Autonomous AI agents that plan and execute multi-step tasks without continuous input.

Meta's open-weight instruction-following model. Available in 8B and 70B parameter sizes.

Composable building blocks for LLM-powered agents with tool use and memory.

OpenAI's multilingual speech recognition model. Accurate transcription across 99 languages.

Run open-source LLMs locally on your machine. Llama 3, Mistral, Phi3, and more with one command.

Data framework for building LLM applications with context augmentation. RAG, queries, and orchestration.

AI-first code editor built on VS Code with diff-based code generation and natural language refactoring.

A powerful and modular UI for Stable Diffusion with a node-based workflow engine.

Microsoft's multi-agent conversation framework for building LLM applications.

State-of-the-art open-source image generation model. 1024x1024 default resolution with fine control.

Suno's open-source text-to-audio model. Generates highly realistic speech, music, and sound effects.

Multi-agent framework for building role-based autonomous teams that collaborate on goals.

Browser-based autonomous agent powered by LangChain + browser automation.

Facebook AI Similarity Search. Efficient dense vector clustering and similarity search.

High-performance vector database with filtering and hybrid search. Self-hostable or cloud.

A 7B parameter model with strong performance on math and coding benchmarks.

Conditionally controlled neural network for conditioning Stable Diffusion models with spatial layouts.

Open-source image generation model from Black Forest Labs with exceptional prompt following.

The AI-native open-source embedding database. Fast vector similarity search with built-in query capabilities.

Open-source text-to-speech with high-quality neural voices and voice cloning support.

Mixture-of-experts model. Only 12B active parameters per token, with 46B total.

Unified interface for 100+ LLMs. Call OpenAI, Anthropic, Azure, Gemini, and local models with one API.

Open-source NLP framework for building production-ready pipelines with LLMs, vector DBs, and custom components.

Open-source vector similarity search for PostgreSQL. Store and query vectors alongside your relational data.

AI code completion tool that learns your codebase. Supports 80+ languages and all major IDEs.

A simple, lightweight agent framework built around a task-driven execution loop.

Alibaba's multilingual LLM family with strong code and math capabilities.

The unified SDK for building AI-powered apps with React, Svelte, and Node. Streams, retries, and UI primitives.

Free AI-powered code acceleration tool with fast completions and search across your codebase.

Open-source vector database with built-in modules for embeddings, RAG, and hybrid search.

Open-source AI code assistant for VS Code and JetBrains. Powered by Claude, GPT-4, and local models.

A platform for running open-source AI models via API. Run Stable Diffusion, FLUX, CogVideoX, and more.

Memory-augmented agents with long-context memory hierarchies for extended conversations.

Reliable event-driven serverless functions. Use AI in production without managing infrastructure.

Hosted inference API for the best open-source models. Finetuning and function calling support.

A lightweight framework for building and deploying autonomous AI agents.

Meta's open-source text-to-speech model. Generate natural voice from text prompts.

Enterprise AI platform with embedding models, rerank, and command models via API.

Access Claude 3 models via Anthropic's API. Supports tool use, vision, and 200k context.

Anthropic's most intelligent model. Excellent for complex reasoning and long-form content.

AI pair programmer integrated into GitHub, VS Code, JetBrains, and Neovim. Real-time code completions.

AI voice synthesis platform with ultra-realistic voices and granular control over tone and emotion.

Google's flagship model with a 1M token context window. Excels at long-document reasoning.

Fast inference API for open-source models. Sub-second latency for Llama 3, Mixtral, and Gemma.

AWS's AI code companion with security scanning and custom model support.

OpenAI's latest image generation model with near-perfect prompt adherence and high fidelity.

AI APIs for real-time transcription, speaker diarization, content moderation, and summarization.

OpenAI's most capable language model. Multimodal, 128k context window.