize sync overhead and storage requirements.
    • Significant performance gains: CPU/memory usage drops to 1/200th of Git, and CI/research task checkouts shrink from minutes to seconds.
  3. Hacker News AIT2·48 pts

    Anthropic's Scion VCS Adopts Recursive Derived Data Inspired by Mononoke to Optimize Blame Operations

    • Scion utilizes a 'derived data' architecture to generate non-changeset data like Blame and Skip Lists via a unified mechanism.
    • The mechanism is recursive, computing child node derived data from parents, allowing easy addition of new acceleration structures.
    • Inspired by Meta's Mononoke, the design aims to optimize specific operations like line-level attribution in large-scale codebases.
  4. 新智元 (微信公众号)T2·68 pts

    Anthropic Builds Scion VCS to Handle 30k Daily Merges Driven by Claude's High-Frequency Code Generation

    • Claude-driven code generation caused Anthropic's daily merge volume to surge 12x to 30,000, breaking the existing Git workflow.
    • A 7-person team spent 5 months building a custom version control system named Scion to migrate their monorepo away from Git.
    • The core bottleneck in AI coding has shifted from 'code generation' to matching efficiency in downstream build, test, and integration phases.
  5. 机器之心 (微信公众号)T2·78 pts

    Anthropic Replaces Git with AI-Built Scion in Five Months: Redefining Code Infrastructure

    • Anthropic migrated from Git to its proprietary system Scion in 5 months with only 7 engineers and Claude.
    • The move was driven by the need to support massive AI coding scales that overwhelmed traditional Git infrastructure.
    • This case highlights AI-assisted development's capability to refactor core engineering infrastructure, not just application code.
  6. InfoQ 中文T2·88 pts

    Anthropic Builds Scion VCS: 7-Person Team Replaces Git to Handle 12x Surge in Claude-Generated Code Commits

    • Claude's autonomous coding caused daily merge volume at Anthropic to surge from 2,500 to over 30,000, breaking existing Git mirror infrastructures under PB-scale data transfer demands.
    • The new system Scion achieved ~100GB Monorepo migration via fine-grained object storage and incremental sync, improving CI checkout speeds by two orders of magnitude.
    • Engineering paradigm shift: Version control systems are now designed as high-throughput AI collaboration infrastructure rather than just human-interaction tools.
  7. 宝玉 (@dotey)T2·78 pts

    Anthropic Builds Scion Version Control System to Handle AI Agent Scale, Migrating from Git in Five Months

    • AI agents increased Anthropic's daily merges from ~2,500 to over 30,000, overwhelming Git's architecture.
    • Scion discards Git's offline-first 'full copy' design, optimizing specifically for cloud-based, high-frequency interactions.
    • Anthropic completed the full migration of its monorepo from Git to Scion in just five months.
  8. Simon Willison 博客T2·78 pts

    Anthropic Replaces Git with Custom Source Control to Handle 30k Daily AI Code Merges

    • Anthropic's code merge frequency increased 12-fold in six months, driven primarily by AI agents rather than human engineers.
    • Traditional Git workflows could not sustain 30,000 daily changes, prompting Anthropic to develop a specialized alternative.
    • The new system introduces 'Antique Change Requests' to optimize review and merge efficiency for massive parallel code submissions.
  10. Anthropic AI (@AnthropicAI)T1·78 pts

    Anthropic Builds Custom Version Control to Replace Git Amid 30K Daily Agent Merges

    • Daily code merges at Anthropic surged from ~2,500 to over 30,000 in months, driven primarily by AI agents rather than human developers.
    • Developer infrastructure designed for human scale became a bottleneck, prompting the company to abandon Git and build a custom version control system.
    • The complete migration of their monorepo from Git to the new VCS was accomplished within five months.
  11. Hacker News AIT2·78 pts

    Anthropic Merges 30k Daily Commits: In-House Scion VCS Redefines AI-Native Dev Infra

    • Coding is no longer the bottleneck; daily merged changes grew >12x to 30,000+ in six months due to Claude's autonomy.
    • Traditional Git/CI architectures struggle with AI-generated volume, forcing Anthropic to build the in-house Scion VCS.
    • AI-native dev infra focus shifts from optimizing human experience to maximizing machine throughput and automated integration.