A directory of 253 AI infrastructure tools: inference APIs, vector databases, agent frameworks, observability, fine-tuning, audio, and more. Every entry is reviewed and maintained by hand.
Data from infrabase.ai, where each tool has a detail page with pricing, compliance data, and alternatives. Licensed CC-BY-4.0.
Generated on 2026-08-21. Do not edit this file by hand, see Contributing.
- 🕵️♀️ Agents (38)
- 🔊 Audio (22)
- 🧠 Fine-tuning (21)
- 🏗️ Frameworks & Stacks (35)
- 🤖 Inference APIs (91)
- 📊 Observability & Analytics (45)
- ✍️ Prompt engineering (15)
- 🗄️ Vector databases (25)
- EU-headquartered providers
- Add a tool: submit it at infrabase.ai/submit, or open a PR against this README. PR contributions are folded into the source directory and this file is regenerated, so the entry ends up both here and on the site.
- Fix an error: open a PR or an issue. Corrections land in the source data first, then here.
AI agents are LLM applications designed to perform tasks independently or alongside other AIs and humans. They range from simple functions like web searches to complex ones like building web applications and conducting research. Here you find frameworks for building agents, platforms for deploying and hosting them, and tools for orchestrating agent workflows. Browse with filters on infrabase.ai
- AG2 - Community-driven multi-agent framework forked from AutoGen with backward-compatible API
- AgentOps - Build compliant AI agents with observability, evals, and replay analytics
- AgentsKit - Open-source TypeScript ecosystem for building, distributing and operating AI agents without provider lock-in
- AutoGen - Microsoft's framework for building multi-agent AI applications with event-driven messaging
- BenchGen - Simulated environments for benchmarking AI agents on multi-step tasks, with trajectory-level scoring
- Browserbase - Cloud browser infrastructure for AI agents with stealth mode, proxies, and session management
- Burr - Build stateful AI agents and applications as state machines, with a built-in tracing UI
- ChatBotKit - Platform for building AI agents and deploying them across web, Slack, Discord, WhatsApp, and Telegram
- Claude Agent SDK - Build production agents with the same tools and agent loop that power Claude Code
- Composio - Tool integration platform connecting AI agents to 1,000+ apps with managed auth and execution
- CrewAI - Framework for orchestrating role-playing, autonomous AI agents
- Dust - The operating system for AI agents
- E2B - Open-source cloud sandboxes for running AI-generated code securely in Firecracker microVMs
- ego lite - Chromium browser built for humans and AI agents to browse in parallel through isolated Spaces
- FalsifyLab - MCP server giving AI agents live financial and on-chain data tools
- Fixie - The fastest way to build conversational AI agents
- Google ADK - Open-source agent development kit from Google for building multi-agent systems
- Langdock - GDPR-compliant enterprise AI platform with multi-LLM access and agents
- LangGraph - Low-level framework for building stateful, long-running AI agents with graph-based orchestration
- Langroid - Multi-agent LLM framework using message-based task delegation inspired by the Actor model
- Letta - Framework for building stateful AI agents with persistent memory, formerly MemGPT
- LiveKit Agents - Open-source framework for building real-time voice and multimodal AI agents over WebRTC
- LLM Browser - Enable your AI agents to access any website without worrying about captchas, proxies and anti-bot challenges
- Mastra - TypeScript-first AI framework for building agents, RAG pipelines, and workflows
- Microsoft Agent Framework - Build agents and graph-based multi-agent workflows in .NET and Python
- n8n - AI workflow automation with 400+ integrations and native AI agents
- OpenAI Agents SDK - Official OpenAI framework for building production AI agents with tool use and guardrails
- Openspender - Payment router for AI agents: pay per request across LLM APIs and tools from a self-custodial wallet
- PrivateClawd - Managed cloud hosting for OpenClaw AI agents with dedicated VMs, browser automation, and messaging integrations
- Pydantic AI - Type-safe Python agent framework with Pydantic validation, tool calling, and dependency injection
- Rasa - Conversational AI platform for building enterprise AI agents
- Samtal - Swedish-hosted voice AI API with TTS, ASR, voice cloning, and conversational agents. ElevenLabs-compatible
