RUNIX
workspace://demo › Dashboard
checking…
Self-documenting workflows Run on your hardware — your data stays put One binary · zero install friction

The automation platform that documents itself.

Runix crystallizes every workflow into a reusable .feature file. Generic drivers, autonomous AI agents, distributed swarm, scheduler, and live observability — one binary, one platform, one source of truth.

Engine
— ms
live · uptime —
Drivers
—
— actions
Gherkin steps
—
searchable catalog
Swarm
—
— events

Quick start

recommended
$ curl -fsSL https://runix.dev/install.sh | sh
$ runix.exe ai agent "take a screenshot and tell me what you see"
$ runix.exe swarm start --agents 2 --subscribe channel:*

Recent activity

Live host probe

System status

Real readouts from /api/runtime — driver source presence on disk, node_modules, and desktop-capture availability. This is the actual Pebble host you're talking to, not a mock.

probing…
Loading
…
One-click live workflows

Hand a real task to a real agent

Each card streams a live runix ai agent session. Output flows in the IDE console while the hosted engine works the task end-to-end.

What you can do

The whole platform, one binary

Every capability below is a driver, a scheduler trigger, or a swarm role. Compose them in Gherkin or hand them to the AI.

⚙︎ Gherkin features

Drop a .feature file. Pattern-matched steps route to drivers in real time. Replay-ready. Reports auto-generate.

✦ Autonomous agent

One sentence in, reproducible workflow out. OpenAI · Anthropic · Gemini. Voice in / voice out. Resumable from checkpoint.

⌖ Distributed swarm

Ed25519-identified peers. Local file or NATS bus. Native gateway: Telegram · Slack · Discord · WhatsApp · iMessage.

⏱ Scheduler

7 trigger types: cron, interval, file watch, email IMAP, webhook, database CDC, SMS. Background daemon.

⌥ Vision & OCR

Custom vision model, OCR, and sharp-optimized screenshots for the agent loop. Pixel-accurate clicks.

⇄ MCP-native

Drop into VS Code Copilot, Claude Desktop, Cursor — any MCP host. Tools auto-register from every installed driver.

Workbench

The IDE — drive the engine

Live editor with workflow syntax highlighting, workspace files, and a 6-mode runner: Feature, Task, CLI, Ask, Agent, Voice.

engine … sample · example.feature
≡task-file×
▷cli×
?ai-ask×
✦ai-agent×
◉voice×
FEATURE
Console
idle · ready
// Runix engine ready. Open a file, create a workspace, or click ▶ Run.
Operator chat

Talk to Runix directly

Fast AI Q&A plus one-click escalation into autonomous agent execution.

Chat

New chat

Saved locally. Start a conversation or pick a card below.
New chat

How can Runix help?

Ask anything or start from a quick prompt.

Enter sends ask. Shift+Enter adds a newline.
outputs/ Hosted
—
Library

Workflow library

Reusable Gherkin features. Click any to open in the IDE. Locked workflows require sign-in.

Triggers

Triggers & schedules

Seven trigger types move work from manual launch to durable automation. Configure once, then let Runix keep it running.

daemon idle

Triggers

7 types

Quick presets

Active schedules

Mission Control

Runix Swarm

Tell the swarm what you want done. It figures out who to ask and how to split the work — you just watch the result.

node-…connecting
ASK THE SWARM
idle
LIVE CONSTELLATION
no agents · 0 msg/s
∙ ∙ ∙ awaiting first signal click ▶ Run above to spawn the swarm
planner PM FE BE marketing finance executor researcher agent 📢channel (group chat) 📡topic (broadcast bus)
SWARM STATE
0 agents
No agents running. Click ▶ Run above and one will appear automatically.
RECENT ACTIVITY seq 0
Pending
0
In flight
0
Done
0
Failed ✕ clear
0
--:--:--initConnecting to event stream…
AGENT LIVE CONSOLE
Real-time stream for the focused agent — typed events, operator notes, message bus traffic. Click an agent in Swarm State or any 🛰 console chip to switch.
no agent selected
Pick an agent above to stream its live console here. 

      


      

      

      
      
      

        

          

            
AGENT WORKSPACES

            
All files from every agent in one place. Filter by name, agent, or extension. Click a file to preview / edit. The agent that owns it auto-selects for inject / rename / delete.

          

          

            all workspaces
            
            
            
            
            
          

        

        

          
          —
        

        

          

            
Loading workspaces…

          

          

            
No file selected.

