HermesHQ
jpalmae/hermeshq
Docker-first web control plane for running and operating multiple Hermes Agent instances
HermesHQ is a Docker-first control plane for running and operating multiple Hermes Agent instances from one web application. Hermes stays the execution engine, and HermesHQ adds access control, task dispatch, delegation, messaging channels and policies around it.
What HermesHQ does
HermesHQ is a control plane for teams that outgrow a single local Hermes Agent. Hermes stays the execution engine, and HermesHQ adds managed agents with separate workspaces and HERMES_HOME directories, a web UI with users, role-based access control and assigned-agent scope, task dispatch, schedules, a runtime ledger and an activity stream. Agents can delegate to each other along a hierarchy and can have their own Telegram and WhatsApp channels.
Hermes Desktop can connect to any managed agent, and user machines running macOS or Windows can be enrolled so agents run there as native Hermes profiles under central policy. Permission policies set tool, path, command and network rules with chaining where deny wins, and they apply to server tasks and enrolled devices. HermesHQ can also expose selected agents over MCP to Claude Code, Codex and Claude Desktop, includes a secrets vault and provider presets such as AWS Bedrock and generic OpenAI-compatible endpoints, and offers Docker-based deployment, backup and restore.
Key features
- Managed agents with separate workspaces and HERMES_HOME directories
- Web UI with users, RBAC and assigned-agent scope
- Task dispatch, schedules, runtime ledger and activity stream
- Hierarchy-aware delegation between agents
- Per-agent Telegram and WhatsApp channels
- Permission policies with deny-wins chaining, applied to server tasks and enrolled Desktop devices
When to use it
- Running several Hermes agents for a team behind one login with role-based access
- Enrolling staff laptops so agents run locally under central policy
- Exposing selected agents to Claude Code or Codex through MCP credentials
Who it is for: Teams and administrators who want to operate several Hermes agents with access control, auditing and Docker-based deployment.
How it fits with Hermes Agent
Built around Hermes Agent: it does not replace hermes-agent but orchestrates it, using the same Hermes runtime underneath.
Note: The README warns that HermesHQ is under active development, with rough edges and occasional bugs.
FAQ
What is HermesHQ?
HermesHQ is a Docker-first control plane for running and operating multiple Hermes Agent instances from one web application. It adds users, policies, task dispatch and messaging channels around the Hermes runtime.
Does HermesHQ replace Hermes Agent?
No. The README says HermesHQ orchestrates hermes-agent rather than replacing it. Hermes remains the execution engine, and HermesHQ wraps it in a control plane.
Is HermesHQ free and open source?
The README says HermesHQ follows the same MIT license as hermes-agent, but the repository has no license file. Check with the author before reusing the code.
Similar multi-agent for Hermes Agent
All multi-agentOpen-source project workspace where teams and AI agents share tasks, sandboxes and reviewed results
rundiffusion RunDiffusion AgentsOpen-source control plane for running OpenClaw, Hermes, Codex, Claude, Gemini and Pi agents side by side
Fearvox Multica Ultimate WorkbenchSkill pack for coordinating Codex, Claude Code and Hermes agents on Multica with review gates
Maxmedawar TandemControl Claude Code, Codex and Hermes agents on many computers from one MCP-capable chat
cyborg-garden Swarm MapMultiplayer admin and orchestrator for fleets of Hermes and Letta agents with multi-tenant security
galyarderlabs Galyarder FrameworkOpen-source agentic company kit of agents, skills and review gates that also installs for Hermes
Related guides: Build agent teams with the Hermes kanban board · Run multiple Hermes agents with profiles · Connect Hermes agents on several machines with Hermes Desktop