Matrix
Matrix (Multi-Agent daTa geneRation Infra and eXperimentation framework) is a versatile engine for multi-agent conversational data generation.
About
Matrix is a library designed for fast and scalable multi-agent conversational data generation. It serves various use cases, including model benchmarking and data processing, by running on a Ray cluster for enhanced scalability. The framework supports large-scale inference for both open-source and proprietary large language models, and it includes features for high-throughput data processing and peer-to-peer orchestration.
Open Source Health
- Stars
- 291
- Forks
- 44
- License
- MIT
- Last commit
- 2 months ago
Resources & Links
Related Categories
Vendor
Facebookresearch
Publisher of Fairseq
Quick Links
Open Source
More by Facebookresearch
Related Products
DataArc-SynData-Toolkit
Synthetic Data Generation Platform By DataArcTech
Top category match
Seamless Communication
Foundational Models for State-of-the-Art Speech and Text Translation
More from this vendor
OrienterNet
Source Code for Paper "OrienterNet Visual Localization in 2D Public Maps with Neural Matching"
More from this vendor
Spider
A general physic-based retargeting framework.
More from this vendor
RPG_KDD2025
This repository provides the code for implementing RPG described in our KDD'25 paper "Generating Long Semantic IDs in Parallel for Recommendation".
More from this vendor