- screenpipe - Local-first screen and audio capture that gives AI agents searchable memory of your work
- Semantic Kernel - Microsoft's SDK for building and orchestrating AI agents in .NET, Python, and Java
- Smolagents - Lightweight Python agent framework from Hugging Face where agents write Python code instead of JSON tool calls
- Stagehand - AI-powered browser automation framework with natural language actions, extraction, and observation
- Superagent - Prototype and deploy agents powered by large language models
- Tura - Open-source local coding agent that turns intent into verified repository changes
Generative AI audio models create realistic text-to-speech voices and music, offering a human touch to applications and enabling accessibility, as well as enriching user experiences with audio interactions. Browse with filters on infrabase.ai
- AssemblyAI - Speech-to-text APIs with audio intelligence, speaker diarization, and real-time streaming
- Cartesia - Real-time voice AI with ultra-low latency text-to-speech and voice cloning in 40+ languages
- Cekura - Testing and monitoring platform for AI voice and chat agents
- Deepgram - Build Voice AI into your apps
- Eleven Labs - Natural Text to Speech & AI Voice Generator
- Fish Audio - Open-source text-to-speech and voice cloning with low latency in 13+ languages
- Gladia - Fast speech-to-text API with real-time transcription and speaker diarization
- Hume AI - Empathic voice AI that detects and responds to human emotion in real-time
- KugelAudio - Real-time text-to-speech in 26 languages, trained and hosted in Europe
- LemonFox - Affordable speech-to-text and text-to-speech API with 100+ language support
- LiveKit Agents - Open-source framework for building real-time voice and multimodal AI agents over WebRTC
- LMNT - Low-latency text-to-speech API built for real-time conversational AI
- MusicGPT - AI audio API for generating songs, speech, and sound, with stem splitting, voice conversion, and mastering
- OpenAI - API access to GPT, o-series reasoning, DALL-E, and Whisper models
- PlayHT - AI voice generator acquired by Meta (July 2025) and shut down (December 2025). See alternatives for text-to-speech
- Resemble AI - Generative Voice AI built for Enterprise
- Rime AI - Text-to-speech API with 200+ voices, sub-200ms latency, and on-premise deployment
- Samtal - Swedish-hosted voice AI API with TTS, ASR, voice cloning, and conversational agents. ElevenLabs-compatible
- SpeechifyAI - Text-to-speech API with low-latency streaming, voice cloning, and 30+ locales
- Speechmatics - Enterprise speech-to-text API supporting 55+ languages with high accuracy
- Suno - Make a song with Suno
- VoxCPM - Tokenizer-free open-source text-to-speech with voice cloning across 30 languages
Fine-tuning AI models involves adjusting the parameters of a pre-trained model to perform better on a specific task or dataset. This process allows the model to adapt its learned knowledge to new, related problems, enhancing its accuracy and effectiveness for specialized applications. Browse with filters on infrabase.ai
- Amazon Bedrock - Managed API access to foundation models on AWS with built-in fine-tuning and agent tooling
- Anyscale - Fast, cost-efficient, serverless APIs for LLM Serving and Fine Tuning
- Axolotl - Open-source toolkit for fine-tuning LLMs with a single YAML config across the full training pipeline
- fal - Build the next generation of creativity with fal. Lightning fast inference
- FinetuneDB - Capture production data, evaluate outputs collaboratively, and fine-tune your LLM's performance
- Hugging Face - The open-source AI platform with 500K+ models, inference endpoints, and fine-tuning tools
- Klu - Collaborate on prompts, evaluate, and optimize LLM-powered Apps with Klu
- Lamini - Enterprise LLM fine-tuning platform with Memory Tuning for near-zero hallucination
- LangSmith - LangSmith is a unified DevOps platform for developing, collaborating, testing, deploying, and monitoring LLM applications
- LLaMA-Factory - Open-source fine-tuning framework for 100+ LLMs with a web UI
- Ludwig - Declarative deep learning framework for building and fine-tuning models with YAML configuration
- Modal - Run generative AI models, large-scale batch jobs, job queues, and much more
- Monster API - Access, finetune, deploy LLMs using our affordable and scalable APIs
- OpenAI - API access to GPT, o-series reasoning, DALL-E, and Whisper models
- OVHcloud AI - European cloud provider with AI inference, training, and deployment services
- Prem AI - Fine-tune and deploy LLMs on your own infrastructure with full data sovereignty
