EviCortex

EviCortex documentation

EviCortex is a pre-alpha, local-first Python research kernel for evidence-preserving, temporal memory in LLM applications. It stores exact source observations, derives rebuildable views, and compiles traceable evidence into a hard estimated-token context budget.

The project is testing a research hypothesis; it has not established that it is better than a tuned dense, hybrid, graph, agentic, or production RAG system. Start with the getting-started guide to run the implemented kernel.

Choose a path

Goal Start here
Install EviCortex and run a temporal-memory example Getting started
Understand evidence, claims, time, projections, and capsules Core concepts
Look up public classes, methods, and provider options API guide
Reproduce tests and research checkpoints Benchmarking and reproducibility
Check current limitations, security boundaries, and common questions FAQ and limitations
  1. Follow Getting started and inspect the returned MemoryCapsule.
  2. Read Core concepts, especially namespaces, temporal revisions, and the difference between exact evidence and derived claims.
  3. Use the API guide when integrating the embedded library.
  4. Read FAQ and limitations before evaluating EviCortex for real data or a multi-user application.
  5. Use Benchmarking and reproducibility before interpreting or publishing performance results.

Design and research record

These documents describe the deeper design, evaluation contract, and retained results:

The result files are engineering checkpoints with named configurations and explicit claim boundaries. The synthetic suites are useful for regression testing, but they are not substitutes for official external benchmarks, a shared reader model, calibrated abstention, or statistically powered comparisons.

Current implementation boundary

Implemented today:

Not yet established or production-ready:

See FAQ and limitations for the operational consequences of these boundaries.