Back to browse
GitHub Repository

A Lens into your codebase - RLM-powered repository analysis using Recursive Language Models with enterprise-grade cost control and security

5 starsPython

Rlm-codelens – Codebase intelligence with recursive language model

by wizmlveteran·Feb 25, 2026·2 points·1 comment

AI Analysis

●●SolidBig BrainWizardry

Graph-aware RLM decomposition beats context-window limits; but Codeium/Sourcegraph Cody solve this already.

Strengths
  • Actual static analysis (NetworkX graphs) before RLM reasoning—not just prompt chaining; multi-language tree-sitter support with auto-install
  • Cost control via token budgets is thoughtful for teams running expensive models iteratively
Weaknesses
  • 'Codebase Q&A' is crowded (Cursor, Continue, Cody, CodeGraph CLI on HN last month)
  • No demo output or performance benchmarks; unclear if RLM layering beats cheaper single-pass approaches
Target Audience

Architects, tech leads analyzing large legacy codebases; teams migrating or refactoring systems

Similar To

Sourcegraph Cody · Cursor · Continue IDE Extension

Similar Projects

Developer Tools●●●Banger

Local, privacy-first MCP code intelligence in Rust

AST-aware codebase search and onboarding beats grep, ships as local MCP server.

Big BrainSolve My ProblemWizardry
avirajkhare
103mo ago