Anthropic ditches Git for custom source control after 12x code velocity surge
Source published ·Modelwire updated
Original coverage: Simon Willison ↗·How Modelwire adds context
The development
Anthropic's shift to a custom source control system signals how rapidly scaling AI development has outpaced conventional infrastructure. The company's code merge rate jumped 12x in four months, from 2,500 to 30,000 daily changes, forcing a rethink of Git-based workflows. This reflects a broader pattern among frontier labs: as model training cycles compress and deployment velocity accelerates, standard developer tooling becomes a bottleneck. The move matters beyond Anthropic because it exposes how infrastructure assumptions built for slower software cycles break under AI-scale iteration. Other labs likely face identical pressures, making this a canary for how the entire industry may need to rearchitect development pipelines.
Modelwire’s AI-generated summary of coverage from Simon Willison.
Modelwire analysis
Analyst takeOur AI-generated reading of the wider context and the next developments to watch.
The detail worth sitting with is the timeline: four months to a 12x increase in daily code changes. That pace suggests the bottleneck isn't engineering headcount or model capability but the coordination layer underneath, and Anthropic is now building infrastructure that most software companies have never needed to consider.
This connects directly to the story from October 9th about Claude orchestrating up to 1,000 parallel agents. If a single orchestration run can spawn that many concurrent sub-agents, each potentially generating code artifacts, the pressure on merge pipelines becomes obvious. The source control redesign looks less like a one-off ops decision and more like a downstream consequence of the agentic architecture Anthropic is actively shipping. The evaluation isolation story from October 10th adds another layer: Anthropic is simultaneously air-gapping its test environments and rebuilding its commit infrastructure, which together suggest a company rearchitecting its entire development loop around agent-generated output at volume.
Watch whether OpenAI or Google DeepMind disclose similar infrastructure rewrites within the next two quarters. If they do, this confirms the merge rate pressure is a frontier-lab-wide structural problem rather than an Anthropic-specific scaling artifact.
This interpretation is generated from the summary above and the archive coverage cited below. Our methodology · Report an error
Coverage behind this analysis
These archive entries ground the connection in our analysis. They are ordered by source publication date, with links to our coverage and the original sources.
·The Decoder
Claude orchestrates 1,000 parallel agents to boost bug detection threefold
Anthropic has expanded Claude's agent capabilities to coordinate up to 1,000 parallel sub-agents through dynamic workflows, a significant step toward practical multi-agent systems at scale. Testing shows the approach dramatically improves real-world performance: while a single agent identified 27 of 70 bugs in code review, the orchestrated workflow caught 66, suggesting hierarchical task distribution unlocks…
MentionsAnthropic · Git · Simon Willison · Claude
How this coverage is produced
Modelwire uses AI to generate summaries and context from source headlines, snippets, and selected archive coverage. Automated checks do not verify every claim, and items are not routinely reviewed by a person before publication. Zacaria Solis operates the site. Read the linked source for the full evidence and report errors through our corrections process.
Modelwire summarizes, we don’t republish. Simon Willison originally reported this story as “Redesigning source control at Anthropic”. The full content lives on simonwillison.net. If you’re a publisher and want a different summarization policy for your work, see our takedown page.