- Replicate - Run and fine-tune open-source models. Deploy custom models at scale. All with one line of code
- together.ai - The fastest cloud platform for building and running generative AI
- torchtune - PyTorch-native library for fine-tuning LLMs on consumer and enterprise GPUs
- TRL - Hugging Face library for training language models with RLHF, SFT, and DPO
- Unsloth - Fine-tune LLMs up to 30x faster with 90% less memory usage
The tools and frameworks providing the foundation for AI development offer practical solutions for constructing and deploying AI applications. They facilitate the use of collective research, knowledge, and experience in the field of AI solution development. Browse with filters on infrabase.ai
- AgentsKit - Open-source TypeScript ecosystem for building, distributing and operating AI agents without provider lock-in
- Anycloud - CLI and Python SDK for running AI jobs, services and VMs across your own AWS, Azure, GCP, Lambda and Vast accounts
- Atomic Chat - Open-source local AI chat app for running open-weight models on desktop and mobile
- Burr - Build stateful AI agents and applications as state machines, with a built-in tracing UI
- CC Switch - Open-source desktop manager and local router for AI coding tools
- Dify - Easily build and operate generative AI applications. Create Assistants API and GPTs based on any LLMs
- DSPy - Framework for programming, not prompting, language models with automatic prompt optimization
- Google ADK - Open-source agent development kit from Google for building multi-agent systems
- GPT4All - Desktop app and Python SDK for running open-source LLMs locally on any device
- Haystack - The Production-Ready Open Source AI Framework
- Instructor - Structured data extraction from LLMs using Pydantic models with automatic validation and retries
- Jan - Open-source desktop app for running LLMs locally with a clean GUI
- LangChain - LangChain gives developers a framework to construct LLM‑powered apps easily
- LangGraph - Low-level framework for building stateful, long-running AI agents with graph-based orchestration
- Langroid - Multi-agent LLM framework using message-based task delegation inspired by the Actor model
- LiteLLM - Unified OpenAI-compatible proxy for 100+ LLM providers with cost tracking and load balancing
- llama.cpp - LLM inference in C/C++ with broad hardware support and aggressive quantization
- LlamaIndex - LlamaIndex is a simple, flexible data framework for connecting custom data sources to large language models
- LLM Browser - Enable your AI agents to access any website without worrying about captchas, proxies and anti-bot challenges
- llmkit - One LLM client API for 20+ providers, in Go, TypeScript, Python and Rust
- LM Studio - Desktop app for discovering, downloading, and running local LLMs with a built-in API server
- LocalAI - Open-source, self-hosted OpenAI-compatible API for running models on your own hardware
- Mastra - TypeScript-first AI framework for building agents, RAG pipelines, and workflows
- Microsoft Agent Framework - Build agents and graph-based multi-agent workflows in .NET and Python
- Modular - We rebuilt the modern AI software stack, from the ground up, to boost any AI pipeline, on any hardware
- Ollama - Run large language models locally with a single command
- phidata - Build an AI App in minutes using pre-built templates
- Pydantic AI - Type-safe Python agent framework with Pydantic validation, tool calling, and dependency injection
- Semantic Kernel - Microsoft's SDK for building and orchestrating AI agents in .NET, Python, and Java
- Spring AI - Spring framework for building AI-powered Java applications with portable model and vector store abstractions
- Stagehand - AI-powered browser automation framework with natural language actions, extraction, and observation
- TanStack AI - Framework-agnostic TypeScript library for AI chat, streaming, tools, and structured outputs
- Tokenade - Local proxy that compacts what a coding agent sends to the model
- Vercel AI SDK - Open-source TypeScript toolkit for building AI applications with streaming, tool calling, and agents
- vLLM - High-throughput LLM inference engine with PagedAttention for efficient GPU memory usage
APIs and runtimes for AI models, especially LLMs, enable powerful text generation and processing in apps. They serve as the foundation for many AI solutions and allow easy integration, making advanced AI accessible for developers. Browse with filters on infrabase.ai
