CLI Reference

`rlmx "query"`

Run an RLM query against a context.

rlmx "query" [options]

The default command. Loads context into a Python REPL, then iterates with the LLM until it produces a final answer.

Options

Flag	Type	Default	Description
`--context <path>`	string	—	Path to context directory or file
`--output <mode>`	string	`text`	Output mode: `text`, `json`, or `stream`
`--verbose`	boolean	`false`	Show iteration progress on stderr
`--max-iterations <n>`	number	`30`	Maximum RLM iterations before forced termination
`--timeout <ms>`	number	`300000`	Timeout in milliseconds (5 minutes)
`--stats`	boolean	`false`	Emit JSON stats to stderr (or include in `--output json`)
`--log <path>`	string	—	Write structured JSONL log to file
`--tools <level>`	string	`core`	Tool level: `core`, `standard`, or `full`
`--max-cost <n>`	number	—	Maximum USD spend per run
`--max-tokens <n>`	number	—	Maximum total tokens per run
`--max-depth <n>`	number	—	Maximum recursive `rlm_query` depth
`--ext <list>`	string	`.md`	File extensions for context dirs (comma-separated)
`--thinking <level>`	string	—	Thinking level: `minimal`, `low`, `medium`, `high` (Gemini only)
`--cache`	boolean	`false`	Enable CAG mode (full context cached in system prompt)

Context loading

Input	Behavior
`--context dir/`	Recursively reads files matching `--ext` as `list[{path, content}]`
`--context file.md`	Reads as single string
`--context file.json`	Parses JSON as dict or list
stdin pipe	Reads as single string

Examples

# Basic query with directory context
rlmx "How does IPC work?" --context ./docs/

# JSON output with stats
rlmx "Summarize this" --context paper.md --output json --stats

# Code analysis with extended file types
rlmx "Analyze code" --context ./src/ --tools full --ext .ts,.js

# Budget-limited query
rlmx "Quick question" --max-cost 0.10 --max-tokens 5000

# Piped input with logging
echo "data" | rlmx "Analyze this" --log run.jsonl

# CAG mode for repeated queries
rlmx "First question" --context ./docs/ --cache
rlmx "Follow-up question" --context ./docs/ --cache

# Gemini thinking mode
rlmx "Complex analysis" --context ./src/ --thinking high

Output formats

{
  "answer": "The answer to your query...",
  "references": ["docs/start/create-project.md", "docs/concept/ipc.md"],
  "usage": {
    "inputTokens": 12500,
    "outputTokens": 3200,
    "llmCalls": 5
  },
  "iterations": 3,
  "model": "google/gemini-3.1-flash-lite-preview"
}

`rlmx init`

Scaffold a new rlmx.yaml config file in the current directory.

rlmx init [--dir <path>]

Flag	Type	Default	Description
`--dir <path>`	string	`.` (cwd)	Directory to scaffold in

Creates a fully commented rlmx.yaml with sensible defaults. Idempotent — skips creation if the file already exists.

You can skip rlmx init entirely. RLMX auto-scaffolds on first query if no config is found.

Example

# Scaffold in current directory
rlmx init

# Scaffold in a specific directory
rlmx init --dir ./my-project

`rlmx cache`

Pre-warm the provider cache or estimate context size and costs.

rlmx cache [options]

Flag	Type	Default	Description
`--context <path>`	string	—	Path to context directory or file
`--estimate`	boolean	`false`	Show cost estimate without making LLM calls
`--ext <list>`	string	`.md`	File extensions for context dirs

Examples

# Estimate cache costs (no LLM calls)
rlmx cache --context ./docs/ --estimate

# Warm the provider cache
rlmx cache --context ./docs/

# Estimate with custom extensions
rlmx cache --context ./src/ --ext .ts,.js --estimate

Estimate output

The --estimate flag shows token counts, provider limits, and cost projections without making any API calls:

Context: ./docs/ (23 files, 145KB)
Estimated tokens: 43,500
Provider limit: 1,000,000 (google)
Cache retention: long
Estimated first-query cost: $0.003
Estimated cached-query cost: $0.0003 (90% savings)

`rlmx batch`

Run bulk queries from a questions file against cached context.

rlmx batch <file> [options]

Flag	Type	Default	Description
`--context <path>`	string	—	Path to context directory or file
`--max-iterations <n>`	number	`30`	Maximum RLM iterations per question
`--max-cost <n>`	number	—	Maximum total USD spend across all questions
`--parallel <n>`	number	`1`	Concurrent questions
`--batch-api`	boolean	`false`	Use Gemini Batch API for 50% cost reduction
`--output <mode>`	string	—	Output mode
`--verbose`	boolean	`false`	Show progress

Cache is always enabled for batch mode. See Batch Mode for full details.

Example

# Run questions from a file
rlmx batch questions.txt --context ./docs/

# With budget cap
rlmx batch questions.txt --context ./src/ --max-cost 1.00

# Low iteration count for quick answers
rlmx batch questions.txt --context ./docs/ --max-iterations 3

`rlmx config`

Manage global settings stored at ~/.rlmx/settings.json.

