rlm-cli 1.3.1

Recursive Language Model (RLM) REPL for Claude Code - handles long-context tasks via chunking and recursive sub-LLM calls
Documentation
cff-version: 1.2.0
message: "If you use this software, please cite it as below."
type: software
title: "rlm-cli"
abstract: >-
  Recursive Language Model (RLM) CLI for Claude Code - handles long-context
  tasks via chunking and recursive sub-LLM calls. Implements hybrid semantic
  and BM25 search with Reciprocal Rank Fusion, code-aware chunking, and
  pass-by-reference chunk retrieval for efficient subagent processing.
version: 1.3.1
date-released: 2026-06-12
license: MIT
url: "https://github.com/zircote/rlm-rs"
repository-code: "https://github.com/zircote/rlm-rs"
authors:
  - family-names: Allen
    given-names: Robert
    email: zircote@gmail.com
    orcid: "https://orcid.org/0009-0007-9691-004X"
identifiers:
  - type: url
    value: "https://github.com/zircote/rlm-rs"
    description: "GitHub repository"
keywords:
  - llm
  - claude
  - recursive
  - language-model
  - repl
preferred-citation:
  type: software
  title: "rlm-cli"
  abstract: >-
    Recursive Language Model (RLM) CLI for Claude Code - handles long-context
    tasks via chunking and recursive sub-LLM calls.
  version: 1.3.1
  date-released: 2026-06-12
  license: MIT
  url: "https://github.com/zircote/rlm-rs"
  repository-code: "https://github.com/zircote/rlm-rs"
  authors:
    - family-names: Allen
      given-names: Robert
      email: zircote@gmail.com
      orcid: "https://orcid.org/0009-0007-9691-004X"
references:
  - type: software
    title: "claude_code_RLM"
    abstract: >-
      Original Python implementation of the Recursive Language Model pattern
      for Claude Code that inspired the creation of rlm-rs.
    url: "https://github.com/brainqub3/claude_code_RLM"
    repository-code: "https://github.com/brainqub3/claude_code_RLM"
    license: MIT
    authors:
      - family-names: Adeojo
        given-names: John
    year: 2026
  - type: article
    title: "Recursive Language Models"
    abstract: >-
      RLMs treat long prompts as part of an external environment and allow the
      LLM to programmatically examine, decompose, and recursively call itself
      over snippets of the prompt. RLMs can handle inputs up to two orders of
      magnitude beyond model context windows.
    url: "https://arxiv.org/abs/2512.24601"
    authors:
      - family-names: Zhang
        given-names: Alex L.
      - family-names: Kraska
        given-names: Tim
      - family-names: Khattab
        given-names: Omar
    year: 2025
    institution:
      name: "MIT CSAIL"