- AiQu - Swedish GPU infrastructure and LLM hosting platform with API-first deployment, no Kubernetes required
- Airon - Dedicated bare-metal GPU infrastructure for AI workloads, hosted in Nordic datacenters
- AKI.IO - European AI API for open-source models on EU infrastructure
- Akumi - EU-hosted OpenAI-compatible inference API with data residency, PII pseudonymization and per-request audit trails
- Amazon Bedrock - Managed API access to foundation models on AWS with built-in fine-tuning and agent tooling
- Anthropic Claude - Claude API for building AI applications with Opus, Sonnet, and Haiku models
- Anyscale - Fast, cost-efficient, serverless APIs for LLM Serving and Fine Tuning
- ARK Labs - Sovereign AI inference infrastructure for regulated EU environments, with heterogeneous GPU support
- Baseten - AI inference platform for deploying and serving ML models with autoscaling and optimized infrastructure
- Beam - Open-source serverless GPU cloud with sub-second cold starts and auto-scaling
- BentoML - BentoML is the platform for software engineers to build AI products
- Berget AI - EU-sovereign AI inference platform with OpenAI-compatible API
- Cerebras - Ultra-fast inference on custom wafer-scale hardware with OpenAI-compatible API
- Cerebrium - Serverless GPU infrastructure for deploying AI models with sub-5 second cold starts
- CheapestInference - Flat-rate unlimited inference on open-weight models, sold in daily 8-hour windows
- Cloudflare Workers AI - Run AI models at the edge on Cloudflare's global network with serverless inference
- CodingPlanX - Unified AI API gateway providing access to 600+ models from OpenAI, Anthropic, Google, DeepSeek, and more
- cohere - Cohere’s world-class LLMs help enterprises build powerful, secure applications that search, understand meaning and converse in text
- CoreWeave - GPU cloud infrastructure built for large-scale AI training and inference workloads
- Cortecs AI - European AI inference gateway with smart routing across EU providers
- deepinfra - Run the top AI models using a simple API, pay per use. Low cost, scalable and production ready infrastructure
- DeepSeek - Cost-effective inference API with OpenAI-compatible endpoints and open-weight models
- EUrouter - European AI gateway that routes to 100+ models with EU data residency
- evroc - European-sovereign cloud and inference APIs running open-source models on NVIDIA Blackwell GPUs in EU data centers
- fal - Build the next generation of creativity with fal. Lightning fast inference
- Fast Pivot - Unified OpenAI-compatible API for routing across 300+ models from 50+ providers
- FerryAPI - OpenAI-compatible API gateway with prepaid balance and usage billing
- fireworks.ai - The production AI platform built for developers
- General Compute - ASIC-powered inference cloud built for AI agents, OpenAI-compatible API
- Genesis Cloud - European GPU cloud, website offline and company in liquidation as of August 2026
- Geodd - Managed AI inference endpoints and GPU infrastructure with OpenAI-compatible API
- Google Gemini API - Google's API for Gemini models with text, image, video, and audio capabilities
- GreenPT - French inference API for open-weight models, hosted on Scaleway with embeddings, reranking and speech
- Groq - LPU-powered inference API for LLMs, speech, and vision models with usage-based pricing
- Hyperstack - On-demand cloud GPU platform for AI and ML workloads with per-minute billing
- Infer by Flow7 - Responses API gateway for coding agents, with a public model catalog and per-request spend ceilings
- Infercom - European sovereign AI inference with OpenAI-compatible APIs hosted in EU datacenters
- IONOS AI Model Hub - OpenAI-compatible API for open-weight LLMs and image models, hosted in IONOS EU data centers
- IonRouter - High-throughput inference API with OpenAI-compatible access to open-source models at half market rate
- Jina AI - Search APIs for embeddings, reranking, and web-to-markdown conversion
- KV Cache Store - Build, share and reuse precomputed KV-cache artifacts to skip redundant prefill
- Lambda - GPU cloud for AI training and inference with on-demand and cluster options
- Lepton - GPU compute marketplace from NVIDIA (formerly Lepton AI). Connects developers to 20+ cloud providers through one interface for training, dev pods, and inference
- LibertAI - Decentralized, privacy-first inference API running open-source LLMs in trusted execution environments
- LLMBase - EU-hosted inference API with 30+ open-source models, OpenAI-compatible, GDPR-compliant
