IDLE HOPS · HOVER FOR HAPPY · CLICK TO GREET Robot Orchestra is ready.
EDGE | AGENCY / AI AUTOMATION SPECIALISTS

Your AI agent orchestra.
Right on your desktop.

Coordinate specialist AI agents from your Windows desktop. Keep tasks, goals, and activity visible; choose direct local Ollama or optional Hermes delegation. The free v0.6.0 download is for Windows x64.

Free desktop downloadWindows 10/11 · 64-bitVersion 0.6.0
Check the latest GitHub release
01 Direct local Ollama option02 Hosted OpenRouter Free default · v0.6.003 Free Windows x64 installer04 Browser and Knowledge context are opt-in
01 DIRECT LOCAL OPTION · V0.6.0

Run Ollama locally.
Keep inference on your PC.

The current v0.6.0 app starts new profiles on hosted OpenRouter Free. To keep inference on this PC, install a model in Ollama, then select it under Task Model. Direct local inference needs no Hermes adapter or model API key. Browser and Knowledge context remain opt-in.

Direct local inference. Select an installed Ollama model under Task Model. Ollama runs at 127.0.0.1:11434; this route bypasses the separate Hermes bridge.
Already use Hermes? See the optional setup
LOCAL OLLAMA SETUP

Three steps to your first model.

ON DEVICE
  1. 01
    Install and open Ollama

    Use the official Windows installer, then leave Ollama running on this PC.

    Install Ollama ↗
  2. 02
    Install one model sized for your PC

    Choose a model from the Ollama library. In PowerShell, use ollama pull <model-name> and wait for the download to finish.

    Browse models ↗
  3. 03
    Select your local model in Robot Orchestra

    Click Detect local Ollama, then choose the installed model under Task Model. New v0.6.0 profiles start on hosted OpenRouter Free until you switch.

No Hermes adapter or model API key is needed for this direct local route. Model requirements depend on your hardware and the model you choose.
QUICK RECOVERY

Model not showing up?

  1. Check Ollama is open. Install it for Windows and start it before detecting models.
  2. Check that a model is installed. Run ollama list; if the list is empty, choose a model from the Ollama library and install it.
  3. Detect again. Click Detect local Ollama. If no model appears, confirm it is installed and Ollama is running, then retry.
L
Direct local Ollama

Choose this route for on-device inference. In v0.6.0, select an installed model under Task Model; new profiles otherwise default to hosted OpenRouter Free.

H
Optional: Hermes delegation

Open Bridge setup or choose Need Hermes delegation instead? Enter your adapter’s local address, such as http://127.0.0.1:4178, then select Test. The adapter must provide GET /health and accept POST /v1/orchestra/tasks. Use its actual port; remote Hermes URLs are rejected. If Test fails, confirm the adapter is running and the port is correct; check its /health route.

02 A QUIETER WAY TO WORK

Stay in the loop.
Keep the final say.

Research notes, drafts, and suggestions stay visible and reviewable. Start with local Ollama; choose the optional Hermes route only when you want delegation.

Robot Orchestra Brain workspace showing goals, recent signals, planning controls and reviewable suggestions.BRAIN / SUGGESTIONS, NOT SILENT ACTIONS
01 / KEEP CONTEXT

A Brain that keeps the next move visible.

Keep goals, ideas, and recent work in one reviewable workspace. Suggestions stay suggestions until you choose what to do next.

HOVER TO WAKE · CLICK TO GREET
02 / STAY CLOSE

Your companion, one click away.

Open the draggable desktop head and compact chat when you need them. Keep it out of the way when you don’t.

YOUChoose the task
HHermesdelegated route
LOllamadirect local route
YOUR MODEL / YOUR ROUTE
03 / CHOOSE THE ROUTE

Local Ollama first. Hermes when you choose.

Run inference through Ollama on your PC, or connect a compatible local Hermes bridge for optional delegated work. These are separate routes.

04 START WITH THE CURRENT BUILD

Your desk is
ready for a copilot.

Install Robot Orchestra 0.6.0 for Windows with a per-user setup—no administrator access is required. New profiles use hosted OpenRouter Free by default. Choose an installed Ollama model under Task Model for on-device inference; the separate Hermes bridge is optional.

RELEASEv0.6.0 · Free
PLATFORMWindows 10/11 · x64
INSTALLER135.6 MB · Per-user setup
05 ON THE ROADMAP
PLANNED V2 EXPANSION

More voice.
More environments.

The planned V2 expansion adds a richer voice companion and a multi-environment view. Mobile remains platform-specific: Android is the direction for true floating-head support; iOS would use system surfaces such as Dynamic Island / Live Activities and wallpaper experiences, not a permanent overlay.

  • ✳ Voice-first assistant interactions
  • ✳ Multi-environment agent view
  • ✳ Android floating head; iOS Dynamic Island / Live Activities and wallpaper direction
Ask about the V2 roadmap
PLANNED EXPANSION
$8.99
PLANNED ONE-TIME PRICE · NOT AVAILABLE YET

The current Windows desktop download is free. V2 is planned at $8.99 one-time; no checkout or purchase is available on this page.

Roadmap preview
No checkout on this page

This is a roadmap preview, not an offer to purchase. Features, timing and final terms may change before release.

06 GOOD TO KNOW

A few things
before you start.

Can’t find the answer? Ask the Robot Orchestra head in the corner, or email EDGE | AGENCY.

Do I need Hermes to use Robot Orchestra?

No. In v0.6.0, new profiles start on hosted OpenRouter Free. For on-device inference, install Ollama and a model, click Detect local Ollama, then choose it under Task Model. The separate Hermes bridge is optional for delegated work.

What does “local-first” mean here?

Robot Orchestra stores its Brain data on your PC, but model routing depends on your selection. New v0.6.0 profiles start on hosted OpenRouter Free; direct Ollama sends inference to the Ollama service on your PC. The separate Hermes bridge may use its configured model provider. Browser and Knowledge context are off until you opt in.

Can I scan a browser page?

The Chrome/Edge companion supports user-triggered, bounded site scanning. Review the captured text first; page text is not sent to a model until you explicitly include it. The browser side panel is optional to the desktop download.

Why might Windows show a warning?

Release 0.6.0’s Windows installer is unsigned. SmartScreen may warn when you run it. Download only from the official GitHub release and compare the SHA-256 shown on this page if you choose to verify it; v0.6.0 does not attach a separate checksum file.

Is the $8.99 V2 expansion available now?

No. $8.99 is the planned one-time V2 price, not a current offer. The Windows 0.6.0 download is free, and this page has no checkout. Mobile directions are planned only: Android floating-head support; iOS Dynamic Island / Live Activities and wallpaper experiences.