AI Chatbot

Vicuna-13B is an open-source conversational language model from LMSYS, fine-tuned from LLaMA on user-shared conversations and released with training code, model weights, and a research demo for non-commercial use.

Kolibri is Aleph Alpha's Apache-2.0 open-weight German-English mixture-of-experts reasoning model with 78B total and 3.46B active parameters, up to 1M-token context, tool calling, and self-hosted vLLM deployment.

Spark-X2.5 is an Apache-2.0 open model series with compact 4B and 1.7B variants, native 1M-token context, coding and agent capabilities, and local deployment across Ollama, LM Studio, vLLM, SGLang, llama.cpp, and MLX.

Meta personal AI agent that takes action under user direction, using a persistent secure virtual machine and browser to handle web tasks, connected apps, files, and approved consequential actions.

Model-agnostic AI coworker for Slack and Microsoft Teams that routes work to 80+ models, runs scoped cloud agents, maintains a team wiki, and asks for approval before consequential actions.

Hermes Bot Mode is an open-source desktop plugin for Hermes Desktop (Nous Research) that turns agent profiles into a roster of named bots, each with its own chat, avatar, personality, routines, and bot-to-bot messaging. Install it in minutes and orchestrate multi-agent workflows without patching the core app.

Xiaomi cloud-based AI agent platform for one-click OpenClaw deployment. Powered by the MiMo-V2.5-Pro flagship model with Kingsoft WPS Office integration for document generation, editing, and multi-step task automation.

AI tutoring assistant by Khan Academy — personalized learning guidance, homework help, and teaching assistance powered by GPT-4.

Personal AI super intelligence that runs privately and locally — simple, powerful, and designed to keep your data under your control.

Multi-modal AI platform by Step Intelligence with real-time voice interaction, paralinguistic awareness, image generation, and lightning-fast speech recognition.

Advanced AI reasoning and coding assistant with world-class performance on complex tasks, math, and code generation at competitive pricing.

xAI conversational AI assistant with real-time information access, image generation (Grok Imagine), video creation, and voice TTS in 20+ languages.

Tencent OS-level AI assistant available on Windows, Mac, and Android. Handles document analysis, image recognition, system maintenance, and can orchestrate different AI models.

Chinese AI platform offering 600+ voice models with Speech 2.8 Turbo, multimodal chat, and video generation capabilities. Industry-leading text-to-speech quality.

Open-source, local-first personal AI assistant with cross-session memory. Integrates with WhatsApp, Telegram, and other messaging platforms for unified AI access.

Unified AI model routing platform where developers can access GPT Image 2 and other LLMs through a single API, simplifying multi-model integration.

Alibaba Cloud large-model assistant for chat, writing, coding, document understanding, and multimodal tasks.

ByteDance AI assistant for chat, writing, image generation, search, learning, and productivity tasks.

Moonshot AI assistant popular in China for long-text reading, web search, document analysis, and writing.

AI answer engine that combines web search, cited answers, research workflows, and file analysis.

Google AI assistant for chat, research, writing, coding, and multimodal work across Google products.

Anthropic AI assistant for long-context reasoning, writing, coding, and document analysis.

OpenAI conversational AI assistant for writing, coding, analysis, research, and multimodal tasks.