gpt-oss playground
Demo platform for open-weight GPT models with adjustable reasoning
The gpt-oss playground is a demo platform designed for developers to explore OpenAI’s open-weight models, specifically gpt-oss-120b and gpt-oss-20b. It allows users to interact with these models and observe their reasoning capabilities.
Vecy: On-device AI & LLM APP for RAG
Private AI chat with local files on Android
Vecy is an Android AI app that allows users to chat with fully-private LLMs and local files (documents, photos). It automatically processes and indexes local files on the phone, and users can also directly upload files. Vecy offers RAG tools for processing local files to enhance LLM responses. Users can select from a range of small LLMs (from 0.5B to 3.5B parameters) and engage in conversations with documents stored locally. The app automatically processes files (PDFs, DOCX documents, images, etc.) within the Documents, Download, and DCIM directories to generate embedding vectors, which are stored locally on the device. These embedding vectors are crucial for RAG (retrieval-augmented generation) capabilities, enhancing the LLM's ability to provide more accurate and relevant responses when queries are related to the local files.
ReActGPT
Enhance LLM accuracy with thought-action-observation training
ReActGPT revolutionizes AI interactions using the ReAct paradigm. It trains AI with thought-action-observation sequences for accurate and dynamic results, minimizing AI errors and optimizing outcomes. It aims to improve the accuracy of ChatGPT search results and reduce hallucinations and error propagation in large language models (LLMs).
GPT Duel
Watch GPT models argue with each other
GPT Duel is a website that allows users to watch GPT models argue with each other. Users can vote to start the next round and participate in the debates.
Airbyte
The Context Layer for AI Agents
Airbyte is an open-source data integration platform and ELT tool designed to seamlessly integrate, transform, and load data. It offers reliable database and API replication at any scale, AI/LLM ready data, and the ability to embed connectors easily. Airbyte provides solutions for AI & LLMs, database replication, analytics, and embedding connectors. It supports various deployment models, including self-hosted, cloud, and hybrid, ensuring data security and governance.
MCP Defender
AI Firewall for AI apps
MCP Defender is a desktop application designed to automatically secure AI apps like Cursor, Claude, Visual Studio Code, and Windsurf from various attacks. It functions as an AI Firewall, monitoring and protecting Model Context Protocol (MCP) communications by intercepting tool calls and responses. It verifies these against security signatures and alerts the user if it detects any malicious activity, allowing them to block or allow the action. It provides intelligent LLM-powered threat detection and acts as a secure proxy, analyzing communications in real-time.
Forking Path
Visualize and navigate AI conversations with branching timelines
Forking Path transforms complex AI conversations into clear, interactive timelines. It allows users to navigate, branch, and merge dialogue paths with unprecedented clarity. It offers universal support for all LLM platforms and provides powerful features for visualizing, managing, and understanding AI conversations at scale.
Pongo
Moondream is an open-source visual language model (VLM) designed to understand images using simple text prompts. It is lightweight, fast, and capable, requiring only 1GB of space. Moondream can be used for various applications, including image captioning, object detection, visual question answering, and more. It's designed for developers who want a versatile and easy-to-use visual AI solution.
Afford AI
Real-time LLM usage tracking and cost analytics
Afford AI is an analytics app designed to track LLM usage, providing real-time insights into token consumption, costs, and key usage patterns. It helps founders monitor LLM interactions in real-time, get precise cost and usage details, and offers pay-as-you-go with credit-based pricing.
Nexal AI - All In One AI Platform
Nexal AI is an all-in-one AI platform that integrates leading large language models (LLMs) such as ChatGPT, Gemini, Llama, Mistral AI, Leonardo AI, and Claude. It empowers users to harness the power of advanced natural language processing, automation, and data analysis.
MyDeviceAI
Private, offline AI on your iPhone
MyDeviceAI is an iOS application developed by Naved Merchant that brings the power of AI directly to your iPhone. It allows users to run a powerful AI model locally on their device without needing an internet connection. This ensures fast, private, and optimized performance, specifically designed for iPhone 13 Pro, iPhone 14, and later models. The app focuses on processing data locally, ensuring user privacy and enabling AI-powered features in areas without Wi-Fi or mobile data.
