OpenAI Builds Pando to Scale Git for Codex

Nov 3, 2026
OpenAI built Pando, a new Git repository backend that supports more concurrent work from Codex while preserving existing Git workflows.

In a company blog post, OpenAI describes Pando, a new backend that now powers all development in its monorepo. The system retains compatibility with the Git protocol and client, so engineers and coding agents can continue using existing workflows.

OpenAI built Pando after increased Codex use produced more branches, pushes, merges, fetches, clones, and continuous integration jobs. The previous infrastructure experienced slow operations and failed merges, with reliability sometimes falling below 90%.

Pando coordinates updates to each branch independently, allowing pushes to unrelated branches to proceed in parallel. It stores incoming packfiles as immutable blobs and reuses packfiles across fetches, reducing the computation needed to serve many clients. OpenAI says Pando reduced median push latency by nearly five times and now delivers almost one petabyte of Git data each day.

We hope you enjoyed this article

Consider subscribing to one of our newsletters like Daily AI Brief or AI Programming Weekly.

Also, consider following us on social media:

AI Brief AI Brief (X)
Free newsletter

AI Programming Weekly

Weekly news about AI tools for software engineers, AI enabled IDE's and much more.

Guide
AI app builders

AI app builders

Tools that turn a description into a working web or mobile app, and the platforms companies use to build internal tools with AI

Whitepaper

Tensordyne Napier: What If One Rack Could Do the Work of Nine?

Tensordyne

This Tensordyne whitepaper presents Napier, an inference-focused AI processor and rack-scale system based on the company’s TDN Math logarithmic number system. It examines infrastructure requirements for large mixture-of-experts and agentic models, compares major inference architecture approaches, and details the TDN AIP processor, TDN72 pod, TDN Link fabric, and Napier Ultra configuration. The paper reports simulation-based performance, cost, and accuracy-validation results, including Tensordyne’s projected comparison of one Napier rack with a nine-rack Nvidia Rubin plus Groq deployment; the chip is reported as taped out and in fabrication.

Read more

You may also like

Free, six days a week

Daily AI Brief: the AI news that matters, in your inbox.