# Projects Public software with source code, design decisions and reproducible results. Each project page explains the problem, demonstrated capabilities and limitations. - ## [Citable Publication]() Deterministic HTML, Markdown and JSON publishing from one corpus, with integrity verification before release and reproducible faults. Python · License: MIT [Read the project]() · [Repository]() - ## [RAG Evaluation Workbench]() Reproducible RAG evaluation with BM25, dense and hybrid retrieval, local CPU inference, and separate retrieval and answer metrics. Python · License: MIT [Read the project]() · [Repository]() - ## [Agent Replay Runtime]() Durable tool execution with event replay, idempotency keys and recovery after real process crashes. Includes effect traces and cases that stop instead of retrying automatically. Python · License: MIT [Read the project]() · [Repository]() - ## [Agent Injection Evals]() Reproducible prompt-injection evaluation with a pinned local model, simulated tools and separate metrics for task capability, attack attempts and realized effects. Python · License: MIT [Read the project]() · [Repository]() - ## [MCP Contract Harness]() Read-only MCP server and independent clients for checking stdio negotiation, pagination, errors and cancellation, with actual wire messages and reproducible reports. Python / JavaScript · License: MIT [Read the project]() · [Repository]()