Implements the Recursive Language Model pattern, enabling LLMs to process arbitrarily long contexts through session-based document management, on-demand chunking, BM25 search, and artifact storage.
Enables AI assistants to analyze documents larger than their context window by loading files into RAM and querying them via search, navigation, and Python execution tools. Supports recursive reasoning to process massive datasets in chunks using sub-agents.
An MCP server implementing Recursive Language Models (RLM) to process arbitrarily large contexts through a programmatic probe, recurse, and synthesize loop. It enables LLMs to perform multi-step investigations and evidence-backed extraction across massive file sets without being limited by standard context windows.
Enables an LLM to analyze documents far larger than its context window by emitting constrained symbolic S-expression commands that are validated and executed server-side, avoiding vector databases and chunking heuristics. Large intermediate results are kept as in-memory handles so the model carries compact stubs instead of full text, and recursive sub-queries let it reason over structured portions of a document.
Enables token-efficient analysis of documents far larger than an LLM context window by executing constrained symbolic commands against server-side handles instead of chunking or vector databases. It supports recursive queries, multi-document contexts, and memoized context stubs for compact agent interactions.