AI Tools Directory

General-purpose conversational AI assistant from OpenAI.

Anthropic’s conversational AI focused on reliability and safety.

Framework for building LLM-powered applications and workflows.

Unified analytics engine for large-scale data processing and ML workloads.

AI-native code editor for building software with LLMs.

Distributed event streaming platform for real-time data pipelines and integrations.

The most widely used no-code automation platform for connecting SaaS apps.

Unified data and AI platform built on Apache Spark, Delta Lake, and MLflow.

Graph-based framework for stateful, multi-agent LLM workflows.

High-performance C/C++ inference for LLaMA and GGUF models on CPU and GPU.

Local model runner with simple command and HTTP interface.

Transform data in your warehouse using version-controlled SQL models.

Data framework for connecting LLMs to private and structured data.

Industry-standard workflow orchestration for data and ML pipelines.

Open-source AI software engineering agent for autonomous coding and debugging.

Open-source vector extension for PostgreSQL — the default choice for SQL + embeddings.

High-throughput LLM inference engine with PagedAttention.

Production-ready platform for building and operating LLM apps, agents, and workflows.

In-process analytical database for fast local SQL on Parquet, CSV, and DataFrames.

Reference-free evaluation framework specifically for RAG pipelines.

Managed vector database for similarity search and RAG.

Agentic coding assistant from Anthropic that works in your terminal.

Open-source data integration platform with 300+ connectors for ELT pipelines.

Stream-first data processing engine for real-time analytics and event pipelines.

Open-source LLM evaluation framework with 50+ metrics and CI integration.

Elasticsearch with vector search, hybrid retrieval, and enterprise AI features.

Low-code visual builder for LLM apps, agents, and RAG pipelines.

Fair-code workflow automation platform with native AI and self-hosting.

Hugging Face production server for LLM inference with continuous batching on GPUs.

Visual IDE for building LangChain-powered agents, RAG flows, and LLM applications.

Self-hosted web interface for local and remote LLMs.

Managed cognitive search with vector, hybrid, and semantic ranking on Azure.

AI evaluation and observability platform for testing prompts, models, and agents in production.

Data orchestrator for building, testing, and monitoring ML and AI pipelines.

Open storage layer that brings ACID transactions to Apache Spark and lakehouses.

Official MCP server for GitHub — repos, issues, PRs, and code search for agents.

Open-source framework for validating and structuring LLM inputs and outputs.

Minimal agent library from Hugging Face — simple code agents with tool use.

Unified API gateway for 100+ LLM providers with routing and fallbacks.

Vector similarity search built into Redis — low-latency embeddings at scale.

Open-source LLM engineering platform for tracing, evals, and analytics.

AI-native IDE with Cascade agent for flow-state development.

ML and LLM observability platform for monitoring, evaluation, and drift detection.

Platform for deploying, serving, and scaling ML and LLM models in production.

Integration platform with 250+ tool connectors and managed MCP server hosting.

Managed ELT platform for automated data movement to warehouses and lakes.

Agent Development Kit for building multi-agent workflows on Google Cloud and Gemini.

AI security platform for prompt injection detection and LLM firewall protection.

Open framework for evaluating LLMs and model outputs with customizable benchmarks.

Open-source search and analytics engine with k-NN vector search support.

Blazingly fast DataFrame library for Python and Rust data engineering workloads.

Modern Python workflow orchestration with dynamic execution and observability.

Cloud platform to run ML models via API without managing infrastructure.

Durable execution platform for reliable long-running workflows and microservices.

Open-source PII detection and anonymization for text and images.

Vector search integrated into MongoDB Atlas alongside operational document data.

Open-source vector database with filtering and hybrid search.

Autonomous coding agent for VS Code with browser and terminal access.

Managed Ray platform for scaling Python, ML, and LLM workloads.

Open table format for huge analytic datasets with ACID transactions on object storage.

Visual automation platform for building complex multi-step workflows.

MCP integrations for Microsoft 365, Teams, and Azure services.

Open platform for the ML lifecycle — experiments, models, and deployment.

NVIDIA toolkit for programmable guardrails using Colang dialogue flows.

Official SDK for building agentic workflows with OpenAI models.

Cloud platform for running and fine-tuning open-source LLMs.

Open-source background jobs platform for long-running AI and TypeScript workflows.

