Hermes Agent is a mobile-first AI agent app from Nous Research for running local models and practical Android workflows on your phone.




MiroThinker is described as 'Open-source search agent model, built for tool-augmented reasoning and real-world information seeking, aiming to match the deep research experience of OpenAI Deep Research and Gemini Deep Research' and is a AI Chatbot in the ai tools & services category. There are more than 50 alternatives to MiroThinker for a variety of platforms, including Web-based, Mac, Windows, Linux and Android apps. The best MiroThinker alternative is ChatGPT, which is free. Other great apps like MiroThinker are Lumo by Proton, DeepSeek, Ollama and Mistral Vibe.
Hermes Agent is a mobile-first AI agent app from Nous Research for running local models and practical Android workflows on your phone.




LLM inference server with continuous batching & SSD caching for Apple Silicon — managed from the macOS menu bar.


Anna is a desktop AI agent that combines local execution power with a cloud server for memory and sync. Unlike purely local agents, Anna automatically manages your context and memory in the cloud, so there's no manual pruning or "memory book" chaos.



Teleton is an AI agent that controls its own Telegram account with native TON blockchain integration. Powered by its own agentic loop and 100+ built-in tools, it manages his own wallet, Gifts, DMs, channels, and group & more like any Telegram user.





Inferencer lets you run, host and deeply control the latest SOTA AI models (OSS, DeepSeek, Qwen, Kimi, GLM, MiniMax and more) from your own computer.




An honest AI assistant that grounds answers in real knowledge and live search — no hallucinations, no API key required. Works offline. Open source.



OpenClaw is powerful, but give it real credentials and you're exposed. Prompt injections steal API keys. Malicious skills grab passwords. IronClaw fixes this. Your credentials live in an encrypted vault inside a TEE — injected at the network boundary only for approved...




Built end-to-end by Tencent, Hy is a large language model engineered for excellence in content creation, reasoning, code, and conversation. From complex tasks in writing, research, and work, to everyday dialogue, knowledge, and creativity, Hy responds with precision, coherence...

Local-first governed agent kernel for durable, inspectable AI work. Every AI action goes through policy evaluation and approval workflows, produces structured receipts, and supports proof export and rollback recovery.