Claude Code
Hard, multi-step coding work in the terminal when you want the highest benchmark scores.
A native desktop app for terminals and coding agents. Agents run in herdr-core, a small local server, so quitting or updating the app leaves them working; a status view shows which agent needs you. Layouts, mods and settings are plain files your agent can edit. Remote machines join over SSH.
| Free tier | Yes. The app, herdr-core and Herdr TUI are free and open source (Apache 2.0). |
|---|---|
| Paid plans | None. You pay for whichever agents and models you run. |
| Maker | herdrdev |
| Source | https://herdr.dev |
| Last verified |
Hard, multi-step coding work in the terminal when you want the highest benchmark scores.
Getting strong agentic coding for the lowest cost per task, starting free with a ChatGPT account.
An AI-first code editor for everyday work, with local and cloud agents.
Teams already on GitHub who want agent mode, cloud agents and code review in their existing IDE.
Managing several local and cloud coding agents from one IDE, including third-party agents.
Yes. The app, herdr-core and Herdr TUI are free and open source (Apache 2.0).
None. You pay for whichever agents and models you run.
Running several coding agents (Claude Code, Codex and others) side by side and keeping their sessions alive when the window closes.
Herdr is made by herdrdev.
Spotted something out of date? Tell us and we'll re-verify. Facts on this page come only from the linked sources.