          

        

        

          

            
OPERATOR INJECT

            
            —
          

          
          

            
            
          

        

      


      
      

        

          

            
PROJECT BOARDS

            
Each project-manager owns a live .md board. Edit it here — the swarm picks up your changes automatically.

          

          

            
            
            
            no boards yet
          

        

        
        

          
          

            

              
No boards yet.

            

            
          

          
          

            
            
Select a board or click ＋ New board to start.

          

        

      


      

      

      
      

        

          

            
COMPANIES & MISSION CONTROL

            
Multi-initiative companies with a CEO/VP/PM org chart, budget envelope, and a HITL approval queue.

          

          

            
            
            
            
            idle
          

        


        
        

        
        

        
        

        

        
        

          

            
HITL APPROVAL QUEUE (0)

            Coordinator decisions waiting for human approval. Approve or deny each one to unblock the agent.
          

          

          
No approvals pending. Coordinators only ask when an action is high-stakes or above the auto-approve threshold.

        

      


      

      

      
      

        
          ▸
          Advanced — spawn specific agents & send raw messages
          (only if you know what you're doing — most users should just use ▶ Run above)
        
        

          
Pick a specific role + driver allowlist. Spawning a planner here gives you the same auto-orchestrator the ▶ Run button uses. Other roles wait passively for messages. Use topic:<name> or channel:<name> as a Send target to broadcast or route through the gateway.

          

            

              
Spawn agent

              

                
Role

                
                
Drivers (comma-separated)

                
                
              

            

            

              
Agent types & skills —

              

                

                  

                    
Agent types

                    

                      
                      
                    

                    

                      
Loading…

                    

                  

                  

                    
Skills

                    

                      
                      
                    

                    

                      
Loading…

                    

                  

                

                
                
Attached skills (click tree · comma-separated)

                
                
New type id

                
                
Name

                
                
System prompt

                
                

                  
                  
                  
                  
                

                

              

            

            

              
Send message

              

                
Target

                
                
Body

                
                
              

            

            

              
Reach

              

                Same bus across CLI · this dashboard · VS Code @runix · Copilot MCP.


                Multi-machine: set RUNIX_SWARM_TRANSPORT=nats + RUNIX_SWARM_NATS_URL on every node.


                Channels (Telegram/Slack/Discord/WhatsApp/iMessage) bridge through the gateway. Send to channel:<name>.


                Full manual ↗
              

            

          

        

      


      

        

          
Conversation tree —

          
Every message that flowed through the swarm — your task, the planner's decomposition, each delegated subtask, and the final answer. Subtasks show ↳ delegated · replies to X. Click any agent id to filter. Polls every 4s.

        

        

          
          
        

      

      

        

        

          
Loading transcript…

        

      


      


      

      
      

        

          
Audit timeline

          
Every typed event for a single trace. Paste a traceId (from the Messages tab, the engine log, or company-<id>) and walk the chain end-to-end. Persists to disk; survives restarts.

        

        

          
          
          
          no trace loaded
        

      

      

        

          

            Paste a traceId above and click ▶ Load. Common trace ids:
            
    
              
  • company-<companyId> — every coordinator decision, delegation, budget charge, and HITL gate for that company.
    • 
              
  • The correlationId shown next to "↳ delegated · replies to X" badges in the Messages tab — walks one planner→executor handoff chain.
    • 
              
  • Any traceId from /api/swarm/events.
    • 
            

          

        

      

      


      

      

        

          
Execute as agent

          
Run a real autonomous agent task with the same tool-calling loop, screenshots, reports, and logs as the IDE's Agent mode. Output streams below; artifacts land in outputs/ and refresh in the strip.

        

        

          idle
          
        

      

      

        

          
Task & live console
no target

          

            
Task (executed by the selected agent)

            
            

              
              
              max iters: 25 · drivers: ai,web,vision
            

            

              › idle. Pick an agent above and click ▶ Run to execute a task with full artifact pipeline. Open ▤ Preview in the top bar to see the live screen.
            

          

        

        

          
Run summary
—

          

            
Live screen

            
The screen output isn't trapped in this panel — open the global ▤ Preview dock (top bar, or Alt+P) to see browser frames, host desktop, recent files, or the terminal stream from any view.

            
            
Last event

            
no events yet

          

        

      

      

        
Recent run artifacts
Newest screenshots, reports, and logs from this host. Click to open. Updates after each run.

