Hermes Agent
Hermes is the persistent background worker tier — an always-on, self-improving MCP bridge that runs 24/7 on the AI OS platform. While Claude is the "brain" (planning and decisions), Hermes is the "hands" (interacting with the real world around the clock).
Architecture
Hermes connects to AI OS as a Model Context Protocol (MCP) server. The Orchestrator delegates tasks to Hermes for persistent, background execution:
- Claude (AI OS) — Planning, decision-making, orchestration, complex reasoning
- Hermes — 24/7 execution, mobile bridge, cron jobs, approval gating, long-running tasks
The MCP connection is managed by the platform and configured automatically for each tenant.
Remote Approval Gate
When Hermes encounters a destructive or risky operation, it pauses execution and pushes an approval prompt to your phone:
- A task requests a risky action (file deletion, force-push, database modification)
- Hermes suspends the action and creates an approval request
- A notification is sent via Telegram, Slack, or Discord
- You approve or reject from your phone
- Hermes resumes or aborts based on your decision
Approval requests are tagged with risk levels:
| Risk Level | Examples | Default Action |
|---|---|---|
| High | Force-push, database drop, production deploy, key rotation | Block until approved |
| Medium | File deletion, config changes, branch deletion | Block until approved |
| Low | Log cleanup, cache purge, temp file removal | Auto-approve after 5 min |
Walkaway Mode
Initiate a long-running task from the dashboard, then close your laptop. Hermes acts as the bridge:
- Progress pings — Sends status updates to your phone at each milestone
- Mobile replies — Reply from your phone with instructions: "keep going," "make it simpler," "push to GitHub"
- Completion notification — Alerts you when the task finishes with a summary
- Approval integration — If the task hits a risky action, you get an approval prompt on mobile
Remote Bug Diagnosis
When a bug report arrives in Discord or Slack, use Hermes from your phone to trigger analysis:
- Send a message to Hermes via Telegram: "Analyze the auth bug reported in #bugs"
- Hermes reads the bug report, instructs Claude to analyze the relevant files
- Claude's diagnosis is sent back to your phone
- Optionally, approve a fix from mobile
Scheduled Skills
Hermes has six named skills. Three run for real today — dispatched to a real agent on a schedule, or on demand from the dashboard or via /api/hermes/delegate. The other three are still simulated pending their own real integrations.
Real skills
| Job | Schedule | Description |
|---|---|---|
| Dev Project | On demand | Grok Build plans a platform upgrade — see Self-Improve |
| News Brief | 0 6 * * * | Live intelligence sweep via the scout agent |
| Uptime Check | */30 * * * * | Health-snapshot review via the sysadmin agent (real disk, memory, and load metrics) |
Simulated skills
The schedule and dashboard UI exist for these, but delegating them does not yet call a real agent or touch a real external service — treat their output as a placeholder, not a real result:
| Job | Schedule | Why it's not real yet |
|---|---|---|
| Inbox Summary | 0 8 * * * | No email/OAuth integration yet |
| GitHub Backup | 0 2 * * * | Scope not yet decided (state snapshot vs. repo mirror) |
| Comment Monitor | 0 */4 * * * | No YouTube/social polling integration yet |
Platform Self-Improvement
Hermes's Dev Project skill hands off to Self-Improve, which reads AI OS's own code and proposes upgrade plans using xAI's Grok Build — either to apply to your instance or as a draft pull request against the public distribution repo. Every apply and every PR always requires your explicit approval; see the Self-Improve docs for the full safety architecture.
Frequently asked questions
No. Hermes's real skills run as an in-process dispatcher inside your AI OS instance — there is no standalone Hermes MCP server to install or manage.
Check the tables above, or call GET /api/hermes/status — each entry in the returned skills array is tagged real: true when it dispatches to an actual agent.
They're the same underlying feature reached two ways — Dev Project is Self-Improve's planning flow triggered through Hermes's delegate API instead of the dedicated Self-Improve dashboard view. See Self-Improve for the full picture.
API Endpoints
Check MCP connection status, uptime, stats, and loaded skills.
Delegate a task to Hermes. Modes: background, walkaway, cron (simulated), or the real dev-project, news-brief, uptime-check.
List all active delegated tasks with progress and logs.
Get pending approval requests with risk levels and context.
Approve or reject a pending action. Body: { "decision": "approve" }
List all scheduled Hermes cron jobs.
Create a new Hermes cron job.
Configuration
| Variable | Default | Description |
|---|---|---|
HERMES_MCP_URL | http://127.0.0.1:8420 | MCP server endpoint for Hermes |
TELEGRAM_BOT_TOKEN | — | Required for mobile approval prompts via Telegram |
SLACK_WEBHOOK_URL | — | Required for Slack notifications from Hermes |
Key Benefits
- Tenant isolation — Each tenant's Hermes tasks are fully isolated from other tenants.
- Cost efficiency — Background and cron tasks use your own API keys at standard rates.
- Always available — Unlike interactive sessions, Hermes works 24/7 without requiring your browser.