Enum Commands 

pub enum Commands {
    Init {
        force: bool,
    },
    Status,
    Reset {
        yes: bool,
    },
    Load {
        file: PathBuf,
        name: Option<String>,
        chunker: String,
        chunk_size: usize,
        overlap: usize,
    },
    ListBuffers,
    ShowBuffer {
        buffer: String,
        chunks: bool,
    },
    DeleteBuffer {
        buffer: String,
        yes: bool,
    },
    Peek {
        buffer: String,
        start: usize,
        end: Option<usize>,
    },
    Grep {
        buffer: String,
        pattern: String,
        max_matches: usize,
        window: usize,
        ignore_case: bool,
    },
    ChunkIndices {
        buffer: String,
        chunk_size: usize,
        overlap: usize,
    },
    WriteChunks {
        buffer: String,
        out_dir: PathBuf,
        chunk_size: usize,
        overlap: usize,
        prefix: String,
    },
    AddBuffer {
        name: String,
        content: Option<String>,
    },
    UpdateBuffer {
        buffer: String,
        content: Option<String>,
        embed: bool,
        strategy: String,
        chunk_size: usize,
        overlap: usize,
    },
    ExportBuffers {
        output: Option<PathBuf>,
        pretty: bool,
    },
    Variable {
        name: String,
        value: Option<String>,
        delete: bool,
    },
    Global {
        name: String,
        value: Option<String>,
        delete: bool,
    },
    Search {
        query: String,
        top_k: usize,
        threshold: f32,
        mode: String,
        rrf_k: u32,
        buffer: Option<String>,
        preview: bool,
        preview_len: usize,
    },
    Aggregate {
        buffer: Option<String>,
        min_relevance: String,
        group_by: String,
        sort_by: String,
        output_buffer: Option<String>,
    },
    Dispatch {
        buffer: String,
        batch_size: usize,
        workers: Option<usize>,
        query: Option<String>,
        mode: String,
        threshold: f32,
    },
    Chunk(ChunkCommands),
}

Available CLI commands.

Variants

Init

Initialize the RLM database.

Creates the database file and schema if they don’t exist.

Fields

force: bool

Force re-initialization (destroys existing data).

Status

Show current RLM state status.

Reset

Reset RLM state (delete all data).

Fields

yes: bool

Skip confirmation prompt.

Load

Load a context file into a buffer.

Fields

file: PathBuf

Path to the context file.

name: Option<String>

Optional name for the buffer.

chunker: String

Chunking strategy (fixed, semantic, code, parallel).

chunk_size: usize

Chunk size in characters.

overlap: usize

Overlap between chunks in characters.

ListBuffers

List all buffers.

ShowBuffer

Show buffer details.

Fields

buffer: String

Buffer ID or name.

chunks: bool

Show chunks as well.

DeleteBuffer

Delete a buffer.

Fields

buffer: String

Buffer ID or name.

yes: bool

Skip confirmation prompt.

Peek

Peek at buffer content.

Fields

buffer: String

Buffer ID or name.

start: usize

Start offset in bytes.

end: Option<usize>

End offset in bytes (default: start + 3000).

Grep

Search buffer content with regex.

Fields

buffer: String

Buffer ID or name.

pattern: String

Search pattern (regex).

max_matches: usize

Maximum number of matches.

window: usize

Context window size around matches.

ignore_case: bool

Case-insensitive search.

ChunkIndices

Get chunk indices for a buffer.

Fields

buffer: String

Buffer ID or name.

chunk_size: usize

Chunk size in characters.

overlap: usize

Overlap between chunks in characters.

WriteChunks

Write chunks to files.

Fields

buffer: String

Buffer ID or name.

out_dir: PathBuf

Output directory.

chunk_size: usize

Chunk size in characters.

overlap: usize

Overlap between chunks in characters.

prefix: String

Filename prefix.

AddBuffer

Add text to a buffer (intermediate results).

Fields

name: String

Buffer name.

content: Option<String>

Content to add (reads from stdin if not provided).

