Discover AI Infrastructure Tools

Formerly text-generation-webui: open-source desktop app and web UI for local LLMs with an OpenAI-compatible API

Local AI server for LLMs, speech and images, tuned for AMD Ryzen AI NPUs and Radeon GPUs

Microsoft's on-device AI runtime and SDK that runs ONNX models on the user's NPU, GPU or CPU

Run and serve local LLMs from Docker Hub or Hugging Face with docker model commands and an OpenAI-compatible API

Run and serve local LLMs in GPU-matched OCI containers with Podman or Docker

Emirati Arabic text-to-speech with real-time streaming for AI agents, IVR and voice-over

Voice agent infrastructure that routes across STT, TTS and LLM providers with region-pinned execution

Real-time text-to-speech API plus speech-to-speech voice conversion, with licensed voices

Real-time text-to-speech in 26 languages, trained and hosted in Europe

AI audio API for generating songs, speech, and sound, with stem splitting, voice conversion, and mastering

One API and one bill for 450+ image, video and audio generation models

Image generation API built for design work, with vector (SVG) output, brand styles and editing tools

API for the FLUX image models and FLUX 3 Video from the German lab that trains them, pay as you go

Video, image and audio generation API with Runway's Gen models plus Veo, Seedance and Wan behind one key

Generation API for images, video, audio and 3D: open models on its own GPUs plus partner models per call

EU-hosted AI gateway that checks prompts, responses and MCP tool calls against policy, with DLP and team budgets

Hosted evals, tracing and monitoring for LLM apps, from the team behind DeepEval

Adversarial testing, a runtime firewall and monitoring for AI agents and chatbots, with an open-source engine

Drop-in security proxy that blocks prompt injection and data leaks in LLM apps by changing one base URL

Open-source agent observability with traces, failure detection and evals

Managed Qdrant, Weaviate and Meilisearch alongside Postgres and 15 other engines, on flat monthly plans.

Hosted context containers that agents query over MCP, with hybrid retrieval built in

Open-source search engine in Rust with full-text, semantic, and hybrid search

Open-source typo-tolerant search engine with built-in vector and hybrid search

Serverless vector database on Cloudflare's global network

EU-resident OpenAI-compatible API that routes across European model providers, plus post-training on your data

Fine-tune and deploy LLMs on your own infrastructure with full data sovereignty

European cloud provider with AI inference, training, and deployment services

Open-source fine-tuning framework for 100+ LLMs with a web UI

PyTorch-native fine-tuning library from Meta, no longer actively maintained (development wound down in 2025)

Structured prompt builder that treats prompts like code, with versioning and a reusable building-block library

Sovereign AI gateway and LLMOps platform: model routing, prompt management, evals, and governance

AI gateway for routing to 1,600+ LLMs with observability, guardrails, and prompt management

Open-source CLI for testing, evaluating, and red-teaming LLM applications

Collaborate on prompts, evaluate, and optimize LLM-powered Apps with Klu.