OpenAI builds Pando Git backend with AI agents
Original title: OpenAI Builds Pando Git Infrastructure Using AI Agents and Deploys Continuous Security Testing
OpenAI deployed Pando, a new Git infrastructure built using Codex agents, supporting its monorepo with continuous security testing.
OpenAI constructed Pando, a custom Git backend, in 10 weeks using AI agents from Codex. The system replaced the previous setup behind the main code repository without interrupting engineering. Agents now run continuous red-team testing on Pando and Git, with production traffic starting in April 2026.
- Median push latency reduced by nearly 80%
- Delivers nearly a petabyte of Git data daily
- Cache hit rates above 99%
- Implemented in Rust with no legacy dependencies
- Uses Lean and TLA+ for system checks
- 1.Upgrade to Pando via OpenAI's public Git repository
From the original article
3 min read at cybersecuritynews.com
OpenAI has built Pando, a new Git backend, with Codex agents in just 10 weeks, replacing the system behind its main shared code repository without stopping engineering work. The company says agents now run around the clock to red-team both Git and Pando, testing the software that supports its growing AI-driven development workload. In its […]
By Guru Baran · cybersecuritynews.com
A short excerpt; the article and its images belong to the publisher. Summary, key facts and assessment above are AI-written from the article and can be wrong.