- LLMWise - Multi-LLM API orchestration platform for comparing and blending AI models
- Lyceum - EU-hosted inference cloud for open-source models, OpenAI-compatible
- Melious AI - European inference API serving 60+ open-weight models on OpenAI- and Anthropic-compatible endpoints
- Meriarc Token - One OpenAI-compatible endpoint for 54 models, billed in prepaid credits
- Miapi - Web-grounded AI answers API with citations, OpenAI-compatible, pay-per-query pricing
- Mistral - Use models in a few clicks with our platform. Download our open models for deep access
- Modal - Run generative AI models, large-scale batch jobs, job queues, and much more
- Monster API - Access, finetune, deploy LLMs using our affordable and scalable APIs
- Nebius - Full-stack AI cloud with GPU infrastructure for training and inference
- novita.ai - APIs, Serverless and GPU Instance In One AI Cloud
- Nscale - European AI hyperscaler with serverless inference and GPU cloud
- OctoAI - OctoAI delivers production-grade GenAI solutions running on the most efficient compute, empowering builders to launch the next generation of AI applications
- OpenAI - API access to GPT, o-series reasoning, DALL-E, and Whisper models
- OpenRouter - Unified API for 400+ AI models across 60+ providers, OpenAI SDK-compatible, pay-as-you-go
- Openspender - Payment router for AI agents: pay per request across LLM APIs and tools from a self-custodial wallet
- Opper - EU-hosted AI gateway serving 300+ models through one OpenAI-compatible API
- OurToken - Unified OpenAI-compatible API gateway that routes requests across multiple LLM providers
- OVHcloud AI - European cloud provider with AI inference, training, and deployment services
- Packet.ai - On-demand NVIDIA GPU cloud with per-second billing, SSH, CLI, and API access
- Prem AI - Fine-tune and deploy LLMs on your own infrastructure with full data sovereignty
- Project Zero - CPU-only LLM inference engine in C with no runtime dependencies
- regolo - OpenAI-compatible inference API run on Italian infrastructure with zero data retention
- Replicate - Run and fine-tune open-source models. Deploy custom models at scale. All with one line of code
- Requesty - LLM gateway and router with one OpenAI-compatible API across 400+ models
- RunPod - The Cloud Built for AI
- Runware - Unified API for image, video, audio and 3D generation running on custom inference hardware
- SambaNova - Custom AI chip inference platform with purpose-built hardware for high-throughput LLM serving
- Scaleway - European serverless AI inference APIs, 100% hosted in Europe
- SGLang - High-performance open-source serving framework for LLMs and multimodal models
- SiliconFlow - OpenAI-compatible API serving 200+ open-source LLM and multimodal models
- SimpleLLM - OpenAI-compatible API for open-weight models, hosted only in EU data centres
- Solheim AI - Private EU-hosted LLM instances billed at a flat monthly fee rather than per token
- Synexa - Simple, fast, and stable. Deploy AI models with just one line of code
- Taiga Cloud - European GPU cloud for AI training and inference by Northern Data Group
- TensorX - EU-sovereign inference API with 42+ open-source models and zero data retention
- Theta EdgeCloud - Decentralized GPU cloud for AI inference, training, and containerized workloads
- together.ai - The fastest cloud platform for building and running generative AI
- TokensMind - Unified OpenAI-compatible API gateway to 100+ models across providers
- Tokenware - Unified OpenAI-compatible API to 200+ models with smart routing and failover
- Vast.ai - GPU marketplace for renting compute at market-driven prices with per-second billing
- Vercel AI Gateway - Unified API for hundreds of AI models, with built-in rate limiting and key management
- Verda - European GPU cloud with on-demand instances and serverless inference
- vLLM - High-throughput LLM inference engine with PagedAttention for efficient GPU memory usage
- vMetal - Bare metal GPU server provisioning for companies building AI compute clouds
- Voyage AI - Embedding and reranker models for RAG retrieval quality, from MongoDB
- WAYSCloud - Norwegian cloud platform with an LLM inference API running open-weight models in Norway
Specialized DevOps tools tailored for optimizing LLMs: from tuning parameters to enhance task-specific performance to analytics for monitoring and refining LLM applications. Browse with filters on infrabase.ai
- Agenta - Open-source prompt management, evaluation, and observability for LLM apps
