Built a personal agent: cowork runtime + code tools + outward identity + people memory
Summary
The author shared Zinley, a personal agent with multi-step work handoff, coding tools, outward identity, and people memory, designed to operate across devices and represent the user as AI.
Similar Articles
built another AI agent runtime. What would you do with it?
The author introduces Contenox, a personal AI agent runtime built to streamline LLM workflows, and asks the community for advice on how to monetize or share it.
Mythos Begets Fable, Cursor's Composer 2.5, Agents Building Agents
Andrew Ng discusses the rise of desktop AI agents and coding CLI tools, introduces the open-source OpenCoworker project, and examines agent harness designs where LLMs drive autonomous task execution.
How do you actually make a personal agent useful when half the value depends on memory?
A reflection on the challenge of evaluating personal AI agents whose value heavily relies on memory, illustrated by the author's experience with the Macaron agent.
We built a 54-agent ecosystem where some of the agents are persistent fictional characters — the hardest part has been controlling what they’re allowed to learn
The author describes building a 54-agent ecosystem for a project called Trading Hearts, focusing on challenges in controlling agent learning and maintaining persistent identities and rules.
I built a platform that lets you host your own personal AI agent — persistent, customizable, no infra to manage
A platform that allows users to host their own persistent and customizable personal AI agent without managing infrastructure.