Overview
Understanding how Recurse works under the hood—RAGE, frames, and structural extraction
Recurse works automatically—you upload sources, route requests through the proxy, subscribe to Context Streams, and structure extraction happens in the background. These concept pages explain the mechanisms underneath, for those curious about how the system works or planning to build on top of the infrastructure.
Core Mechanisms
RAGE
The processing engine that transforms unstructured sources into structured knowledge graphs.
Handles source ingestion, frame extraction, and relationship mapping. Creates evolving structures that navigate meaning rather than just matching keywords.
Frames
Typed semantic units with named slots that capture meaning and relationships.
The fundamental building blocks that enable navigation by structure. Frames reference each other and nest recursively to form knowledge graphs.
Adaptive Schemas
Schema discovery without predefined ontologies.
The system learns frame patterns from your content automatically. Creates emergent structure that adapts as you add sources across different domains.
Temporal Versioning
Evolution tracking with complete history preservation.
New information updates previous understanding while maintaining timestamps, diffs, and explanations. Creates living memory that stays current without losing context.
Continuous Knowledge
Source Subscriptions
Continuous, automatic ingestion from individual feeds.
Monitor URLs and RSS for ongoing updates. Temporal versioning maintains both current understanding and complete evolution history as sources change.
Context Streams
Domain expertise sharing based on trust and authority.
Experts share subgraphs of their knowledge bases—sources, documents, and semantic connections. Subscribe to streams from people you trust for queryable expertise.
How These Work Together
Frame extraction provides structured semantic units. Adaptive schemas enable the structure to emerge from your content. Temporal versioning maintains knowledge currency while preserving evolution history. Source subscriptions keep information flowing automatically. Context Streams package expertise for sharing. Recursivity enables iterative refinement. RAGE integrates all these mechanisms into a coherent system.
The architectural consequence: Recurse treats knowledge as living structures rather than static text. This enables retrieval systems that navigate relationships rather than just matching keywords, accumulate genuine understanding rather than aggregating text, and support actual inquiry rather than just answering questions.