- Arize AI - AI observability platform with tracing, evaluation, and monitoring for LLM and ML applications
- BenchGen - Simulated environments for benchmarking AI agents on multi-step tasks, with trajectory-level scoring
- Braintrust - Stop building AI in the dark
- Cekura - Testing and monitoring platform for AI voice and chat agents
- Cleanlab - Real-time detection and remediation of incorrect, unsafe, or non-compliant AI agent responses
- Cloudflare AI Gateway - LLM proxy with caching, logging, rate limiting, and cost analytics
- Comet Opik - Comet provides an end-to-end model evaluation platform for AI developers
- Datadog LLM Observability - LLM tracing, evaluation, and prompt monitoring built into the Datadog APM platform
- DeepEval - Open-source LLM evaluation framework with 50+ metrics for testing agents, RAG, and chatbots
- Dunetrace - Runtime reliability and failure detection for AI agents
- Evidently AI - Open-source ML and LLM evaluation with 100+ built-in metrics and CI/CD integration
- Future AGI - Open-source platform for testing, monitoring, and improving AI agents with tracing, evals, guardrails, and gateway
- Galileo - AI evaluation and observability platform with hallucination detection and real-time guardrails
- Giskard - Eliminate risks of biases, performance issues & security holes in AI models. In <10 lines of code
- Greptime - Gain comprehensive insights into the cost, performance, feedback, traces of your LLM applications
- Guardrails AI - Open-source framework for adding input and output validators around LLM calls
- HAIEC - Scans AI application code, runs adversarial tests against live endpoints, and generates signed compliance evidence
- Hamming AI - At-scale testing & production monitoring for AI voice agents
- Helicone - Open-source LLM observability platform for monitoring, debugging, and improving AI applications
- Honeyhive - AI Performance and Reliability, Delivered
- Humanloop - Develop AI features with confidence
- Klu - Collaborate on prompts, evaluate, and optimize LLM-powered Apps with Klu
- Lakera - API-first runtime security for LLM apps and agents, prompt injection and data-leak defense
- Langfuse - Traces, evals, prompt management and metrics to debug and improve your LLM application
- LangSmith - LangSmith is a unified DevOps platform for developing, collaborating, testing, deploying, and monitoring LLM applications
- LangWatch - LLM observability platform with quality monitoring, guardrails, and evaluation workflows
- LLM Guard - Open-source input and output scanners for securing LLM apps against prompt injection, PII, and toxicity
- Log10 - LLMOps platform for logging, debugging, and improving LLM-powered applications
- lunary - The platform to monitor, manage and improve your LLM apps
- NeMo Guardrails - NVIDIA toolkit for adding programmable guardrails to LLM conversational apps
- Patronus AI - Detect LLM mistakes at scale and use generative AI with confidence
- Portkey - AI gateway for routing to 1,600+ LLMs with observability, guardrails, and prompt management
- Presidio - Microsoft open-source SDK for detecting and anonymizing PII in text and images
- PromptLayer - Visually manage prompts. Evaluate models. Log LLM requests. Search usage history. Collaborate as a team
- RAGAS - Open-source evaluation and testing framework for LLM and RAG applications
- Redcells - Automated adversarial testing for AI systems you own, with replayable evidence
- Rhesis AI - Open-source testing platform for LLM and agentic applications. Test generation, adversarial probing, and regression tracking
- Sentrial - Production monitoring for AI agents with automated failure detection and diagnosis
- The Context Company - Agent observability that pairs traces with conversation analytics to catch silent failures in production
- Traceloop - Open-source LLM observability built on OpenTelemetry, with automatic instrumentation for major providers and frameworks
- TrueFoundry - AI gateway for routing across 250+ LLMs with fallbacks, rate limiting, guardrails, and RBAC
- TruLens - Systematically evaluate and track LLM apps and agents with feedback functions and tracing
- Vercel AI Gateway - Unified API for hundreds of AI models, with built-in rate limiting and key management
- Weights & Biases - ML experiment tracking, LLM observability, and evaluation platform for AI teams