        
See all in Artifacts →

      

      

        
Loading…

      

      

    


    
    

      

        
Catalog
Drivers & capabilities
Every driver is a peer WebSocket server. Drop a folder with a driver.json and Runix discovers it.

        
— drivers · — actions

      

      
Loading…


      

        

          
Action catalog
—

          

          
Loading…

        

        

          
Gherkin step catalog
—

          

          
Loading…

        

      

    


    
    

      

        
Manifest
Everything Runix can do
The full capability matrix — 12 pillars, 31 categories, 450+ shipping features. Sourced live from /api/capabilities and /api/features; everything below corresponds to actual code in this repository.

        
— features · — categories

      

      

        
Loading capability matrix…

      

      

        
Feature catalog
Filter by category or search by name/detail. Highlights matches inline.

        

      

      

      

        
Loading feature catalog…

      

    


    
    

      

        
Outputs
Artifacts & runs
Browse every file the swarm produces — outputs userspace, agent workspaces, project boards, libraries (agents/skills), MCP queue, conversation scripts. Click any text file to preview & edit; the engine picks up your changes on the next iteration. Live screen moved to the global Preview dock — press Alt+P to see what's on screen from any view.

        

          
          
        

      

      

        
        — files
      

      

        

          
Loading file tree…

        

        

          

            

              
Select a file to preview

              
—

            

            
            
            
            
          

          

            
Pick a file from the tree on the left.

          

        

      

    


    
    

      

        
Hands-free
Voice & wake word
Whisper STT (90-95% accuracy) with native fallback. Wake word training via ElevenLabs. Continuous conversation mode.

        
idle

      

      

        

          
TTS preview

          

            
Provider

            
            
Text

            
            

              
              
            

            
› idle.

          

        

        

          
Browser STT (live transcription)

          

            
Uses the browser's native SpeechRecognition (Web Speech API). Chrome/Edge supported. Click "Start" and speak — partial transcripts appear live, finalized phrases route to chat or IDE.

            
Send transcripts to

            
            

              
              
              stopped
            

            
› press Start and speak.

          

        

        

          
Wake word recorder

          

            
Record three samples of your chosen wake phrase. Samples are kept locally (browser only) and the average duration is used as a heuristic threshold for client-side activation.

            
Wake phrase

            
            

              
              
              0 / 3 samples
            

            

          

        

        

          
Voice interrupt commands

          

            
During engine voice mode (runix.exe ai agent --voice), these phrases trigger immediate state changes. The browser STT panel can also dispatch them when "Send transcripts to" is set to "IDE Agent task" and an agent is running.

            

              🛑 halt — stop & checkpoint

              🚪 quit — stop immediately

              ▶︎ go — resume

              ℹ info — show progress

              🔀 redirect — give new instructions
            

          

        

      

    


    
    

      

        
Extensions
Driver & integration marketplace
Drop-in drivers and integrations. Everything routes through MCP.

        

          
          
          
        

      

      

    


    
    

      
Configuration
Settings
Workspace, account, and engine configuration.

      

        

          
Account

          

            
Authentication token

            

            
Required for /api/ai-agent, /api/run-feature, /api/swarm/spawn, /api/swarm/send.

            
Workspace

            
            
Engine endpoint

            
          

        

        

          
Build info

          

            
Loading…

          

        

      


      
Environment configuration
Live RUNIX_*, AI_*, OPENAI_*, ANTHROPIC_*, GOOGLE_*, GEMINI_*, ELEVENLABS_* + NODE_ENV/PATH/etc the engine sees. Secrets are masked.
—

      

        

          
Loading environment…

        

      


      
Profile
Persisted to state/profile.json on the server. Drives default voice, model, and notification choices across the UI.
—

      

        

          

            
Display name

            
            
Preferred TTS provider

            
            
Preferred AI model

            
            
Theme

            
          

          

            
Notifications

            
            
            
Experimental flags (comma-separated)

            
            

              
              
            

          

        

      


      
Privacy & compliance

      

        
GDPR · SOC 2 · ISO 27001
Data retention, consent management, audit trails — built into the engine.

        
Multi-tenant
Tenant isolation, resource quotas, namespace-based security.

        
Self-hostable
One binary, your servers, your models. No cloud dependency.

      

    


  


  
  

    Engine …
    ⌖ 0 agents
    ⌬ — drivers · — actions
    ⏚ 0 events
    
— idle —

    

    build …
    UTC --:--:--
    ○ public sandbox