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.
More from coding & agent
- An MCP server signs every AI agent tool call into a verifiable Merkle chain — Funky_Chicken_22 · 2026-07-22
- Claude Code skill uses 10 Markdown rules to make outputs ADHD-friendly — alex_verem · 2026-07-22
- A Firecracker-based platform says it can host 6,000 AI agents on one 256 GB server — maritime_sh · 2026-07-22
- A better path to agent autonomy is running waves, finding friction, and iterating — JnBrymn · 2026-07-22
- AI agent designers map the visual and tonal cues behind companionship products — Unlikely-Platform-47 · 2026-07-22
- Coding agents are heading toward an AI-writes, AI-reviews, human-approves workflow — aftahi_ai · 2026-07-22