Prompt engineering is the skill of designing inputs that steer large language models (LLMs) toward generating targeted behaviors and outputs. It is a foundation skill for developers creating AI applications using many of the current AI systems. These services enhance prompt development, maintenance and generation. Browse with filters on infrabase.ai
- Dify - Easily build and operate generative AI applications. Create Assistants API and GPTs based on any LLMs
- FinetuneDB - Capture production data, evaluate outputs collaboratively, and fine-tune your LLM's performance
- Fixie - The fastest way to build conversational AI agents
- Giskard - Eliminate risks of biases, performance issues & security holes in AI models. In <10 lines of code
- Klu - Collaborate on prompts, evaluate, and optimize LLM-powered Apps with Klu
- Knit - Professional prompt editors with gpt-4-turbo/vision, gemini-pro and more models, function call simulation and more!
- Orq.ai - LLMOps platform for prompt management, evaluation, and AI governance
- Portkey - AI gateway for routing to 1,600+ LLMs with observability, guardrails, and prompt management
- Prompt Mixer - Open source app for prompt testing
- Prompt Optimizer - Prompt engineering IDE with quality scoring, automated tuning, and side-by-side model comparison
- PromptFoo - Open-source CLI for testing, evaluating, and red-teaming LLM applications
- PromptLayer - Visually manage prompts. Evaluate models. Log LLM requests. Search usage history. Collaborate as a team
- PromptLeo - Advanced prompt engineering platform for prompt engineers to create, test, and change prompts
- Prompty - Structured prompt builder that treats prompts like code, with versioning and a reusable building-block library
- Superagent - Prototype and deploy agents powered by large language models
A vector database stores data as mathematical vectors, enabling efficient similarity searches for AI-driven applications like search engines, recommendation systems, and Retrieval-Augmented Generation (RAG). This makes it easier for developers to integrate advanced AI functionalities into their applications with ability to search and understand relationships within data. Browse with filters on infrabase.ai
- Azure AI Search - Microsoft managed search service with vector, hybrid, and agentic retrieval for RAG
- chroma - The AI-native open-source embedding database
- Cloudflare Vectorize - Serverless vector database on Cloudflare's global network
- Elasticsearch - Distributed full-text search and analytics engine with built-in vector and hybrid search
- Epsilla - A one-stop platform for building production ready LLM applications connected with your proprietary data
- FAISS - Meta's open-source library for efficient similarity search and dense vector clustering
- LanceDB - The hyper scalable, easy to use, embedded vector database
- Marqo - Use your data to increase relevance with vector search
- Meilisearch - Open-source search engine in Rust with full-text, semantic, and hybrid search
- Milvus - Vector database built for scalable similarity search
- Myscale - The SQL Vector Database for Scalable AI
- OpenSearch - Open-source search and analytics suite with full-text, vector, and hybrid search
- pgvecto.rs - pgvecto.rs is a Postgres extension that provides vector similarity search functions
- pgvector - Open-source PostgreSQL extension for vector similarity search alongside relational data
- Pinecone - Build remarkable GenAI applications fast, with lower cost, better performance, and greater ease of use at any scale
- Qdrant - Powering the next generation of AI applications with advanced and high-performant vector similarity search technology
- Redis - In-memory vector database for low-latency similarity search across AI applications
- Supabase Vector - Open-source Postgres vector database and AI toolkit built on pgvector
- TopK - AI-native search engine combining vector, keyword, and faceted search
- Turbopuffer - Serverless vector and full-text search engine built on object storage for cost-efficient scale
- Typesense - Open-source typo-tolerant search engine with built-in vector and hybrid search
- Vespa - Open-source search and serving engine combining vector search, keyword search, and ML ranking at scale
- Weaviate - Weaviate is an open source, AI-native vector database that helps developers create intuitive and reliable AI-powered applications
- Wire - Hosted context containers that agents query over MCP, with hybrid retrieval built in
- Zilliz - A Widely-Adopted Vector Database
Tools headquartered in the EU, with GDPR compliance as stated by the vendor and verified against their site. See also the maintained EU index page.
