AGENT MACHINES

v0.2 multi-agenthermes . openclaw

An agent's loadout,
in one machine.

A rig with everything wired in: 23 built-in tools (shell, browser, vision, cron, memory), 95 SKILL.md files that auto-load by intent, 17 services ranked by interface (Vercel, Stripe, Supabase, Linear, ...), and Cursor SDK delegation through .cursor/rules. Pick Hermes or OpenClaw; plug in any provider key.

View on GitHubHermes docs

-> every cell on the right is one day in this rig's life. hover to see what fired, click to pin. dedalus boots, an agent serves, cursor codes, the rig itself reloads skills from github.

ACTIVITY -- 6 MONTHS

103 active days

hover or click a cell

nov
dec
jan
feb
mar
apr
may
lessmore

SHAPE -- STACK

vCPU

1

memory

2 GiB

storage

10 GiB

ports

8642 / 9119

api / dashboard

skills

95

bundled + wiki

mcp

cursor

@cursor/sdk

Dedalus Machines

runtime layer

->

Hermes / OpenClaw

agent layer

->

Cursor SDK

codework layer

->

CAPABILITIES

Eight surfaces, one machine.

DELEGATION

Spawns Cursor coding agents

When you ask for real code changes, Hermes hands off to a Cursor agent via the cursor_agent MCP tool. Same model the Cursor IDE runs, full file access, with the rig's skills injected as .cursor/rules.

cursor_agent@cursor/sdkload_skills

TOOLS

40+ tools, one prompt away

Terminal, file ops, web search, browser automation (Playwright), vision, image generation, MCP servers, code execution, subagent delegation.

terminalbrowser_*web_searchexecute_code

KNOWLEDGE

95-skill bundled library

SKILL.md docs that load on-demand. Ethos, empirical verification, production safety, design taste, security audit, performance, taste. Drop your own folders into knowledge/skills/ to extend.

agent-ethosdeepsectorvaldstaste-stitch

MEMORY

Persistent across sessions

USER.md models you. MEMORY.md models the environment. FTS5 sessions DB lets the agent search every prior conversation.

USER.mdMEMORY.mdFTS5

SCHEDULE

Cron, in plain English

Ask: "every weekday at 8am, brief me." It schedules itself. Pre-seeded with health checks, digests, audits.

every 1h0 9 * * *0 4 * * mon

RUNTIME

Sleep / wake, by the second

Dedalus microVMs hibernate while idle and wake in seconds. Persistent volume keeps your skills, memory, and venv intact across sleeps.

microVM/home/machine persistssecond-billing

PERSIST

Edit on GitHub, click reload

knowledge/ lives in this repo. The dashboard's Reload button runs git pull on the VM and rsyncs the new SKILL.md files into ~/.hermes/. No CLI ever.

git pullrsyncno CLI

API

OpenAI-compatible endpoint

Hermes exposes /v1/chat/completions, /v1/responses, /v1/models. Open WebUI, LobeChat, ChatBox -- anything that speaks OpenAI works as a frontend.

/v1/chat/completionsBearer authSSE streaming

LOADOUT

Your agent's complete kit.

See full loadout

Mirrors the wiki's tool-hierarchy.mdc: every tool the agent picks from, ranked. Built-in tools fire in one turn. MCP servers get auto-spawned at bootstrap. Service entries cover 17 platforms (Vercel, Stripe, Supabase, Sentry, ...). Task entries rank which skill or tool to use for code review, design review, QA, research, and more.

callable tools

33

skills

95

services

17

task categories

12

built-in tools . 23

view >
  • Browser6
  • Filesystem4
  • Memory3
  • Search3
  • Shell1
  • Vision1
  • Image1
  • Audio1
  • Code1
  • Delegate1
  • Schedule1

services . 17

view >
  • . Vercel
  • . Stripe
  • . Supabase
  • . Clerk
  • . Firebase
  • . Figma
  • . PostHog
  • . Sentry
  • . Datadog
  • . Linear
  • . Slack
  • . Shopify
each ranksMCP>CLI>skills

tasks . 12

view >
  • Browser automationagent-browser
  • Frontend verificationagent-browser diff
  • Generative UIjson-render
  • Code reviewcode-review
  • Design reviewdesign-review
  • QA + testingqa
skill . design23
skill . ops18
skill . engineering18
skill . review13
skill . philosophy11
skill . content8
skill . delegation4
callable byhermes/openclaw

COMPONENTS -- LIVE

The same chrome the dashboard uses.

status pill

StatusPill

Click to cycle

4 visible phases. Active phases pulse the dot. Sharp corners, inherits color from the variant.

button

ReticleButton

Three variants, two sizes

Primary uses the single purple. Secondary borrows the border token. Ghost is invisible at rest, surface on hover.

prompt

StarterGrid

One-tap starters

log tail

LogsTail

Polling every 7s

12:04:18infoPOST /v1/chat/completions
12:04:18infoloaded 95 skills + 10 mcp tools
12:04:21infostream open . tokens=312
12:04:21warncron next: weekly-skill-audit in 3d
12:04:23infostream done . duration=1832ms
built withdedalus+nous/openclaw+cursor

SKILLS -- 95 BUNDLED

Loaded into ~/.hermes/skills/

philosophy

11

How the agent thinks about code -- minimal-fix bias, invariants, taste.

agent-ethoscounterfactualempirical-verificationfail-closed-case-matchinginvariant-first-codinginvariant-first-testing+5

engineering

18

Conventions and refactors -- commits, comments, types, language style.

column-aligned-fieldscommentcommitfix-typesgenerate-interfacegit-workflow+12

review

13

Bug-finding and audit discipline -- adversarial review, perf, postmortems.

bugscode-reviewcross-modal-reviewdaily-bugfix-checkdeepsecexemplar-audit+7

design

23

Frontend craft -- React, taste systems, component design, image direction.

design-engineeringdesign-reviewfont-switcher-dev-toolfrontend-designfrontend-design-tasteloading-screens+17

content

8

Writing -- copy, voice, social, SEO/GEO.

app-onboarding-questionnairecontent-strategycopywritingseo-auditseo-geo-optimizationsocial-content+2

ops

18

Run things, schedule things, browse the internet, query databases.

agent-activity-logagent-browseragent-reachautomation-cronci-cd-best-practicescomputer-use+12

delegation

4

When and how to spawn another agent (Cursor, sub-agents, skill discovery).

cursor-codingfind-skillsskill-auditorskill-creator

ARCHITECTURE

One key, two endpoints, full agent.

The same DEDALUS_API_KEY provisions the machine and authenticates inference. Dedalus owns the runtime, Nous ships the agent, Cursor handles codework.