streaming-json

A micro-library of stream components for building custom JSON and JSONC processing pipelines with a minimal memory footprint — parse, filter, and transform JSON far larger than available memory with a SAX-inspired token API, on Node.js or Web Streams.

Progressive UI from LLM

+4M Downloads! Repair invalid LLM JSON, commonly used to parse the output of LLMs — Parsing ChatGPT and llm JSON stream response — Partial and incomplete JSON parser python library for OpenAI | repair invalid JSON, parse output of LLMs

The OData v4.01 Producer for Laravel

A list of examples that involve streaming with Akka Streams and used together with Akka HTTP

Repair incomplete JSON (e.g. from streaming APIs or AI models) so it can be parsed as it's received.

Small, independent TypeScript packages for LLM plumbing — token budgets, streaming JSON repair, cost accounting, retries, embedding caches. No provider SDKs.

🔧 Kotlin Multiplatform library for parsing and repairing partial/incomplete JSON strings. Perfect for handling streaming JSON from LLMs like ChatGPT. Features real-time JSON completion, robust error handling, and pure Kotlin implementation. Supports parse incomplete JSON into objects and complete/repair partial JSON to valid format.

Library for parsing potentially huge json streams on devices with scarce memory . Based on mrfaptastic/json-streaming-parser2, modified and extended independently.

Streaming JSON for Web Streams: NDJSON, incremental array streaming, and partial JSON for LLM output. Zero dependencies, runs on every runtime.

Pre-release. Deterministic, spec-cited grades for CMS hospital price-transparency files, published with the evidence attached: files are discovered from cms-hpt.txt, streamed rather than loaded into memory, graded fail-closed against the CMS rule and schema docs, and every number on the site is generated from a committed comparison document.

O(1) streaming JSON parser for the AI era. Zero dependencies. ~4KB gzipped.

Stream typed, validated partial objects out of an LLM token stream — render structured output as it arrives, with per-field completion status.

Import Microsoft Skype / Teams 'Chat history' data exports into MongoDB for easy browsing and search. Streams large messages.json files without loading them into memory.