MCP server exposing streamparse: parse partial / truncated JSON, extract JSON from messy LLM output, validate JSON streams. Built for Claude Desktop, Cursor, Cline, Windsurf, and Zed.

Deterministic link provenance for LLM output. Flattens Markdown links the model never grounded, keeps the ones it did. No network, no model, no dependencies.

MCP server: structured-output enforcer. Extract JSON from messy LLM output, validate against a shape spec, and produce retry feedback when the model returns the wrong shape. Wraps @mukundakatta/agentcast.

n8n community node for the Nexara speech-to-text API: transcription, diarization, speaker roles, emotion recognition, and structured LLM output

LLM output guard for n8n: LLM-aware JSON extraction + real ajv JSON Schema validation + a repair-loop contract (Valid / Repair / Failed outputs) for HTTP-based LLM workflows. Never throws; every repair attempt is visible in the execution log.

Overwing MCP server: guardrails for LLM output. Score any text for safety, quality and compliance and get pass / fail / review verdicts with calibrated confidence, from any MCP-capable agent. Plus Overwing Atlas: identify any User-Agent string against a r

Extract structured data from LLM output with streaming support

Agentic orchestration and semantic enforcement for structured LLM output, with native JSON repair and deterministic retries.

Pre-processing pipeline that fixes the most common ways LLM output breaks remark-math/KaTeX

Shared LLM generation policy for DeepSeek Harness session-title providers

Multi-language library for parsing labeled/structured LLM output

Resolver and validator for the SourceCheck spec: machine-checkable source refs for LLM output.

Pipeline to strip LLM output noise and minimize token count before re-prompting

Objectivist-inspired Named Entity Recognition with grammar-constrained LLM output

Harness-neutral Traditional Chinese enforcer + offline converter (skill, DSH bundle, CLI). One script axis either way + Cantonese/Japanese-only filters. Converts both ways; optional wording preference. Also: an LLM output guard, cp950/GBK console scan.

Much like tests in traditional software, evals are an important part of bringing LLM applications to production. The goal of this package is to help provide a starting point for you to write evals for your LLM applications, from which you can write more c

Provider-neutral LLM service interface for the DeepSeek Harness

TypeScript library for Islamic text translation prompts with LLM output validation and prompt stacking utilities.

Streaming XML parser for LLM output — incremental chunk input, structured event output

JavaScript library for parsing labeled/structured LLM output