Running rig as a service, AI Agents

Rig Agency Implementation, Productized AI Code Automation

Learn how to package Rig's autonomous codebase reading, concurrent tool execution, and background worker scheduling into retainer services for development teams. This course covers client onboarding workflows, custom Python plugin development for agency-specific tasks, and pricing models for ongoing code maintenance and test automation delivered through the agent.

Open the decision record for rig

What does running rig for clients commit you to?

Published figures for this service. Blank fields are not published.

Monthly tool cost
Vendor software cost: open-source, pricing model published as open-source. No paid plan tiers are published, so software cost is Not published. Agency labor to install, configure endpoints, and validate against a client repo is required and must be modeled from your own rates.
Time to first value
Not published, time_to_value is listed as 'hours' but no explicit duration is supplied
Payback
Not modeled, client price, labor rate, model usage cost, overhead, and expected engagement volume are not supplied
Guided implementation
8 hours

Is rig worth running as a client service?

The published evidence supports rig as an MIT-licensed, self-hosted coding agent suitable for agencies with in-house developers who want endpoint control and auditable agent code. What remains unknown: how much an agency can charge clients for a managed rig service, and what the actual delivery economics are, since no vendor pricing tiers or market rates are published.

An agency-fit judgement for reselling this service. It is separate from the tool description on the decision record.

Before you start

What has to be in place before the first client engagement.

Tools and subscriptions

  • rig single binary (MIT-licensed, no runtime dependencies)
  • OpenAI-compatible model endpoint, llama.cpp, llama-swap, Ollama, or OpenRouter
  • Target client repository with local read/write access
  • AGENTS.md file with standing session instructions
  • Python environment for single-file rig plugin authoring

People and inputs

  • Developer time to inspect the few-hundred-line agent loop before deployment
  • Internal runbook covering endpoint config, plugin registration, worker sandbox, and /scheduler cron setup
  • Validation repo to test concurrent tool calls, background workers, and resumable sessions
  • Per-client repo onboarding checklist aligned to the task board requires/blocks model

Included with the course

7 working documents for delivering this service.

  • Rig Client Onboarding Checklistchecklist
  • Custom Python Plugin Template for Agency Toolstemplate
  • Concurrent Tool Execution SOP for Code Auditssop
  • Background Worker Scheduling Worksheetworksheet
  • Rig Retainer Pricing and Scope Guideguide
  • AGENTS.md Standing Instructions Templatetemplate
  • SSH Session Resume Troubleshooting Guideguide

Listed by name. These documents are not yet published as individual downloads.