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

A concrete answer to coding agents losing architecture and drowning in tool output on large repos: a REPL the model programs against, with focused sub-questions delegated recursively instead of accumulating in context.

• context window — The maximum amount of text a model can consider at once — its working memory for the current conversation or task.

• videoBrains vs Hands: How to Run AI Agents Safely in Production — Viren Baraiya
• videoWe Mapped 115 Microservices for Our Coding Agents — Kamalakannan Nandagopal, Postman
• videoTurning Agent Memory Into Skills That Work — Will Lyon, Neo4j
• videoWhy We Deleted Our MCP Server and Rebuilt It — Abhi Arya, Reducto

• videoIt’s Tokens All The Way Down: How RLMs are Different — Kevin Madura, AlixPartnersAI Engineer
• videoRecursive Coding Agents - Raymond Weitekamp, OpenProseAI Engineer
• videoRecursive Language Models — Alex Zhang, MIT PhDLatent Space

Checking sign-in…

Loading comments…