Turn any LLM into a reliable local JSON API | Contract-first local LLM API builder for structured JSON outputs, model/prompt comparison, schema validation, repair/retry, model switching, and runtime testing.

🛡️ Programmable Guardrails for LLM Applications in Java. A framework-agnostic toolkit for input/output validation, PII masking, and jailbreak detection. The Java alternative to NVIDIA NeMo Guardrails.

The new package transforms a user’s plain‑text search phrase into a structured, BM25‑ranked list of PostgreSQL search results. It takes the query text as input, forwards it to an LLM that rewrites the

A new package that processes user-provided text input to generate structured summaries of technical challenges, such as the difficulty of implementing resumable LLM streaming. It uses a system prompt

A unified suite of MCP suppressors that prevent hallucinations, enforce grounding, and stabilise agent behaviour.

A practical Python toolkit for evaluating, monitoring, and governing LLM outputs in production

Return Surface Analysis is a defensive security review heuristic for finding risk in the less-analyzed direction of a system: the path by which data, metadata, errors, artifacts, or tool output returns from a boundary-crossing operation.

Design-by-contract: verify your function inputs and outputs. Includes a large number of generated verifcation functions for convenience.