Cloud Native Batch System (Project under CNCF).
Directory
Search results
Published directory entries matching your search.
A comprehensive testing and evaluation framework for voice agents across language models, prompts, and agent personas.
An inference and serving engine for language models.
VLFeat is an open and portable library of computer vision algorithms, which has a Matlab toolbox.
JSMLT - Machine learning toolkit with classification and clustering for Node.js; supports visualization (see ).
Some of the python libraries were cut-and-pasted from.
Enterprise-Grade Graph RAG for Secure, On-Premise AI with Verifiable Attribution.
AI product development platform to experiment with, evaluate, and deploy advanced LLM apps.
AutoML algorithm tool chain by Huawei Noah's Arb Lab.
"leaderboard Comparing LLM Performance at Producing Hallucinations when Summarizing Short Documents".
Vast.ai provides machine-learning models, research, training resources, or evaluation tools.
Minimize LLM token complexity to save API costs and model computations.
Any URL to clean markdown for LLMs. Free API, no signup required. Strips JS/CSS and outputs LLM-ready content.
Open-source project that provides machine-learning models, research, training resources, or evaluation tools.
unpkg.ai provides machine-learning models, research, training resources, or evaluation tools.
Change just one letter and get github repo context to use as context for your LLM.
Open-source project that provides machine-learning models, research, training resources, or evaluation tools.
Discover datasets around the world!
A Java implementation of Twitter's text processing library.
Tusk provides machine-learning models, research, training resources, or evaluation tools.
Open-source project that provides machine-learning models, research, training resources, or evaluation tools.
Documentation for Tune, covering setup, features, and practical usage.
Python library for automatic extraction of relevant features from time series.
TruLens instruments your AI agent with OpenTelemetry, scores every step with benchmarked LLM judges, and tells you which version to ship.