Context Cortex

The Context Cortex is lean-ctx's intelligence layer that goes beyond simple file caching. It connects multiple data sources, ranks content by relevance, and proactively prefetches context your AI agent is likely to need next.

Think of it as a search engine for your entire development context — code, issues, documentation, and external APIs — unified into a single query interface.

How It Works

Cross-Source Intelligence

When you read a file, the Cortex automatically surfaces related context from other sources. A ctx_read of auth.rs might append hints from a GitHub issue about JWT expiry or a Jira ticket about the authentication refactor.

Provider Bandit

lean-ctx uses Thompson sampling to learn which providers deliver the most useful context for your workflow. Providers that consistently return relevant results get queried more often; noisy providers are automatically deprioritized.

Thompson sampling adjusts query probability based on historical relevance scores. Higher-scoring providers receive more queries.

Active Inference

Based on your recent tool calls, the Cortex predicts what context you'll need next and prefetches it in the background. If you just read auth.rs and middleware.rs, it might pre-query GitHub issues tagged with 'authentication'.

Consolidation Engine

The consolidation engine merges provider chunks into the session cache. It deduplicates content across sources, applies token budgets, and ensures the most relevant context is always available — even if the original provider is temporarily unreachable.