OpenPeer AI Pre-Launch
Decentralized AI platform using LonScript, Mojo, and LLM Standard
OpenPeer AI is a decentralized AI platform built using LonScript, the Decentralized-Internet SDK, Mojo, and the LLM Standard. It leverages BOINC as its foundation and aims to provide a scalable platform for AI, ensuring accuracy and predictability. It focuses on utility-oriented AI solutions, supporting diffusion models, generative art, AI safety, horizontal scaling, and Robotic Process Automations (RPAs).
Helicone AI
Build Reliable AI Apps
Helicone is an open-source LLM observability platform designed for monitoring, debugging, and improving AI applications. It offers features like cost tracking, agent tracing, and prompt management through a 1-line integration. It helps developers ship AI apps with confidence by providing an all-in-one platform to monitor, debug, and improve production-ready LLM applications.
EmilyGPT
EmilyGPT is a website featuring Emily, presented as the face of GPT. The site includes sections for Home, About, Privacy, and Contact. It also offers a newsletter signup to stay updated.
tinynudge AI
Scheduled AI prompts delivered via email.
tinynudge.ai allows users to input a prompt and a frequency, and the platform will feed the prompt to a Large Language Model (LLM) and email the response at the user's desired frequency.
PromptShow
PromptShow is a platform designed to easily create and share visually appealing images of LLM (Large Language Model) prompts. It allows users to input their prompts and generate shareable images, enhancing the presentation and accessibility of these prompts.
Entry Point AI
No-code platform to create custom AI models for your business or projects
Entry Point is a no-code platform that helps you create custom AI models for your business or projects. Manage training data, generate synthetic examples, estimate fine-tuning costs, and optimize models — all in one place! Train, manage, and evaluate custom large language models (LLMs) fast and efficiently on Entry Point AI with no code required.
LM-Kit.NET
Complete Local AI Runtime for .NET
LM-Kit.NET is a high-level inference SDK for LLMs, offering advanced Generative AI capabilities for Cand VB.NET. It provides specialized AI functionalities, including text completion, NLP, content retrieval, text enhancement, translation, and more. LM-Kit.NET delivers Multimodal Generative AI systems for .NET, enabling AI Agent customization, new Agent creation, and Multi-Agent orchestration. Its data processing, text analysis, translation, text generation, and model optimization tools integrate seamlessly into Cand VB.NET, empowering developers with cutting-edge AI solutions.
Terracotta
Supercharge your LLM experimentation
Terracotta is a platform designed to simplify and accelerate the process of experimenting with Large Language Models (LLMs). It streamlines the training and evaluation of LLMs by providing a unified interface for managing models, data, and evaluations. Terracotta aims to supercharge the LLM iteration process, making it more intuitive and efficient.
nat.dev
Open-source playground for testing and comparing LLMs
OpenPlayground is an open-source playground designed for testing Large Language Models (LLMs). It provides a platform to experiment with and evaluate different GPT models.
LLMule
Decentralized AI freedom with local and peer-to-peer model execution
LLMule is a decentralized AI ecosystem that allows users to run models locally or connect to a P2P network. It emphasizes data privacy, community-shared models, and the ability to share compute power. LLMule aims to provide AI freedom outside of big tech control by democratizing access to artificial intelligence through distributed computing.
LLM Clash
Test your LLM against others in live debate
LLM Clash is a playground for AI enthusiasts, hobbyists, and researchers to test their LLM's against other LLM's in debate. Fine-tuned or not, local LLM or cloud hosted, you can still partake. Sometimes a good prompt is all you need to win a debate!
Supervised app
No-code AI development platform for supervised LLMs
Supervised AI is a no-code AI development platform that allows users to build supervised LLMs (Large Language Models) using OpenAI's GPT engine and their own data. It caters to enterprises looking to integrate AI into their business, as well as individuals wanting to build and sell their own AI apps. The platform provides tools to fine-tune AI models, deploy them on the cloud, and monetize them.
Snack AI
Ask multiple LLMs at once
Snack AI is a platform designed to immerse users in the world of cutting-edge AI. It allows users to explore the latest innovations and unlock their potential by providing a tool to ask multiple Large Language Models (LLMs) at once.