AI Infrastructure

lakeFS provides data version control for data lakes using Git-style workflows.

Cala provides sourced, typed facts through an API, CLI, and MCP for AI agents to query structured data.

Superwise provides an agent management platform with visibility, guardrails, and policy enforcement for regulated industries.

The goro project provides a high level machine learning library written for Go.

CoderPlan routes API access for Claude Code, Codex, Gemini CLI, and other developer tools through a pay-as-you-go service.

Venice AI generates text, images, characters and video, and offers access to AI models through private or anonymized options.

ModAstera guides teams through data labeling, AI model building, validation, and deployment in one workflow.

Curated list of awesome vector search framework/engine, library, cloud service and research papers to vector similarity search.

This Docker-based starter kit provides a runtime for machine learning work in Jupyter notebooks.

Tilores resolves and deduplicates customer records using fuzzy matching to unify scattered data in real time.

Unsloth Studio provides a local workspace for running and training AI models.

PyTorch TNT supplies lightweight tools and utilities for training with PyTorch.

PAI schedules resources and manages clusters for AI workloads across distributed computing environments.

PyTorch Ignite provides a high level library for flexibly training and evaluating neural networks.

Maze provides an applied reinforcement learning framework for developing projects in Python.

BentoML helps build and serve AI apps and models through inference APIs, job queues, and multi-model pipelines.

Monkt converts PDFs, Word, PowerPoint, Excel, CSV, webpages, and HTML into Markdown or structured JSON.

Curated list of awesome open source libraries to deploy, monitor, version and scale your machine learning.

TensorRT-LLM provides Python and C++ runtimes with optimizations for language model inference on NVIDIA GPUs.

PromptLayer supports prompt versioning, LLM evaluations, and production monitoring with traces, logs, and regression sets.

BLACKBOX AI serves selected open-weight models as dedicated deployments or through one inference endpoint.

DeepSeek’s API documentation lists pricing and capabilities for its DeepSeek-V4-Flash model.

Extensible Toolkit for Finetuning and Inference of Large Foundation Models.

NannyML provides Python tools for post-deployment data science and monitoring model performance under data drift.