AI Tools Directory

AI pair programmer built into VS Code, JetBrains IDEs, and Neovim; autocompletes code and answers questions in a chat panel.

An AI-native fork of VS Code with built-in multi-file editing, chat, and an agent mode for larger codebase changes.

Anthropic's agentic CLI and IDE-integrated coding assistant that can read, edit, and run code across a whole repository.

An AI-native code editor with an agentic "Cascade" mode for multi-step coding tasks, plus free autocomplete.

Codebase-aware AI assistant that uses Sourcegraph's code search to ground answers and edits in your actual repository.

AI code completion tool with an emphasis on private, on-prem, or VPC-hosted models for enterprise codebases.

AWS's AI coding assistant with autocomplete, chat, and automated code transformations like Java version upgrades.

Messages API access to the Claude model family, with tool use, extended thinking, and prompt caching.

API access to GPT models plus embeddings, image generation, and the Assistants/Responses APIs.

API access to Google's Gemini models via AI Studio or Vertex AI, with a generous free tier.

European AI lab offering open-weight and hosted Mistral models via API, including strong small, efficient models.

Enterprise-focused LLM API with a strong emphasis on retrieval, rerank, and embeddings for search and RAG use cases.

API access to Perplexity's search-augmented Sonar models, which return real-time web answers with citations.

Popular framework for chaining LLM calls, tools, and memory into applications and agents, in Python and JavaScript.

Data framework focused on connecting LLMs to your own documents and data sources for retrieval-augmented generation.

Framework for orchestrating role-based teams of autonomous AI agents that collaborate on a task.

Microsoft's framework for building multi-agent conversational AI applications with customizable agent roles.

Microsoft's lightweight SDK for integrating LLMs into C#, Python, and Java apps with plugins and planners.

TypeScript toolkit for building AI-powered UIs and agents with streaming and tool calling across React, Vue, and Svelte.

Fully managed vector database purpose-built for high-scale similarity search and RAG applications.

Open-source vector database with built-in hybrid search and native support for multi-modal embeddings.

Rust-based open-source vector database and search engine, available self-hosted or as a managed cloud.

Lightweight, developer-friendly open-source embedding database designed to be easy to run locally for prototyping.

The largest hub for open-source models, datasets, and spaces, plus hosted inference endpoints.

Run open-source machine learning models — image, audio, video, and LLMs — via a simple API, billed per second of compute.

Fast, cost-efficient inference and fine-tuning for open-source LLMs, with an OpenAI-compatible API.

Custom LPU hardware delivering extremely fast inference for open-source LLMs via API, often accessible on a free tier.

Run open-source LLMs locally on your own machine with a simple CLI and REST API — no cloud required.

Tracing, debugging, and evaluation platform for LLM applications, tightly integrated with LangChain.

Open-source LLM observability platform for tracing, prompt management, and evaluation.

ML experiment tracking platform with Weave for tracing and evaluating LLM applications.

Drop-in proxy for logging, monitoring, and caching LLM API requests with one line of code.

Web-based playground for testing prompts against Claude models, comparing outputs, and generating API code.

Web-based playground for experimenting with GPT models, system prompts, and function calling before writing code.

Platform for evaluating, testing, and comparing prompts and models side by side with scoring pipelines.