Matryoshka
未认领MCP server for token-efficient large document analysis via the use of REPL state
安装
npx matryoshka-rlm "How many ERROR entries are there?" ./server.log工具（19 个）
lattice_bindings
Show current variable bindings and memo labels
lattice_close
Close the session and free memory
lattice_expand
Expand a handle to see full data (with optional limit/offset)
lattice_help
Get Nucleus command reference
lattice_llm_batch_respond
Respond to a pending (llmbatch ...) suspension with all N responses
lattice_llm_respond
Respond to a pending (llmquery ...) suspension
lattice_load
Load a document for analysis
lattice_memo
Store arbitrary context as a memo handle (no document required)
lattice_memo_delete
Delete a stale memo to free memory
lattice_query
Execute Nucleus commands on the loaded document
lattice_reset
Reset all bindings and memos but keep document loaded
lattice_status
Get session status, document info, and memo usage
lattice-http
HTTP server for Nucleus queries
lattice-mcp
MCP server exposing direct Nucleus commands (no LLM required)
lattice-pipe
Pipe adapter for programmatic access
lattice-repl
Interactive REPL for Nucleus commands
lattice-setup
Setup script for Claude Code integration
rlm
Main CLI for document analysis with LLM reasoning
rlm-mcp
MCP server with full RLM + LLM orchestration (analyzedocument tool)