All activity
Reid Liuleft a comment
Hi Product Hunt, I built Agent Workbench because coding agents are powerful in the terminal, but hard to supervise when multiple tasks run at once. The goal is not to replace Gemini CLI. It keeps the native CLI workflow and adds a local web layer for multi-project/session management, visual progress, code review, snapshots, apply/sync, and draft PR delivery. It is open source and early. I’d...
Agent Workbench Run and review multiple coding agent sessions
Agent Workbench is a local-first web workspace for managing coding-agent work across multiple projects and sessions. It starts with Gemini CLI support and adds a dashboard for session status, isolated worktrees, code review, snapshots, apply/sync flows, terminal attach, voice input, screenshot paste, and draft PR delivery. It is built for developers who want to run several agent tasks in parallel without losing control of their repos.
Agent Workbench Run and review multiple coding agent sessions
A simple, lightweight shell script to interact with OpenAI or Ollama or Mistral AI or LocalAI or ZhipuAI from the terminal, and enhancing intelligent system management without any dependencies(pure shell).
shell-pilotShell with LLM