Directory
Published directory entries matching your search.
Future AGI is an open-source, self-hostable platform for evaluating, observing, and improving LLM and AI agent applications. It combines tracing, evals, simulations, datasets, a gateway and guardrails on one platform with a feedback loop. The Apache 2.0 core can be self-hosted, and a managed Cloud option is offered.
Future AGI SDK is a production-grade software development kit for AI evaluation, prompt management, and observability. It offers automated evaluations with sub-100ms guardrails and does not require human-in-the-loop. The SDK supports Python and TypeScript.
Testing framework dedicated to ML models, from tabular to LLMs. Detect risks of biases, performance issues and errors in 4 lines of code.
Cloud-Native LLM Routing Engine. Improve LLM app resilience and speed.
Go binding for MXNet c predict api to do inference with a pre-trained model.
Creating semantic cache to store responses from LLM queries.
GPUStack is a GPU cluster manager built for high-performance AI model serving, with support for vLLM and SGLang, and offers on-demand SSH-accessible GPU instances, hosted in the gpustack/gpustack GitHub repository.
Gradio is an open-source Python library that enables developers to build and share machine learning web applications easily. It provides simple interfaces for creating demos and sharing models, supporting a wide range of ML frameworks.
Hydrosphere Mist is a serverless proxy for Spark clusters. It offers a functional programming framework and deployment model for Spark applications, with a REST HTTP and messaging API for Scala and Python Spark jobs. Sessions are managed across EMR, Hortonworks, Cloudera, DC/OS and vanilla Spark clusters.
This repository provides a hyperparameter optimization implementation for machine learning algorithms, accompanying a paper on hyperparameter optimization theory and practice. It includes sample code for regression and classification problems using the Boston-Housing and MNIST datasets, covering algorithms such as random forest, SVM, KNN and artificial neural networks.
An archived educational course repository for learning about LLMs, LLMOps and vector databases by designing, training and deploying a real-time financial advisor LLM system. It includes source code, video and reading materials, and covers a training pipeline using QLoRA and a streaming pipeline ingesting financial news. The repository was archived by its owner and is read-only.
Build multimodal AI services via cloud native technologies · Model Serving · Generative AI · Neural Search · Cloud Native.
Kaito is the Kubernetes AI Toolchain Operator, an operator suite that automates LLM inference, fine-tuning and RAG engine deployment in a Kubernetes cluster. It simplifies the CRD API and provides optimized preset configurations for inference engine scheduling parameters. Workspaces are the basic CRD for managing inference and tuning workloads, and all vLLM-supported models can be run.
Kubeflow Katib is a Kubernetes-native project for automated machine learning (AutoML). It supports hyperparameter tuning, early stopping and neural architecture search, and is agnostic to machine learning frameworks, natively supporting frameworks such as TensorFlow, PyTorch and XGBoost. Training jobs can use any Kubernetes Custom Resources, with out-of-box support for Kubeflow Training Operator, Argo Workflows and Tekton Pipelines. A Python SDK simplifies creating tuning jobs.
Kubernetes custom resource definition for serving ML models on arbitrary frameworks.
Kitaru is an open-source, self-hosted tool providing replay-based evaluations for AI agents. It records or imports production runs as sessions and replays them against a changed model, prompt, or code, with tool calls answered from the recording. It is available for Python and TypeScript and comes from the team behind ZenML.
Knowledge3D (K3D) is a sovereign GPU-native reference implementation for the W3C PM-KR specification. It aims to unify web knowledge representation by allowing humans and AI to consume the same procedural knowledge from a single source, addressing fragmentation across fonts, embeddings, metadata, and renderings.
KServe is a standardized distributed generative and predictive AI inference platform for scalable, multi-framework deployment on Kubernetes. It is a Cloud Native Computing Foundation incubating project. The platform supports backends such as vLLM and llm-d for serving LLMs, and multi-framework predictive serving. Standalone installation on standard Kubernetes is described as more lightweight but without canary deployment or request-based autoscaling with scale-to-zero.
Laminar is an open-source observability platform purpose-built for AI agents. It provides OpenTelemetry-native tracing with a one-line SDK setup, plain-English signals that alert in Slack, and an SDK and CLI for running evals. It is written in Rust with 20x trace compression, and can be used via a managed platform or self-hosted with Docker Compose.
FastAPI framework to build production-grade LLM applications.
LanceDB is a developer-friendly open-source embedded retrieval library for multimodal AI. It emphasizes searching more and managing less. The project tagline is 'Search More; Manage Less.' It is available on GitHub.
An archived, read-only repository that provided a way to deploy LangChain apps using Jina and FastAPI, wrapping apps as services on Jina AI Cloud. The README notes the project is no longer maintained and that it could deploy apps on a user's own infrastructure.
LangKit is an open-source toolkit for monitoring large language models (LLMs). It extracts signals from LLM prompts and responses, and offers features such as text quality assessment, relevance metrics, and sentiment analysis to support LLM observability.
LangWatch is a platform for evaluating large language models and testing AI agents. The open-source project is hosted on the GitHub platform under the langwatch organization as the langwatch/langwatch repository.