UpdateBuffer

Update an existing buffer with new content.

Re-chunks the buffer and incrementally updates embeddings.

Fields

buffer: String

Buffer ID or name.

content: Option<String>

New content (reads from stdin if not provided).

embed: bool

Automatically embed new chunks after update.

strategy: String

Chunking strategy (semantic, fixed, parallel).

chunk_size: usize

Chunk size in characters.

overlap: usize

Chunk overlap in characters.

ExportBuffers

Export all buffers to a file.

Fields

output: Option<PathBuf>

Output file path (stdout if not specified).

pretty: bool

Pretty-print if JSON format.

Variable

Set or get context variables.

Fields

name: String

Variable name.

value: Option<String>

Value to set (omit to get current value).

delete: bool

Delete the variable.

Global

Set or get global variables.

Fields

name: String

Variable name.

value: Option<String>

Value to set (omit to get current value).

delete: bool

Delete the variable.

Search

Search chunks using hybrid semantic + BM25 search.

Returns chunk IDs and scores. Use chunk get <id> to retrieve content.

Fields

query: String

Search query text.

top_k: usize

Maximum number of results.

threshold: f32

Minimum similarity threshold (0.0-1.0).

mode: String

Search mode: hybrid, semantic, bm25.

rrf_k: u32

RRF k parameter for rank fusion.

buffer: Option<String>

Filter by buffer ID or name.

preview: bool

Include content preview in results.

preview_len: usize

Preview length in characters.

Aggregate

Aggregate findings from analyst subagents.

Reads JSON findings from stdin or a buffer, groups by relevance, deduplicates, and outputs a synthesizer-ready report.

Fields

buffer: Option<String>

Read findings from a buffer instead of stdin.

min_relevance: String

Minimum relevance to include (none, low, medium, high).

group_by: String

Group findings by this field (chunk_id, relevance, none).

sort_by: String

Sort findings by this field (relevance, chunk_id, findings_count).

output_buffer: Option<String>

Store aggregated results in a new buffer with this name.

Dispatch

Dispatch chunks for parallel subagent processing.

Splits chunks into batches suitable for parallel subagent analysis. Returns batch assignments with chunk IDs and metadata.

Fields

buffer: String

Buffer ID or name.

batch_size: usize

Number of chunks per batch (overrides –workers).

workers: Option<usize>

Number of worker batches to create (alternative to –batch-size).

query: Option<String>

Filter to chunks matching this search query.

mode: String

Search mode for query filtering (hybrid, semantic, bm25).

threshold: f32

Minimum similarity threshold for query filtering.

Chunk(ChunkCommands)

Chunk operations (get, list, embed).

Trait Implementations

impl Debug for Commands

fn fmt(&self, f: &mut Formatter<'_>) -> Result

Formats the value using the given formatter.

impl FromArgMatches for Commands

fn from_arg_matches(__clap_arg_matches: &ArgMatches) -> Result<Self, Error>

Instantiate Self from ArgMatches, parsing the arguments as needed.

fn from_arg_matches_mut( __clap_arg_matches: &mut ArgMatches, ) -> Result<Self, Error>

Instantiate Self from ArgMatches, parsing the arguments as needed.

fn update_from_arg_matches( &mut self, __clap_arg_matches: &ArgMatches, ) -> Result<(), Error>

Assign values from ArgMatches to self.

fn update_from_arg_matches_mut<'b>( &mut self, __clap_arg_matches: &mut ArgMatches, ) -> Result<(), Error>

Assign values from ArgMatches to self.

impl Subcommand for Commands

fn augment_subcommands<'b>(__clap_app: Command) -> Command

Append to Command so it can instantiate Self via FromArgMatches::from_arg_matches_mut

fn augment_subcommands_for_update<'b>(__clap_app: Command) -> Command

Append to Command so it can instantiate self via FromArgMatches::update_from_arg_matches_mut

fn has_subcommand(__clap_name: &str) -> bool

Test whether Self can parse a specific subcommand