github.com
Open-source project that supports deploying, serving, monitoring, or operating AI and machine-learning systems.
Directory
AI Infrastructure & MLOps
Explore AI Infrastructure & MLOps resources in AI & Machine Learning.
github.com
OpenLIT is an open-source agent harness engineering platform built on OpenTelemetry. It provides tracing, evaluations, guardrails, prompt and context management, and cost and GPU monitoring for the harness around AI agents and coding agents. It is free to self-host under Apache 2.0 and is described as working with many models, frameworks and harnesses.
github.com
Turns your ML code into microservices with web API, interactive GUI, and more.
parea.ai
Platform and SDK for AI Engineers providing tools for LLM evaluation, observability, and a version-controlled enhanced prompt playground.
github.com
pgvecto.rs is an open-source tool that provides scalable, low-latency, hybrid-enabled vector search for PostgreSQL. It is designed to enhance vector search capabilities without modifying the core database system, per its official GitHub repository.
github.com
Open-source vector similarity search for Postgres.
podcast.zenml.io
Pipeline Conversations is a podcast from ZenML featuring interviews with platform engineers, ML practitioners and technical leaders building production AI systems. Episodes cover MLOps and LLMOps topics including Kubernetes workflows, model fine-tuning and evaluation, LLM security, cost optimization, prompt engineering and agents in production.
portkey.ai
Portkey is a production stack for generative AI builders that offers a suite of tools including an AI gateway, observability features, guardrails and prompt management modules. It is designed to help organizations democratize and productionize generative AI.
github.com
pyhsmm is a Python library for approximate unsupervised inference in Bayesian Hidden Markov Models and explicit-duration Hidden semi-Markov Models, focusing on the HDP-HMM and HDP-HSMM with weak-limit approximations. Extensions include autoregressive models, switching linear dynamical systems and factorial models. The package is stated as no longer maintained and was last tested with Python 3.7.
github.com
Open-source project that supports deploying, serving, monitoring, or operating AI and machine-learning systems.
quix.io
Quix is described as an agentic AI platform for hardware engineering. It turns test-rig and sensor data into real-time insight and is presented as automating engineering workflows across the V, from requirements through verification, validation and operation.
github.com
The open source solution for monitoring your AI models in production.
github.com
Rapid-MLX is an open-source, Apache 2.0 licensed large language model inference server and Mac application for Apple Silicon devices. It is compatible with OpenAI and Anthropic APIs, built on the MLX framework, and focused on reliable tool calling for coding agents.
Examples showing how to use the OpenAI vision API to run inference on images, video files and webcam streams.
github.com
Rune is a project that provides containers to encapsulate and deploy EdgeML pipelines and applications. It is associated with the repository hotg-ai/rune and is licensed under Apache 2.0 or MIT at the user's option.
github.com
MLOps framework to package, deploy, monitor and manage thousands of production machine learning models.
github.com
Python-free Rust inference server with OpenAI API compatibility and hot model swapping.
singlebase.cloud
SinglebaseCloud is an AI-native backend platform and Firebase alternative that combines document and vector databases, authentication, storage, and built-in AI services to support the development and scaling of modern applications.
socialbu.com
SocialBu is a social media management tool for planning, scheduling, responding to, automating, and analyzing social media across connected accounts. It offers AI-assisted drafting and refinement of posts and captions, content curation, listening streams for mentions and keywords, a unified inbox, automation rules, and performance reports. A 7-day free trial is mentioned. An MCP Server connects compatible AI clients to supported tasks.
mc-stan.org
Stan is software for Bayesian data analysis that combines statistical modeling capabilities with user-friendly interfaces and open-source development. Its probabilistic programming language supports applications from simple linear regression to multi-level models and time-series analysis. Interfaces exist for Python, Julia, R, and the Unix shell, usable on laptops, clusters, or in the cloud. Official documentation covers the language, inference algorithms, and built-in functions.
github.com
An MLOps/LLMOps platform for model building, evaluation, and fine-tuning.
github.com
Lets you create apps for your ML projects with deceptively simple Python scripts.
superwise.ai
Superwise is a platform offering AI Gateway, Secure AI Chat, and AI Services. Its Sentinel product prevents sensitive data from leaking into external AI tools, Chat provides a safe AI workspace for teams, and its services help organizations plan, build, and govern AI use cases.
systemprompt.io
Self-hosted control plane that sits between connected AI clients, model providers, and tools. It applies access rules to users and agents, routes supported model requests through a gateway, checks governed tool calls before execution, and records policy decisions, execution records, and usage in the operator's environment. It deploys a Rust runtime with PostgreSQL on infrastructure the operator controls.