Every local AI, benchmarked.

Self-improving AI agent with persistent memory, built-in learning loop, and multi-platform messaging. By Nous Research.

Self-hosted workflow automation with native LLM, vector DB, and agent nodes - the local Zapier for AI pipelines.

The simplest way to run open-source LLMs locally - pull a model, get an OpenAI-compatible API.

The ChatGPT-style web interface for Ollama and any OpenAI-compatible local LLM.

Node-based UI for Stable Diffusion, Flux, video generation, and the entire open-source image/video AI ecosystem.

High-performance LLM inference in pure C/C++ with GPU acceleration - the engine behind most local AI tools.

High-throughput LLM serving engine with PagedAttention - the gold standard for production local inference.

Self-hosted AI workspace with chat, autonomous agents, deep research, and productivity tools - local-first, no telemetry.

All-in-one local RAG application - workspaces, document chat, agents, and embeddable widgets, fully self-hosted.

Open-source, offline-first ChatGPT alternative that runs 100% locally on your computer.

Open-weight 8B text-to-speech model with human-like emotion, one-shot voice cloning, and 110ms latency.

Autonomous AI agent that breaks down goals into sub-tasks, executes code, and iterates to completion.

Feature-rich web interface for Stable Diffusion with extensive extensions and fine-tuning controls.

Low-code visual framework for building multi-agent and RAG applications with any LLM provider.

Open-source LLM app development platform with visual orchestration, built-in RAG, and agent capabilities.

Framework for developing LLM-powered applications with composable chains, agents, and 500+ integrations.

Open-source RAG engine with deep document understanding for precise question answering.

Lightweight, cross-platform ChatGPT UI that deploys in one click and works with any LLM backend.

Modern, open-source ChatGPT/Claude UI with plugin ecosystem, multi-model support, and built-in TTS.

Free-to-use, locally running, privacy-aware chatbot that works on CPU without any GPU required.