← back

RLM: Recursive Language Models for Large Codebases - Shashi, Superagentic AI

3.2K views · Jul 12, 2026 · 17:27 min · Watch on YouTube ↗
Takeaway

Treat a large repository as structured data that an agent can query programmatically instead of loading it wholesale into context.

Summary

  • Recursive language models externalize repository context into a programmable REPL, where the model writes code to inspect and select relevant evidence.
  • Recursive LLM queries delegate questions to other model calls and return bounded observations before final synthesis.
  • Superagentic AI’s open-source RLM Code demonstrates this pattern with local or hosted models, a Docker sandbox, and inspectable execution traces.
rlmcontext-managementcodebases
Original description
Large codebases break coding agents: they lose the architecture and drown in tool output as context grows. This talk introduces Recursive Language Models (RLM) from a MIT paper a pattern that loads the repo into a programmable REPL where the model writes code to inspect it and recursively delegates focused sub-questions via llm_query. With a live demo on RLM Code (independent, unofficial), you'll see the loop run end to end on local and cloud models, with a fully inspectable trajectory.

Speakers:
Shashi (Superagentic AI): Building tools and frameworks for AI Agents
  X/Twitter: https://x.com/Shashikant86
  LinkedIn:   / shashikantjagtap  
  GitHub: https://github.com/Shashikant86