[](https://dl.circleci.com/status-badge/redirect/gh/taneliang/coerce-llm-output/tree/main) [![codecov](https://codecov.io/github/taneliang/coerce-l

Detect degenerate LLM output that arrives with a 200 OK. Zero dependencies, deterministic, composes with any retry or fallback layer.

Headless streaming markdown engine for React: block splitting, smooth reveal, per-char fade animation and LLM output preprocessing

A robust utility to repair JSON strings - fix malformed or broken JSON, especially from LLM output like ChatGPT.

Clean LLM output to keyboard-printable text

LLM output evaluation metrics for Node.js/TypeScript

Framework-free DOM adapter for AIGUI — stream LLM output straight into the DOM.

A robust utility to repair JSON strings - fix malformed or broken JSON, especially from LLM output like ChatGPT.

Score LLM output instead of asserting equality. Deterministic metrics, an optional LLM judge, and the bill for both.

stream LLM output to telegram via sendMessageDraft + finalize sendMessage

Parse partial JSON as it streams in. Type-safe, tiny, built for LLM output.

A powerful, type-safe library to convert Markdown (incl. GFM tables, code, mentions, and LLM output) into Slack Block Kit JSON — and back. Supports Slack's native data_table block with dynamic cell typing.

React adapter for AIGUI — stream LLM output into live React components with cards, plugins, and interactive widgets.

Vue 3 adapter for AIGUI — stream LLM output into live Vue components with cards and plugins.

A markdown renderer component using remark/rehype with syntax highlighting, mermaid diagram support, and streaming mode for LLM output.

Pydantic/Instructor-style LLM output validation with retry loops and grammar enforcement

MCP server for AI content validation — multi-dimensional quality checks for LLM output

Ridiculously fast Markdown for React and AI. Streaming-native renderer that caches settled code lines, table rows, and list items so growing LLM output does not re-parse finished work.

UICP parser for extracting and rendering UI components from LLM output

A simple workflow showing how to work with structured LLM output in Loopstack.