Recursive Language Models for Large Codebases

AI Engineer · youtube · 2026-07-13

This talk covers using Recursive Language Models (RLM) in massive codebases. As codebases grow, coding agents often lose architectural context and get overwhelmed by tool outputs. To fix this, the repo can be loaded into a programmable REPL, letting the model write its own code to inspect the repo and use llmquery to recursively break down problems and delegate focused subtasks.

The video also demos the end-to-end workflow of RLM Code, which runs on both local and cloud models with a fully observable/auditable trajectory. The speaker is Shashi (Superagentic AI), focusing on building tools and frameworks for AI agents.

Original post →

More from coding & agent

coding & agent channel →