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
Verify a Release Binary
Every release binary carries SLSA build provenance,
and releases only publish after fail-closed attestation verification. To verify a
download yourself:
gh attestation verify rlm-cli-<version>-<platform> --repo zircote/rlm-rs
See SECURITY.md for details.
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
| Command | Description |
|---|
init | Initialize the RLM database |
status | Show current state (buffers, chunks, DB info) |
load | Load a file into a buffer with chunking (auto-embeds) |
search | Hybrid semantic + BM25 search across chunks |
update-buffer | Update buffer content with re-chunking |
dispatch | Split chunks into batches for parallel subagent processing |
aggregate | Combine findings from analyst subagents |
chunk get | Retrieve chunk by ID (pass-by-reference) |
chunk list | List chunks for a buffer |
chunk embed | Generate embeddings (or re-embed with --force) |
chunk status | Show embedding status |
list | List all buffers |
show | Show buffer details |
delete | Delete a buffer |
peek | View a slice of buffer content |
grep | Search buffer content with regex |
write-chunks | Write chunks to individual files |
add-buffer | Add text to a new buffer |
export-buffers | Export all buffers to JSON |
var | Get/set context variables |
global | Get/set global variables |
reset | Delete all RLM state |
Chunking Strategies
| Strategy | Best For | Description |
|---|
semantic | Markdown, prose | Splits at natural boundaries (headings, paragraphs) |
code | Source code | Language-aware chunking at function/class boundaries |
fixed | Logs, plain text | Splits at exact byte boundaries |
parallel | Large files (>10MB) | Multi-threaded fixed chunking |
# 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:
| RLM Concept | Implementation |
|---|
| Root LLM | Main Claude Code conversation (Opus/Sonnet) |
| Sub-LLM | rlm-subcall agent (Haiku) |
| External Environment | rlm-cli CLI + SQLite |
Development
Prerequisites
- Rust 1.95+ (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 1.95.
License
MIT License - see LICENSE for details.
Documentation
📚 Complete Documentation - Full documentation hub with tutorials, guides, and reference materials
Quick Links
Advanced Topics
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:
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
