By rand
Adds recursive language model orchestration with multi-provider routing, unbounded context handling, and epistemic verification for hallucination detection. Externalizes conversation and files as Python REPL variables for efficient large-context analysis.
Run performance benchmarks for RLM-Claude-Code.
Review the current changes following docs/process/code-review.md.
Invoke the RLM orchestrator agent for complex context management tasks.
Toggle or configure RLM (Recursive Language Model) mode.
Bypass RLM mode for a simple operation.
Uses power tools
Uses Bash, Write, or Edit tools
Own this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge. GitHub access is read-only (username + org membership).
Sign in to claimOwn this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge. GitHub access is read-only (username + org membership).
Sign in to claimBased on adoption, maintenance, documentation, and repository signals. Not a security audit or endorsement.
Transform Claude Code into a Recursive Language Model (RLM) agent with intelligent orchestration, unbounded context handling, persistent memory, and REPL-based decomposition.
rlm-core integration: This project bundles rlm-core as a required dependency, providing shared Rust-based implementations with recurse. rlm-core provides 10-50x faster pattern classification via PyO3 bindings. Pre-built wheels are available for common platforms.
RLM (Recursive Language Model) enables Claude to handle arbitrarily large contexts by decomposing complex tasks into smaller sub-queries. Instead of processing 500K tokens at once, RLM lets Claude:
This results in better accuracy on complex tasks while optimizing cost through intelligent model selection.
brew install [email protected] or python.orgcurl -LsSf https://astral.sh/uv/install.sh | shrustup update stable — not needed if installing from pre-built wheelsDownload the wheel for your platform from GitHub Releases, then:
pip install rlm_claude_code-*.whl
# Clone with submodules (rlm-core is bundled)
git clone --recurse-submodules https://github.com/rand/rlm-claude-code.git
cd rlm-claude-code
# Build and install (compiles rlm-core Rust library)
maturin develop --release
# Install Python dependencies
uv sync --all-extras
# Verify
python -c "import rlm_core; print(rlm_core.version())"
uv run pytest tests/ -v
# Add the marketplace (one-time setup)
claude plugin marketplace add github:rand/rlm-claude-code
# Install the plugin
claude plugin install rlm-claude-code@rlm-claude-code
The plugin includes rlm-core (bundled via maturin). After installation:
# Navigate to the plugin directory (adjust version number as needed)
PLUGIN_DIR=~/.claude/plugins/cache/rlm-claude-code/rlm-claude-code/$(ls ~/.claude/plugins/cache/rlm-claude-code/rlm-claude-code/ | sort -V | tail -1)
cd "$PLUGIN_DIR"
# Create venv and install (includes rlm-core)
uv venv && uv sync
# Verify rlm-core is available
"$PLUGIN_DIR/.venv/bin/python" -c "import rlm_core; print('rlm_core OK:', rlm_core.version())"
Restart Claude Code. You should see "RLM initialized" on startup.
Test the hooks manually:
PLUGIN_DIR=~/.claude/plugins/cache/rlm-claude-code/rlm-claude-code/$(ls ~/.claude/plugins/cache/rlm-claude-code/rlm-claude-code/ | sort -V | tail -1)
"$PLUGIN_DIR/.venv/bin/python" "$PLUGIN_DIR/scripts/init_rlm.py"
# Should print: RLM initialized
When updating, you'll need to re-create the venv:
claude plugin update rlm-claude-code@rlm-claude-code
# Re-setup the new version
PLUGIN_DIR=~/.claude/plugins/cache/rlm-claude-code/rlm-claude-code/$(ls ~/.claude/plugins/cache/rlm-claude-code/rlm-claude-code/ | sort -V | tail -1)
cd "$PLUGIN_DIR" && uv venv && uv sync
# rlm-core is bundled — no extra linking needed
Efficient skill management system with progressive discovery — 410+ production-ready skills across 33+ domains
A disciplined AI-assisted development workflow with specification-first development, test-driven implementation, ADRs, and traceable task management. Inspired by the Rue language development process.
npx claudepluginhub rand/rlm-claude-code --plugin rlm-claude-codeRecursive Language Model for large context processing with token efficiency
Automatic model switching for Claude Code based on prompt complexity. No API key required.
Context management and multi-agent orchestration with performance optimization tools
Agent skill for handling long-context tasks through recursive decomposition strategies based on RLM research (Zhang, Kraska, Khattab 2025)
Intelligent delegation framework for routing tasks to external LLM services while retaining strategic oversight
Multi-LLM orchestration: delegate to Claude, Codex, and Gemini from a single interface with session management and async jobs.