teamchong/vectorjson
O(n) streaming JSON parser for LLM tool calls. Agents act sooner, abort bad outputs early. WASM SIMD, up to 2000× faster than stock AI SDK parsers.
When your AI agent uses a tool that outputs a large amount of information, like generated code or detailed instructions, it typically sends this information in a JSON stream. Your application or user interface needs to process this stream efficiently, perhaps to show parts of the output immediately, stream content character-by-character, or skip irrelevant sections. This tool is for developers building AI agents who want to significantly speed up how their applications handle these streaming JSON outputs from large language models, making their agents feel faster and more responsive.
Available on npm.
Use this if you are building an AI agent that frequently makes tool calls and streams large JSON payloads, and you need to process these streams with minimal delay and resource usage.
Not ideal if your application only deals with small, single-shot JSON objects, as standard JSON parsing methods will likely be faster in those specific cases.
Stars
14
Forks
—
Language
JavaScript
License
Apache-2.0
Category
Last pushed
Mar 10, 2026
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/llm-tools/teamchong/vectorjson"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
mangiucugna/json_repair
A python module to repair invalid JSON from LLMs
antfu/shiki-stream
Streaming highlighting with Shiki. Useful for highlighting text streams like LLM outputs.
yokingma/fetch-sse
An easy API for making Event Source requests, with all the features of fetch(), Supports...
iw4p/partialjson
+1M Downloads! Repair invalid LLM JSON, commonly used to parse the output of LLMs — Parsing...
kaptinlin/jsonrepair
A high-performance Golang library for easily repairing invalid JSON documents. Designed to fix...