Andrew Ng introduces OpenCoworker, an open-source desktop AI agent harness
Andrew Ng and collaborators Rohit Prasad and Devika Verma have released OpenCoworker, a free open-source desktop agent built by extending the aisuite library to support agent harnesses. The tool allows users to connect frontier LLMs (OpenAI, Anthropic, Google) or local models via Ollama to desktop tasks including file access, messaging, and workflow automation, with privacy as a design priority. Ng frames this as a response to data-retention concerns with commercial desktop agents, citing Anthropic's Fable release as a recent example of policy opacity. The post also provides a concise overview of the current desktop agent landscape and the shift toward LLM-driven agentic loops.
Related guides (4)
Related events (8)
Anthropic launches Claude Mythos 5 and Claude Fable 5; Andrew Ng introduces OpenCoworker desktop agent
Anthropic released Claude Mythos 5 and Claude Fable 5, two variants of the same frontier model that set new state-of-the-art results across software engineering, knowledge work, cybersecurity, and agentic coding benchmarks. Claude Fable 5 is the general-availability version with safety classifiers that restrict responses on security, biology, chemistry, and cutting-edge AI topics, priced at $10/$50 per million input/output tokens; Mythos 5 is restricted to selected partners via Project Glasswing. Separately, Andrew Ng and collaborators released OpenCoworker, a free open-source desktop agent harness built on top of aisuite, designed to give users privacy-preserving agentic workflows with their own API keys or local models. The newsletter also contextualizes the broader shift toward LLM-driven agent harnesses as frontier models have become capable enough to reliably drive next-action decisions.
OpenAI launches Frontier agent orchestration platform to select enterprise customers
OpenAI announced Frontier, an enterprise platform for orchestrating, building, evaluating, and managing fleets of AI agents across corporate environments. The platform provides a unified UI for agent identity management, context sharing, performance evaluation, and memory across frameworks and models. Cisco, T-Mobile, HP, Intuit, and Uber are among early pilot and selected customers, with broader availability planned. The launch positions OpenAI in direct competition with Microsoft's Agent 365 in the emerging agent-management category.
Introducing Operator
OpenAI has announced Operator, a new AI agent product capable of taking actions on the web on behalf of users. The announcement comes from OpenAI's official blog, signaling a major step toward autonomous web-based task execution. Operator represents OpenAI's entry into the agentic AI product space, where models can browse, interact with, and complete tasks across websites without direct user intervention.
Introducing OpenAI Frontier
OpenAI has launched OpenAI Frontier, an enterprise platform designed for building, deploying, and managing AI agents. The platform provides shared context, onboarding workflows, permissions management, and governance tooling. This positions OpenAI more directly in the enterprise AI infrastructure and agent orchestration market.
Microsoft agent-framework: open-source library for building and orchestrating AI agents
Microsoft has published an open-source framework on GitHub for building, orchestrating, and deploying AI agents and multi-agent workflows, with support for both Python and .NET. The repository has accumulated 11,061 stars. It represents Microsoft's entry into the agent harness tooling space alongside existing frameworks like LangChain and AutoGen.
Rowboat: Open-Source AI Coworker with Memory
Rowboat is an open-source TypeScript project from Rowboat Labs implementing an AI coworker with persistent memory capabilities. The repository has accumulated 14,621 stars with 212 added today, indicating strong community traction. It appears to be a multi-agent or assistant framework targeting workplace productivity use cases with memory as a core differentiator.
OpenAI Announces Computer-Using Agent (CUA)
OpenAI has announced a Computer-Using Agent (CUA) capable of interacting with graphical user interfaces across web browsers and desktop applications. The system combines GPT-4o's vision capabilities with reinforcement learning to navigate and operate software as a human would. This represents OpenAI's entry into the agentic computer-control space, competing with similar efforts from Anthropic (Computer Use) and others. The announcement signals a significant step toward general-purpose AI agents that can autonomously complete multi-step tasks on computers.
Agent-S: Open Agentic Framework for Human-Like Computer Use
Agent-S is an open-source Python framework by Simular AI designed to enable AI agents to interact with computers in a human-like manner. The project has accumulated 11,388 GitHub stars with modest daily growth of 29 stars. It represents an entry in the growing space of computer-use agent frameworks targeting GUI and desktop automation tasks.