Prompt, run, edit, and deploy full-stack web applications. -- bolt.new -- Help Center: https://support.bolt.new/ -- Community Support: https://discord.com/invite/stackblitz

A desktop MCP client designed as a tool unitary utility integration, accelerating AI adoption through the Model Context Protocol (MCP) and enabling cross-vendor LLM API orchestration.

Spring AI Playground is a self-hosted web UI for low-code AI tool development with live MCP server registration. It includes MCP server inspection, agentic chat, and integrated LLM and RAG workflows, enabling real-time experimentation and evolution of tool-enabled AI systems without redeployment.

AI-powered document generator. Generate essays, articles and complex documents using automations and AI.

DashHub.ai is an open-source AI platform designed to help teams of all sizes securely integrate and manage AI solutions (LLMs, GenAI). Its flexible, vendor-neutral architecture enables seamless and cost-effective AI adoption, fostering collaboration and innovation across teams.

An interactive AI chat system that runs entirely within your Macbook.

AIGoat - Open-source AI security playground for LLM red teaming. AI Goat provides hands-on labs covering the full OWASP LLM Top 10 with progressive defenses.

Prompt, run, edit, and deploy full-stack web applications with multi-LLM support! Extends bolt.new with OpenAI, Google, Together AI, OpenRouter, Ollama, LMStudio, Groq, DeepSeek, and Mistral integrations. Enhanced with chat file uploads, improved file editor UX, and intelligent error handling with auto-fix suggestions.

Multi-agent AI chat platform - Create AI personas and watch them converse in real-time with Ollama integration

Prompt, run, edit and download full-stack web applications

Python clone of RoboCode, trying to keep as similar features and API as possible.

An intelligent virtual companion that adapts, remembers, and evolves with you over time

An Agentic AI Research Playground for building AI Agents and Mult-Agent systems leveraging open-source models, libraries, and frameworks. Models used to run agents locally on Nvidia RTX A2000 GPU - 8GB VRAM include the quantized Ollama models: llama3.1:8b-instruct-q8_0, llama3.1:8b_q8_0, qwen2.5:7b-instruct-q8_0, and qwen2.5-coder:7b-instruct-q8_0.

Multi-LLM Chat Playground is an interactive tool designed to compare responses from multiple Large Language Models (LLMs) in real time. Built using LiteLLM, this app provides a unified interface to interact with different AI models, making it easy to experiment with various prompts and understand model behaviors.

playground that supports Gemini and Deepseek model

Unified agentic playground for AI benchmarking, workflow automation, and game environments using the Model Context Protocol (MCP). Includes servers for agentic flows, RPGs, chess, and Rubik’s Cube with seamless Claude integration.

Ottomate — your universal AI agent workbench. Give it a goal — it plans, codes, browses, and delivers autonomously. 190+ connectors, advanced multimedia creative suite, browser automation, visual pipelines, 200+ skills, cron task scheduler, and more

Experimental AI agent playground with LangChain, LangGraph, RAG pipelines, multi-agent orchestration & OpenAI GPT-4 Turbo. Build intelligent agents, retrieval-augmented generation systems & autonomous AI workflows.

PromptPunk 🚀🤖 — Your ultimate AI Playground. Craft, test, and manage LLM prompts with an intuitive interface. Supports OpenAI & Google models.

Autonomous Agent Playground. Multi-agent simulation where Vision-Language Models interact in a shared React Three Fiber 3D world.