| Tool | HQ | GDPR | What it does |
|---|---|---|---|
| Cortecs AI | AT | yes | hosted-inference-api |
| Agenta | DE | llm-observability | |
| AKI.IO | DE | gpu-compute | |
| Genesis Cloud | DE | yes | gpu-compute |
| Haystack | DE | rag-framework | |
| IONOS AI Model Hub | DE | yes | hosted-inference-api |
| Jina AI | DE | embedding-api | |
| KugelAudio | DE | yes | text-to-speech |
| Langdock | DE | yes | agent-platform |
| Langfuse | DE | yes | llm-observability |
| LemonFox | DE | yes | text-to-speech |
| Lyceum | DE | yes | hosted-inference-api |
| Melious AI | DE | yes | hosted-inference-api |
| n8n | DE | yes | workflow-builder |
| PromptLeo | DE | yes | prompt-management |
| Qdrant | DE | yes | vector-database |
| Rasa | DE | agent-framework | |
| Rhesis AI | DE | llm-evaluation | |
| SimpleLLM | DE | yes | hosted-inference-api |
| Taiga Cloud | DE | yes | gpu-compute |
| Atomic Chat | EE | local-inference-runtime | |
| llmkit | FI | llm-orchestration-framework | |
| Verda | FI | yes | gpu-compute |
| Dust | FR | yes | agent-platform |
| Giskard | FR | llm-evaluation | |
| Gladia | FR | yes | speech-to-text |
| LibertAI | FR | hosted-inference-api | |
| Meilisearch | FR | ai-search | |
| Mistral | FR | yes | hosted-inference-api |
| OVHcloud AI | FR | yes | gpu-compute |
| Scaleway | FR | yes | hosted-inference-api |
| Tokenade | FR | llm-gateway | |
| TensorX | IE | yes | hosted-inference-api |
| regolo | IT | yes | hosted-inference-api |
| Solheim AI | IT | yes | hosted-inference-api |
| Infercom | LU | yes | hosted-inference-api |
| Akumi | NL | yes | hosted-inference-api |
| EUrouter | NL | yes | hosted-inference-api |
| GreenPT | NL | yes | hosted-inference-api |
| LangWatch | NL | yes | llm-observability |
| Nebius | NL | yes | hosted-inference-api |
| Orq.ai | NL | yes | prompt-management |
| Weaviate | NL | yes | vector-database |
| AiQu | SE | yes | gpu-compute |
| Airon | SE | yes | gpu-compute |
| Berget AI | SE | yes | hosted-inference-api |
| evroc | SE | yes | gpu-compute |
| Opper | SE | yes | hosted-inference-api |
| Samtal | SE | yes | text-to-speech |
Maintained as part of infrabase.ai. Data is licensed CC-BY-4.0: reuse freely with attribution to infrabase.ai. Source for this export: https://github.com/arvida/ai-infrastructure-directory.