Browse All AI Tools

Community platform for sharing AI model weights.

Weights.gg is a community platform for discovering, sharing, and running AI model weights including LoRA adapters, fine-tuned models, and custom checkpoints for image and text generation.

Run open-source LLMs locally on your machine.

Ollama enables running large language models locally with a simple CLI, supporting Llama, Mistral, Gemma, and many other open-source models without cloud dependencies.

Desktop app for running local LLMs with GUI.

LM Studio provides a user-friendly desktop application for downloading, running, and chatting with open-source LLMs locally, with a visual interface and local API server.

Open-source alternative to ChatGPT that runs locally.

Jan is an open-source AI platform that runs 100% offline on your computer, supporting local LLMs and remote APIs with a ChatGPT-like interface and extension system.

Open-source LLM observability and tracing platform.

Langfuse provides open-source observability for LLM applications with tracing, prompt management, evaluations, and analytics to debug and improve AI application quality.

High-performance vector search engine.

Qdrant is a vector similarity search engine optimized for performance, providing extended filtering support, payload management, and distributed deployment for production AI systems.

LLM prompt engineering and evaluation toolkit.

W&B Prompts provides tools for tracking, evaluating, and optimizing LLM prompts with experiment logging, chain tracing, and evaluation metrics for production AI applications.

Infrastructure for deploying ML models as APIs.

Baseten provides serverless GPU infrastructure for deploying machine learning models as production-ready APIs with auto-scaling, monitoring, and support for any ML framework.

GPU cloud for training and deploying AI models.

Lambda provides GPU cloud instances optimized for deep learning with pre-installed ML frameworks, offering A100 and H100 GPUs for training and inference workloads.

End-to-end AI platform with custom LLM agents.

Abacus AI provides an enterprise AI platform for building custom LLM agents, fine-tuning models, and deploying AI solutions with built-in RAG, evaluation, and monitoring.

ML experiment tracking and model management platform.

Comet ML provides experiment tracking, model registry, and production monitoring for ML teams, with LLM evaluation tools and integration with major ML frameworks.

AI model observability and debugging platform.

Tensorleap provides deep visibility into ML model behavior with population exploration, error analysis, and data-centric debugging tools for improving model quality.

Dedicated GPU clusters for AI model inference.

Together's Inference Cloud provides dedicated GPU clusters for organizations running AI at scale, with custom model deployment, guaranteed capacity, and performance optimization.

Memory layer for AI applications and agents.

Mem0 provides a persistent memory layer for AI applications, enabling agents and chatbots to remember user preferences, past interactions, and context across sessions.

AI-powered search for documentation sites.

Mintlify Search provides AI-powered search for documentation websites, allowing users to ask natural language questions and get accurate answers from documentation content.