Agent Manager by HF

Hugging Face released Agent Manager, an Apache 2.0 open-source Docker Space that runs AI coding CLI sessions — Claude Code, Codex, Gemini CLI, opencode, Hermes, OpenClaw and fx — in one private browser workspace. Users duplicate the template, mount a private storage bucket at /data to persist files, logins and conversation history across restarts, and sign in with their own provider logins or API keys. The app has no login of its own, so Hugging Face warns that both the Space and its bucket must stay private because anyone with app access can use its shell and logged-in agents.

| title | Agent Manager | |---|---| | emoji | 🖥️ | | colorFrom | gray | | colorTo | indigo | | sdk | docker | | app port | 7860 | | header | mini | | pinned | false | | license | apache-2.0 | | short description | Private cloud manager for AI coding CLI sessions | Your coding agents, together in one private workspace. Run Claude Code, Codex, Gemini CLI, opencode, Hermes, OpenClaw and fx from your browser. Follow several tasks side by side, read the conversation or open the terminal, and pick up from another device while your Space stays running. Get started get-started · Development https://github.com/huggingface/agent-manager/blob/main/docs/development.md · Report an issue https://github.com/huggingface/agent-manager/issues The current interface with example conversations. - Keep several tasks in view. Group sessions by project, arrange them side by side, and use Overview to see who is working and whose reply needs your attention. - Read at the level you need. Switch between the live terminal and a conversation reader with formatted replies, expandable tool activity, search, and earlier history. Reader support depends on the agent's transcript format. - Work with your files. Browse workspace folders, preview and edit files, upload documents or screenshots, and keep a shell beside your agents. - Give agents shared context. Manage reusable skills in one place and let agents discover, message, and wait for other sessions through the local API. - Keep the agents current. Update each CLI from Settings → General → Agents without rebuilding the Space. - Check usage and schedule work. See token usage, estimated costs, and available quota information; schedule prompts and enable device notifications. Available usage details vary by provider. - Bring another machine. Connect an agent running on your laptop or a remote server to the same workspace's conversation view. Each session has its own conversation. Sessions can share a folder when you want them to work on the same project; groups organize the interface and do not isolate files or credentials. Use your own provider login or API keys. You need a Hugging Face account and access to at least one supported coding agent. The app runs in a Docker Space; a private storage bucket mounted at /data keeps your files, logins, and conversation history across restarts. 1. Open the Agent Manager template https://huggingface.co/spaces/lvwerra/agent-manager-template and choose ⋮ → Duplicate this Space . Set visibility to Private . 2. In your new Space's Settings → Storage Buckets , create or select a private bucket, mount it at /data , and use read-write access. Do this before signing in to agents. See the Hugging Face storage guide https://huggingface.co/docs/hub/spaces-storage for the mount controls. 3. Once the Space is running, open the app. The first-run window lists the agents in your image, shows which are ready, and walks you through connecting one — either by opening a session and following its sign-in, or by adding an API key as a Space secret. Reopen it from Settings → General → Show guide .For Codex , choose Sign in with Device Code in the session. Its ChatGPT option redirects to localhost on the machine the agent runs on, which your browser cannot reach from a Space. 4. Send your first task. Add another session to review it, or create a group to keep both in view. Overview brings you back to all your sessions. Keep both the Space and its bucket private. Agent Manager has no login of its own: anyone with access to the app can use its shell and logged-in agents. The public template is an installation page. The privacy lock https://github.com/huggingface/agent-manager/blob/main/docs/privacy-lock.md helps detect an exposed instance. Agent Manager is open source under Apache 2.0. Your agent subscriptions or API usage, Space hardware, and storage follow their providers' billing. Set up the Space and bucket with Python instead Install the Hub client and sign in with an account that can create Spaces and buckets in your namespace: pip install -U huggingface hub hf auth login The names come from the account you just signed in as: python from huggingface hub import HfApi, Volume api = HfApi username = api.whoami "name" space id = f"{username}/agent-manager" bucket id = f"{username}/agent-manager-data" api.create bucket bucket id, private=True, exist ok=True api.duplicate repo from id="lvwerra/agent-manager-template", to id=space id, repo type="space", private=True, space volumes= Volume type="bucket", source=bucket id, mount path="/data" , , Open https://huggingface.co/spaces/<your-username /agent-manager when the build finishes, then continue from step 3 above. To attach a bucket to an existing Space, use the same Settings controls or the Hub volume API https://huggingface.co/docs/huggingface hub/guides/manage-spaces mount-volumes-in-your-space . Closing the browser or switching devices does not stop your agents. They run in the Space's backend as long as the Space stays awake. A Space sleep, restart, or rebuild ends running processes. With the bucket mounted, saved workspace files and checkpointed CLI state survive. Agent Manager can restart eligible sessions and resume conversations where the CLI supports it; it cannot preserve a running shell command through a reboot. Configure this in Settings → General → Restart sessions after a reboot . Without a bucket, local files and logins are temporary. For details on what is saved, see state checkpoints https://github.com/huggingface/agent-manager/blob/main/docs/agent-state-checkpoints.md and bucket backups https://github.com/huggingface/agent-manager/blob/main/docs/bucket-backup.md . | Task | Guide | |---|---| | Manage shared skills | Managed skills https://github.com/huggingface/agent-manager/blob/main/docs/managed-skills.md | | Run prompts on a schedule | Scheduled prompts https://github.com/huggingface/agent-manager/blob/main/docs/cron-jobs.md | | Connect an agent on another machine | Remote agents https://github.com/huggingface/agent-manager/blob/main/docs/remote-agents.md | | Upload files and follow file links | Uploads https://github.com/huggingface/agent-manager/blob/main/docs/workspace-file-uploads.md · File previews https://github.com/huggingface/agent-manager/blob/main/docs/file-links.md | | Inspect session operations | API log https://github.com/huggingface/agent-manager/blob/main/docs/api-audit-log.md | | Run the source or deploy a development Space | Development guide https://github.com/huggingface/agent-manager/blob/main/docs/development.md | Shared Codex sessions are a work in progress: a draft proposal https://github.com/huggingface/agent-manager/blob/main/docs/proposals/codex-shared-sessions.md describes the intended Agent Manager, TUI and Codex Remote workflow, with an experimental read-only preview https://github.com/huggingface/agent-manager/blob/main/docs/codex-shared-preview.md and an isolated binding pilot https://github.com/huggingface/agent-manager/blob/main/docs/codex-shared-bindings.md . Shared creation and automatic migration are not enabled by default, and none of this changes how you sign in to Codex today. Contributions and bug reports are welcome on GitHub https://github.com/huggingface/agent-manager . Include your agent type, browser, and steps to reproduce when reporting a problem. For a security issue, see SECURITY.md https://github.com/huggingface/agent-manager/blob/main/SECURITY.md .