https://github.com/leocelis/cairn

Deterministic entity/world-model engine for AI agents — resolve, traverse, and assemble trustworthy context with zero LLM calls on the hot path.

ai-agents context-engineering deterministic entity-resolution knowledge-graph python rag retrieval zero-dependencies

Last synced: 22 Jul 2026

https://github.com/leocelis/blindkey

Local-first credential broker for AI agents — secrets your agents can use but never see. 66 testable security constraints. Rust.

ai-agents argon2 claude-code credential-broker credentials encryption local-first mcp password-manager privacy rust secrets-management security

Last synced: 22 Jul 2026

https://github.com/leocelis/eif

Epistemic Integrity Framework — the scientific method applied to AI agent reasoning

Last synced: 22 Jul 2026