google/ax
- Source
- GitHub
- First trending
- Category
- Agents
- GitHub stars
- 12,432
- Main language
- Go
This page introduces an external open-source repository. It is not an HDATF product.
What it does
AX is a declarative orchestrator for agent tasks with isolated sandboxes, configured workspaces and network restrictions. Its core concepts and specifications are still being refined and may change before a stable release.
How it helps ATF
Harness can reference its separation of tasks and workspaces when considering isolated AI execution and preconfigured repositories and tools. Its evolving specifications would need review before adoption.
License
Apache-2.0 Permissive, with a patent grant. Commercial use is allowed; keep the notices and state your changes.
More in this category
- Nasiko-Labs/nasiko
A control plane for deploying, routing, securing, and observing A2A-speaking agents. It proxies agent traffic and applies authentication, rate limits, access controls, and tracing. - shhivv/third-hand
A macOS menu bar assistant that reads accessible controls, types, clicks, and checks results. Jev chooses actions from text descriptions, while Apple Vision handles local text recognition when needed. - BuilderIO/agent-native
A TypeScript framework for agent applications with purpose-built UIs. Agents and UIs share actions, validation, permissions, data, and relevant application state. - ApodexAI/FrontierAgent
An agent runtime, terminal interface, and evaluation suite for extended research and file work. It supports a stateful ReAct agent and an Agent Team with a coordinator, task board, parallel assignments, and collected reports. - totec448-spec/chat-on-steroids
A local MCP workspace connecting ChatGPT to files, tests, terminals, desktop tools, and workers. It supports long-task corrections and carrying session and worker history into a fresh chat.
Only repositories in the ranked Trendshift lists are included, and the lists are used only to find candidates. We do not copy their ranks. Descriptions, licenses and star counts come from each GitHub repository. The notes are our own reading. We have not tested these projects, and a place on a trending list does not prove quality.