Evaluation and tracking for LLM apps — feedback functions and experiment logging.

Open big data serving engine for vector search, ranking, and ML inference at scale.

MCP server exposing 8,000+ Zapier app integrations to AI agents.

Vector search on Neo4j graph database — combine embeddings with knowledge graphs.

Open-source vector database built for billion-scale similarity search.

Open-source AI code assistant for VS Code and JetBrains.

Browser-based AI app builder that generates full-stack projects.

Fast inference platform for open and proprietary LLMs.

Meta's open safety classifier model for input and output moderation.

Desktop app for running local LLMs with a chat interface.

Multi-agent framework that simulates a software company to build applications from requirements.

Serverless cloud platform for running ML models and data pipelines.

MCP server for reading and writing Notion pages, databases, and workspaces.

Registry and hosting platform for discovering and deploying MCP servers.

NVIDIA library for optimized LLM inference on TensorRT.

Open-source LLM gateway for routing, observability, and optimization in Rust.

Distributed SQL query engine for federated analytics across data lakes and warehouses.

Open-source developer platform for building workflows, scripts, and internal tools.

Open-source distributed inference engine for running LLMs, embeddings, and multimodal models.

Terminal pair programmer that edits code in your local git repo.

CLI tool for testing and evaluating LLM outputs with red-teaming support.

Open framework for building, deploying, and observing production AI agents.

Open-source embedding database for AI applications.

Cloudflare-managed MCP servers for Workers, R2, KV, and edge infrastructure.

Cloud platform for LLM evaluation, regression testing, and monitoring built on DeepEval.

Fast inference engine for Transformer models with quantization and batching.

AI app builder that creates production-ready full-stack applications.

Hybrid notebook and pipeline tool for building data workflows with AI assistance.

NVIDIA-acquired platform for efficient model deployment and media generation APIs.

AI security platform for scanning models, datasets, and ML supply chain risks.

GPU cloud for running AI workloads with serverless and pod options.

Microsoft SDK for integrating LLMs into applications with plugins and planners.

MCP server for Slack messaging, channels, and workspace interactions.

Production inference server for ML and LLM models at scale.

Framework for programming — not prompting — language models.

Serverless GPU cloud for running AI workloads, training, and inference.

MCP server directory and gateway for connecting AI clients to tools.

Enterprise AI security platform for model, application, and runtime threat defense.

Scalable model serving library built on the Ray distributed framework.

VS Code extension for autonomous coding agents with multiple modes.

Code-first agent framework from Microsoft Research for data analytics and automation.

Automated evaluation and scoring platform for LLM outputs and safety.

Developer-first integration platform for APIs, workflows, and event-driven automation.

Type-safe agent framework built on Pydantic for structured LLM outputs.

Fast structured generation and serving runtime for LLMs.

Open-source dev-first platform for building, managing, and running autonomous AI agents.

End-to-end NLP framework for building production RAG pipelines.

Unified framework for packaging and deploying ML models as APIs.

GenAI security platform protecting employees and apps from AI-specific threats.

Command-line AI coding agent powered by Google Gemini models.

Serverless ML inference platform with fast cold starts and custom runtimes.

Kubernetes-native serverless model serving platform.

Security API platform with AI guard services for prompt and response scanning.

Open-source observability for LLMs, embeddings, and retrieval.

100-line minimalist LLM framework for building agents and workflows in pure Python.

Open-source orchestration platform for data, infrastructure, and business workflows.

Open-source Zapier alternative with AI workflow building blocks.

TypeScript framework for building AI agents and workflows.

Lightweight framework for building multimodal AI agents.

Open-source framework for communicating agents and role-playing simulations.

Open-source terminal AI coding agent with TUI interface.

Google’s multimodal AI that works with text, images, and code.

Library for building "crews" of collaborating AI agents.

Framework for multi-agent conversations and tool-using AI systems.

Open-source vector database with hybrid search and modules.

AI pair programmer integrated into IDEs and GitHub.

Library for using pretrained transformers in Python and beyond.

Open model family from Meta for local and hosted LLMs.

Python framework for building data and ML web apps quickly.

Python library for quick ML app interfaces and demos.

Text-to-image model accessed primarily through Discord.

OpenAI’s image generation models accessible via API and ChatGPT.

Open-source text-to-image model family.