LibreChat
LibreChat is a powerful open-source application that unifies all your AI conversations into a single, customizable interface. It is designed to work seamlessly with any AI provider, including OpenAI, Anthropic, AWS, and Azure, giving users full flexibility and control. LibreChat supports advanced agents capable of file handling, code interpretation, and API-driven actions. The platform includes a built-in code interpreter that can securely execute multiple programming languages with zero setup. Users can create and manage artifacts like React components, HTML, and Mermaid diagrams directly within chat. Multimodal capabilities allow users to analyze images and interact with files in conversations. Trusted by organizations worldwide, LibreChat delivers a sleek, extensible experience for modern AI workflows.
Learn more
Pi Agent
Pi is a minimal terminal coding harness built to adapt to developer workflows instead of forcing developers to adapt to it. It ships with powerful defaults, but stays intentionally small and aggressively extensible, letting users customize Pi with extensions, skills, prompt templates, themes, and shareable packages from npm or git. If a team needs a command, tool, provider, workflow, or UI tweak, they can ask Pi to build it, manipulate it in place, reload, and keep going. Pi supports interactive, print/JSON, RPC, and SDK modes, making it usable as a full terminal UI, a scriptable command, a JSON event stream, or an embeddable agent harness. It works with 15+ providers and hundreds of models, including Anthropic, OpenAI, Google, Azure, Bedrock, Mistral, Groq, Cerebras, xAI, Hugging Face, Kimi For Coding, MiniMax, OpenRouter, Ollama, and more, with mid-session model switching.
Learn more
PyGPT
PyGPT is an open source, personal desktop AI assistant for Linux, Windows, and Mac, written in Python. It works similarly to ChatGPT, but locally on a desktop computer, with chat, vision, agents, image and video generation, tools, voice control, and more. PyGPT supports multiple models, including OpenAI GPT-5, GPT-4, o1, o3, o4, Google Gemini, Anthropic Claude, xAI Grok, Perplexity Sonar, DeepSeek, Mistral AI, and models accessible through Ollama and LlamaIndex. It offers 12 modes of operation, including chat, chat with files, realtime + audio, research, completion, image and video generation, vision, assistants, experts, computer use, agents, and autonomous mode. Users can chat with their own files and data using integrated LlamaIndex support. PyGPT includes built-in vector database support, automated files and data embedding, full conversation context, short- and long-term memory, internet access through Google, Microsoft Bing, and DuckDuckGo, plus speech synthesis and recognition.
Learn more
Crade
Crade is a native AI screen assistant for Mac and Windows that sees what is on your screen and helps you get things done. It is designed for everyday situations such as spreadsheets, writing help, forms, code errors, documents, data analysis, translation, and research. Instead of requiring setup or plugins, Crade works in three simple steps: download the app, sign in with Google or email, and ask anything about the content already visible on the screen. The assistant understands code, charts, errors, articles, foreign-language documents, Excel formulas, and other on-screen information, then gives users a real answer based on the context of what they are working on. Crade can help interpret error messages, explain documents, assist with writing, analyze data, answer questions about articles, and support practical work without forcing users to copy and paste everything into a separate chat.
Learn more
