Intel

Privacy Terms Submit Map API for Agents

Monorepo vs multi-repo: agent navigation vs end-to-end testing tradeoffs — Intel — VibeLeaderboard

← All Intel

Clip / Other

Monorepo vs multi-repo: agent navigation vs end-to-end testing tradeoffs

From Benchmarking Coding Agents on New vs Legacy Codebases — Denys Linkov, Wisedocs · ≈15:16

“So, if you put it into a higher-level folder, right, they could navigate the the file directory.”

“But, for doing that end-to-end testing and verification and deployment, it's still much harder to do with multiple repos.”

“if you're building a sandbox environment to run sort of a full AI factory, it's it also takes more time to clone repos and get everything set up.”

What’s in it

Explains why one team ditched multi-repo setups for a monorepo
Shows how AI agents navigate multiple repos vs a single one
Reveals sandboxing pain points when running full AI dev pipelines

Watch this moment ↗

Clip transcript

>> Yeah, so the question was before we had multiple repos and did we move into monorepo? Yes, uh we did that. One of the things we found now was that models are much better at navigating multiple repos. So, if you put it into a higher-level folder, right, they could navigate the the file directory. But, for doing that end-to-end testing and verification and deployment, it's still much harder to do with multiple repos. Uh and if you're building a sandbox environment to run sort of a full AI factory, it's it also takes more time to clone repos and get everything set up.