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