`rlmx config set`

rlmx config set <key> <value>

Set a configuration value. Values are type-coerced: "true" becomes boolean, numeric strings become numbers.

rlmx config set GEMINI_API_KEY sk-abc123
rlmx config set model.provider google
rlmx config set model.model gemini-3.1-flash-lite-preview
rlmx config set budget.max_cost 0.50
rlmx config set gemini.thinking_level medium

`rlmx config get`

rlmx config get <key>

Retrieve a setting value. API keys are masked in output.

$ rlmx config get model.provider
google

`rlmx config list`

rlmx config list

Show all configured settings. Sensitive keys (containing API_KEY, SECRET, TOKEN) are masked.

`rlmx config delete`

rlmx config delete <key>

Remove a setting.

`rlmx config path`

rlmx config path

Print the settings file path (~/.rlmx/settings.json).

Common keys

Key	Description	Example
`GEMINI_API_KEY`	Google Gemini API key	`AIza...`
`ANTHROPIC_API_KEY`	Anthropic API key	`sk-ant-...`
`OPENAI_API_KEY`	OpenAI API key	`sk-...`
`GROQ_API_KEY`	Groq API key	`gsk_...`
`XAI_API_KEY`	xAI API key	`xai-...`
`OPENROUTER_API_KEY`	OpenRouter API key	`sk-or-...`
`model.provider`	LLM provider	`google`, `anthropic`, `openai`
`model.model`	Model ID	`gemini-3.1-flash-lite-preview`
`model.sub_call_model`	Model for `llm_query()` sub-calls	`gemini-3.1-flash-lite-preview`
`budget.max_cost`	Default max USD per run	`0.50`
`budget.max_tokens`	Default max tokens per run	`100000`
`budget.max_depth`	Default max recursion depth	`3`
`tools_level`	Default tool level	`core`, `standard`, `full`
`cache.retention`	Cache TTL strategy	`short`, `long`
`gemini.thinking_level`	Default thinking level	`minimal`, `low`, `medium`, `high`
`gemini.google_search`	Enable web search battery	`true`
`gemini.code_execution`	Enable server-side Python	`true`

Priority order

Settings are resolved in this order (highest priority first):

CLI flags (--max-cost 0.10)
Project rlmx.yaml
Global ~/.rlmx/settings.json
Hardcoded defaults

Tool levels

The --tools flag controls which functions are available in the REPL:

`core` (default)

Paper-faithful RLM functions:

Function	Description
`context`	Injected context variable
`llm_query(prompt)`	Single LLM completion
`llm_query_batched(prompts)`	Concurrent LLM calls
`rlm_query(prompt)`	Recursive child RLM session
`rlm_query_batched(prompts)`	Parallel child RLM sessions
`SHOW_VARS()`	List all REPL variables
`FINAL(answer)`	Terminate with answer string
`FINAL_VAR(name)`	Terminate with variable value

Plus any custom tools defined in rlmx.yaml.

`standard` (core + batteries)

All core functions plus utility batteries:

Function	Description
`describe_context()`	Metadata overview of loaded context
`preview_context()`	Content sample
`search_context(query)`	Semantic search over context
`grep_context(pattern)`	Regex search over context
`chunk_context()`	Split context into chunks
`chunk_text(text)`	Split arbitrary text by size
`map_query(fn, items)`	Distributed LLM calls
`reduce_query(fn, items)`	Aggregation queries

With Google provider, also includes Gemini batteries:

Function	Description
`web_search(query)`	Google web search
`fetch_url(url)`	Fetch and summarize URL content
`generate_image(prompt)`	Image generation

`full` (standard + environment)

All standard functions plus auto-injected information about available Python packages and versions in the REPL environment.

Global flags

These flags work with any command:

Flag	Description
`--help`, `-h`	Show help message
`--version`, `-v`	Show version

Getting Started

CLI Reference

Configuration

CLI Reference

CLI Reference

`rlmx "query"`

Options

Context loading

Examples

Output formats

`rlmx init`

Example

`rlmx cache`

Examples

Estimate output

`rlmx batch`

Example

`rlmx config`

`rlmx config set`

`rlmx config get`

`rlmx config list`

`rlmx config delete`

`rlmx config path`

Common keys

Priority order

Tool levels

`core` (default)

`standard` (core + batteries)

`full` (standard + environment)

Global flags

Getting Started

CLI Reference

Configuration

​CLI Reference

​rlmx "query"

​Options

​Context loading

​Examples

​Output formats

​rlmx init

​Example

​rlmx cache

​Examples

​Estimate output

​rlmx batch

​Example

​rlmx config

​rlmx config set

​rlmx config get

​rlmx config list

​rlmx config delete

​rlmx config path

​Common keys

​Priority order

​Tool levels

​core (default)

​standard (core + batteries)

​full (standard + environment)

​Global flags

CLI Reference

`rlmx "query"`

Options

Context loading

Examples

Output formats

`rlmx init`

Example

`rlmx cache`

Examples

Estimate output

`rlmx batch`

Example

`rlmx config`

`rlmx config set`

`rlmx config get`

`rlmx config list`

`rlmx config delete`

`rlmx config path`

Common keys

Priority order

Tool levels

`core` (default)

`standard` (core + batteries)

`full` (standard + environment)

Global flags