CLI Commands
Complete reference for all ReasonKit CLI commands.
Overview
The ReasonKit CLI (rk) is the primary interface for
interacting with the ReasonKit system.
rk [OPTIONS] <COMMAND>
Global Options
| Flag | Description |
|---|---|
-v, --verbose |
Increase logging verbosity (-v info,
-vv debug, -vvv trace)
|
-c, --config <FILE>
|
Path to configuration file (env:
REASONKIT_CONFIG)
|
-d, --data-dir <DIR>
|
Data directory path (default: ./data, env:
REASONKIT_DATA_DIR)
|
-h, --help |
Print help information |
-V, --version |
Print version information |
Core Commands
think (alias: t)
Execute structured reasoning protocols (ThinkTools). This is the main entry point for running analysis.
rk think [OPTIONS] [QUERY]
Arguments:
-
[QUERY]: The query or input to process (required unless--listis used).
Options:
| Flag | Description | Default |
|---|---|---|
-p, --protocol <NAME>
|
Protocol to execute (gigathink,
laserlogic, bedrock,
proofguard, brutalhonesty)
|
|
--profile <NAME> |
Profile to execute (quick,
balanced, deep,
paranoid)
|
balanced |
--provider <NAME> |
LLM provider (anthropic,
openai, openrouter, etc.)
|
anthropic |
-m, --model <NAME>
|
Specific LLM model to use | Provider default |
-t,
--temperature <FLOAT>
|
Temperature for generation (0.0-2.0) | 0.7 |
--max-tokens <INT> |
Maximum tokens to generate | 2000 |
-b, --budget <BUDGET>
|
Adaptive compute budget (e.g., “30s”, “5m”, “$0.50”) | |
--mock |
Use mock LLM (for testing without API costs) | |
--save-trace |
Save execution trace to disk | |
--trace-dir <DIR> |
Directory to save traces | |
-f, --format <FORMAT>
|
Output format (text, json)
|
text |
--list |
List available protocols and profiles |
Examples:
# Basic usage
rk think "Should I migrate to Rust?"
# Use a specific protocol
rk think "The earth is flat" --protocol proofguard
# Use a specific profile
rk think "Analyze this startup idea" --profile paranoid
# Use a specific provider and model
rk think "Explain quantum physics" --provider openai --model gpt-4o
# List available options
rk think --list
web (alias: dive,
research, deep, d)
Deep research with ThinkTools + Web Search + Knowledge Base.
rk web [OPTIONS] <QUERY>
Arguments:
<QUERY>: Research question or topic.
Options:
| Flag | Description | Default |
|---|---|---|
-d, --depth <DEPTH>
|
Depth of research (quick,
standard, deep,
exhaustive)
|
standard |
--web <BOOL> |
Include web search results | true |
--kb <BOOL> |
Include knowledge base results | true |
--provider <NAME> |
LLM provider | anthropic |
-f, --format <FORMAT>
|
Output format (text, json,
markdown)
|
text |
-o, --output <FILE>
|
Save research report to file |
verify (alias: v,
triangulate)
Triangulate and verify claims with 3+ independent sources.
rk verify [OPTIONS] <CLAIM>
Arguments:
-
<CLAIM>: The claim or statement to verify.
Options:
| Flag | Description | Default |
|---|---|---|
-s, --sources <INT>
|
Minimum number of independent sources required | 3 |
--web <BOOL> |
Include web search for verification | true |
--kb <BOOL> |
Include knowledge base sources | true |
--anchor |
Anchor verified content to ProofLedger (Immutable Record) | |
-f, --format <FORMAT>
|
Output format (text, json,
markdown)
|
text |
-o, --output <FILE>
|
Save verification report to file |
System Commands
mcp
Manage MCP (Model Context Protocol) servers and tools.
rk mcp [SUBCOMMAND]
serve-mcp
Start the ReasonKit Core MCP Server. This allows ReasonKit to be used as a tool by other AI agents (like Claude Desktop).
rk serve-mcp
completions
Generate shell completions.
rk completions <SHELL>
Arguments:
-
<SHELL>: Shell to generate completions for (bash,elvish,fish,powershell,zsh).
Experimental / In Development
The following commands are present in the CLI but may be
unimplemented or require specific feature flags (like
memory) to be enabled during compilation.
-
ingest: Ingest documents into the knowledge base. query: Query the knowledge base directly.index: Manage the search index.stats: Show statistics.export: Export knowledge base data.serve: Start the HTTP API server.trace: View and manage execution traces.-
rag: Perform RAG (Retrieval-Augmented Generation) queries. metrics: View execution metrics.