When AI Agents Break Git: How Anthropic Rebuilt Source Control for the Agent Era

说明与用途

Anthropic 用 Scion 替代 Git，以应对每天 30,000 次合并，因为 Git 设计用于人类工作节奏。

问题

Anthropic’s AI coding agents produced 30,000 code merges per day, overwhelming git’s design for human‑scale, offline‑first workflows.

结果

Scion enabled Anthropic to absorb 30,000 daily merges without git failures, eliminating downtime and scaling CI/CD and code review to agent workloads.

工作流

• 1. Measure merge volume and traffic; 2. Identify git limitations for continuous commits; 3. Design Scion with connectivity‑first assumptions; 4. Migrate monorepo to Scion; 5. Deploy complementary tools (Antique, agent‑scale search, IAM).

证据

In May 2026, Anthropic was merging about 2,500 code changes per day. By September, that number had exploded to over 30,000 per day — a 12× increase in just four months.

来源

Git was designed for human developers. Humans work in bursts: write code for hours, commit, push, go home. Agents work continuously: write code in seconds, commit immediately, never stop.

来源

Anthropic built Scion, an in‑house version control system built specifically for agent‑scale development. They migrated their entire monorepo from git in five months.

来源