rlm-rs

Recursive Language Model (RLM) CLI for Claude Code - handles long-context tasks via chunking and recursive sub-LLM calls.

Based on the RLM pattern from arXiv:2512.24601, enabling analysis of documents up to 100x larger than typical context windows.

Features

• Hybrid Semantic Search: Combined semantic + BM25 search with RRF fusion
• Auto-Embedding: Embeddings generated automatically during load (BGE-M3 model)
• Pass-by-Reference: Retrieve chunks by ID for efficient subagent processing
• Multiple Chunking Strategies: Fixed, semantic, code-aware, and parallel chunking
• Code-Aware Chunking: Language-aware chunking at function/class boundaries
• HNSW Vector Index: Optional scalable approximate nearest neighbor search
• Incremental Embedding: Efficient partial re-embedding for updated content
• Agentic Workflow Support: dispatch/aggregate commands for parallel subagent processing
• SQLite State Persistence: Reliable buffer management across sessions
• Regex Search: Fast content search with context windows
• Memory-Mapped I/O: Efficient handling of large files
• JSON/NDJSON Output: Machine-readable output for integration

How It Works

Installation

Via Cargo (Recommended)

cargo install rlm-cli

Via Homebrew

brew tap zircote/tap
brew install rlm-rs

From Source

git clone https://github.com/zircote/rlm-rs.git
cd rlm-rs
make install

Quick Start

# Initialize the database
rlm-cli init

# Load a large document (auto-generates embeddings)
rlm-cli load document.md --name docs --chunker semantic

# Search with hybrid semantic + BM25
rlm-cli search "your query" --buffer docs --top-k 10

# Retrieve chunk by ID (pass-by-reference)
rlm-cli chunk get 42

# Check status
rlm-cli status

# Regex search content
rlm-cli grep docs "pattern" --max-matches 20

# View content slice
rlm-cli peek docs --start 0 --end 3000

Commands

Chunking Strategies

# Semantic chunking (default)
rlm-cli load doc.md --chunker semantic

# Code-aware chunking for source files
rlm-cli load src/main.rs --chunker code

# Fixed chunking with overlap
rlm-cli load logs.txt --chunker fixed --chunk-size 150000 --overlap 1000

# Parallel chunking for speed
rlm-cli load huge.txt --chunker parallel --chunk-size 100000

Supported Languages (Code Chunker)

Rust, Python, JavaScript, TypeScript, Go, Java, C/C++, Ruby, PHP

Claude Code Integration

rlm-cli is designed to work with the rlm-rs Claude Code plugin, implementing the RLM architecture:

Development

Prerequisites

• Rust 1.88+ (2024 edition)
• cargo-deny for supply chain security

Build

# Using Makefile
make build          # Debug build
make release        # Release build
make test           # Run tests
make check          # Format + lint + test
make ci             # Full CI check
make install        # Install to ~/.cargo/bin

# Or using Cargo directly
cargo build --release
cargo test
cargo clippy --all-targets --all-features

Project Structure

src/
├── lib.rs           # Library entry point
├── main.rs          # CLI entry point
├── error.rs         # Error types
├── core/            # Core types (Buffer, Chunk, Variable)
├── chunking/        # Chunking strategies
├── storage/         # SQLite persistence
├── io/              # File I/O with mmap
└── cli/             # Command implementations

tests/
└── integration_test.rs

MSRV Policy

The Minimum Supported Rust Version (MSRV) is 1.88.

License

MIT License - see LICENSE for details.

Documentation

📚 Complete Documentation - Full documentation hub with tutorials, guides, and reference materials

Quick Links

• Getting Started - 5-minute tutorial for new users
• Examples - Practical examples and workflows
• CLI Reference - Complete command documentation
• FAQ - Frequently asked questions
• Troubleshooting - Common issues and solutions
• Glossary - RLM and chunking terminology

Advanced Topics

• Features Guide - Feature flags and build options
• Plugin Integration - Integration with Claude Code
• Architecture - Internal design and architecture
• RLM-Inspired Design - Connection to RLM paper
• API Reference - Rust library documentation
• ADRs - Architectural Decision Records

Citing This Project

If you use rlm-cli in your research or projects, please cite it. You can use GitHub's built-in "Cite this repository" button, or use the following BibTeX:

@software{allen_rlm_cli_2026,
  author       = {Allen, Robert},
  title        = {rlm-cli},
  version      = {1.2.4},
  year         = {2026},
  url          = {https://github.com/zircote/rlm-rs},
  license      = {MIT}
}

Acknowledgments

This project builds on prior work in recursive language model architectures:

• claude_code_RLM - Original Python RLM implementation by Brainqub3 that inspired the creation of this project
• RLM Paper (arXiv:2512.24601) - Recursive Language Model pattern by Zhang, Kraska, and Khattab (MIT CSAIL)
• Claude Code - AI-powered development environment

Adeojo, John. claude_code_RLM. GitHub, 2026. https://github.com/brainqub3/claude_code_RLM

Zhang, Alex L., Tim Kraska, and Omar Khattab. "Recursive Language Models." arXiv:2512.24601, 2025. MIT CSAIL. https://arxiv.org/abs/2512.24601