Release notes, guides, and stories from building AgentOne.

October 26, 2026
Ollama runs AI models on your computer, but on its own it can only chat. Here's how to turn it into a local AI agent that can search the web, work with your files, and run tasks, with no code and no API bills.

October 14, 2026
AgentOne 1.1.2 lets long chats keep going with Compaction, adds Chat History tools, rebuilds Settings with search, and adds 60 new providers.

October 12, 2026
Meta Muse Wonder benchmarks, $4/$20 API pricing, how it compares to Claude and GPT-6, Wonder vs Wonder Full, and how to start using it today.

October 10, 2026
AgentOne 1.1 introduces Scheduled Agents: tell AgentOne what you want done regularly and it will run the task on your schedule, in its own chat, right on your device.

August 17, 2026
AgentOne, the free AI agent and deep-researcher, is now fully open source under the AGPL-3.0 license. Here's why we did it, what you get, and how to get involved.

July 16, 2026
Moonshot AI's Kimi K3 is a 2.8-trillion-parameter open-source model with a 1M-token context window, native vision, and benchmark performance rivaling Claude Fable 5 and GPT-5.6 Sol at roughly half the price.

June 15, 2026
A hands-on comparison of the best free AI agents available in 2026, from no-code desktop apps to open-source frameworks. Honest pros, cons, and who each one is actually for.

June 1, 2026
AgentOne has officially transitioned out of beta with the 1.0.0 release: a more stable, polished, and production-ready AI workspace.

May 29, 2026
A comparison of OpenAI, ElevenLabs, LMNT, and Hume text-to-speech services, covering voice quality, latency, pricing, developer experience, and best use cases.

May 4, 2026
Today, we're open-sourcing the AI Model Directory, the most comprehensive list of AI models and their metadata to date