Skip to content

juliantorr-es/Rig

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

60 Commits
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 

Rig

Rig is the cryptographically governed control plane for local AI coding.

Most AI coding tools mutate your code blindly. Rig forces AI work through isolated Git worktrees, cryptographic receipts, validation gates, and explicit review before anything touches your main branch.

Models propose. Rig disposes.

Install

python3.14 -m pip install -e ".[dev]"

First Run

rig init
rig ui
rig run --task fix-imports --provider custom-command

User Interfaces

  • CLI: Use the terminal for scriptable, deterministic workflows and repository management.
  • Windowed UI (rig ui): Use the rich, windowed control plane for interactive work, streaming logs, agent chat, and governance gates.
  • Textual TUI: Retired. Use rig ui for a rich interface or CLI commands for terminal workflows.

Core Concepts

  • Workspaces as the project authority boundary
  • Agent lanes as governed children of a workspace
  • Isolated worktrees
  • Receipts
  • Proposals
  • Review and apply gates
  • Job queue

Safety Model

  • No silent mutation of main
  • No auto-apply
  • No provider direct mutation
  • No background daemon by default
  • All orchestration leaves receipts and logs

Command Overview

  • rig init
  • rig config inspect
  • rig runtime list
  • rig model list
  • rig provider list
  • rig context build
  • rig system inspect
  • rig job create
  • rig job run
  • rig run --task <task-id> --provider <provider_id>
  • rig agent propose
  • rig workspace status
  • rig workspace lanes
  • rig workspace projection
  • rig workspace receipts
  • rig workspace recommend
  • rig workspace create
  • rig workspace review
  • rig workspace apply
  • rig log list
  • rig log show
  • rig debug bundle
  • rig ui

Maturity

Rig is usable as a standalone CLI and governance shell. Runtime/model/provider integration is advisory only and remains behind explicit policy gates.

Rig requires Python 3.14 or newer.

Documentation

See docs/index.md.

Workspace and lane architecture starts in:

Notes

Rig originated from a migration out of the Anigma workspace, but the product surface is now standalone. Migration history remains in docs/migration/ for reference only.

About

Rig is a local-first orchestration toolkit for turning messy project folders into structured, validated, agent-ready workspaces. It helps bootstrap repos, run deterministic checks, manage project shape, and give AI coding agents safer rails without pretending the model is the source of truth.

Resources

License

Code of conduct

Contributing

Security policy

Stars

0 stars

Watchers

0 watching

Forks

Releases

No releases published

Packages

 
 
 

Contributors