Run coding agents across tabs, panes, and remote machines. Shepherd keeps terminal sessions alive when the app closes, tracks which agents are working or waiting, and lets you return to their files and changes without losing context. Agents understand the current Shepherd context, control tabs and panes, and collect feedback through browser reviews, while you monitor every agent’s status in real time.
Loading comments…
Project Info
Product Keywords
Shepherd Terminal is a workspace built specifically for running coding agents like Codex and Claude across tabs, panes, and remote machines. It combines a terminal, an agent monitor, and a session manager into one interface, so you can launch agents, watch their progress, and pick up exactly where they left off — even after closing the app. Sessions stay alive in the background, and when you reconnect, the same tabs, panes, and live processes are restored.
Shepherd keeps every terminal process running even when the app closes. When you reopen it, the same tabs, panes, and live sessions are restored, so you never lose an agent’s working state or have to restart long-running tasks.
A small, always-available panel shows the status of every active agent — working, waiting for input, or completed since you last looked. You can jump between Codex and Claude sessions without hunting through separate windows.
The Shepherd Plugin gives agents the ability to create panes, open tabs, send input, and read output on their own. You describe the work, and the agent arranges the terminal layout it needs, runs sub-agents, and verifies results without you manually setting up every pane.
Return to an agent session with its exact tab and pane restored. From there, you can view the files and diffs the agent created — all without leaving Shepherd. The worktree view lets you open files and inspect exact changes inline.
Shepherd doesn’t just run agents — it gives them room to work, and gives you the visibility to trust them.
Most terminal tools treat agents as isolated processes. Shepherd treats them as collaborators: agents can build their own workspace, delegate to sub-agents, and run tests in parallel panes while you watch. The combination of persistent sessions, a live monitor, and agent-driven workspace control means you spend less time babysitting terminals and more time reviewing results.
You regularly run multiple coding agents and find yourself losing track of what each one is doing, or you’re tired of re-creating terminal layouts after every restart. If you work remotely and want the same agent workflow on a remote machine, or if you want agents to handle their own pane and tab setup, Shepherd Terminal is built for that exact workflow.
Other tools you might consider
You're running more coding agents than ever, but you can't keep up with them. That's where AgentPeek comes in. It pulls every session up into your Mac notch, live. Glance up, approve a prompt, watch token usage and manage the entire flow without pausing your YouTube video. All local, all yours.
Clears is an agentic execution platform for autonomous software delivery, helping R&D organizations move beyond individual AI tools to agentic execution across the entire SDLC.
The moment an agent needs to deploy something, it slams face-first into a wall built for humans. Today we're rolling out Temporary Accounts on Cloudflare Workers. Any agent can now run wrangler deploy — temporary and get a live Worker in seconds.
AI agents can ship quickly, but without the right product context, they're often flying blind. Brief gives product teams a living source of truth that captures decisions, preserves product intent, and serves relevant context to humans and agents through chat, Slack, CLI, and MCP. It keeps strategy, decisions, and execution connected from vision to impact.
Maker
neon_dev
Alternatives
Loading comments…