A modular super-user kit · MIT licensed

Assemble the AI system you actually want.

Start with project memory. Add agents, expert workflows, human oversight, and secure runtime. Every part is visible, replaceable, and yours.

MIT licensed10+ AI platforms200+ agents400+ deployable parts0 hosted lock-in
01 / Parts index

No black box. Just useful parts.

AIWG turns hard-won ways of working into inspectable building blocks. Use the complete system or start with one capability. The project—not a vendor account—owns the result.

PART 01

Remember

Keep decisions, architecture, instructions, and operating context coherent across providers.

  • Project context
  • Persistent memory
  • Provider adapters
PART 02

Practice

Turn reliable methods into reusable agents, skills, commands, reviews, and complete workflows.

  • Expert agents
  • Lifecycle flows
  • Custom bundles
PART 03

Understand

Make status, decisions, evidence, approvals, and failures visible to the people responsible.

  • Verification
  • Traceability
  • Human gates
PART 04

Own

Run long-lived agents through Cockpit and Agentic Sandbox on infrastructure you control.

  • Containers or VMs
  • Audit trail
  • Local control
02 / Assembly

One paste to a working system.

Open your project in a supported AI provider and paste the instruction below. The installer inspects first, explains its plan, preserves your work, installs AIWG, and verifies the result.

1OPEN

Open your project in Claude Code, Codex, Cursor, Copilot, Warp, or another supported provider.

2PASTE

Give the provider the setup manifest and let it inspect the current system.

3VERIFY

AIWG builds context, deploys the toolkit, and proves that the provider is engaged.

Install or repair AIWG for this project by following
https://aiwg.io/setup.aiwg.yaml
Explain the plan before changing anything, preserve my existing work, and ask
me only for choices you cannot safely determine.
03 / Compatibility

Bring your own AI tool.

AIWG maintains one provider-neutral source and deploys the form each supported tool expects. Switching providers is configuration, not a rewrite.

Built to leave intact

Project-local extensions, addons, frameworks, and plugins keep the same shape as upstream artifacts. Build locally, share privately, or contribute publicly without translating the work.

Explore open customization →
04 / Build notes

See how the kit is made.

Essays, technical guides, research notes, and release reports from building durable AI-assisted systems in the open.

FEATURED · ARCHITECTURE · 8 MIN

Portable workflows are infrastructure.

Why useful practice must survive changes in project, provider, and team—and how identical-form artifacts make that possible.

Read the essay →
OPERATIONS · 11 MIN

Cockpit and the control plane

What people must be able to see, approve, and stop.

Read →
METHOD · 8 MIN

How context is assembled

Building a coherent system prompt from project-owned sources.

Read →
05 / Open workshop

Use it. Change it. Pass it forward.

AIWG is MIT licensed because advanced capability should be broadly available. Inspect every part, adapt it for your own work, and share improvements on your terms.

Build locally

Create project-owned skills, agents, commands, rules, and complete bundles without maintaining a fork.

Learn together

Join the community, compare methods, report gaps, and help make high-quality AI practice accessible.

Contribute upstream

Promote useful project-local work into the shared corpus without rewriting its structure.

06 / Optional secure runtime

Run long-lived agents on your terms.

Add AIWG Cockpit and Agentic Sandbox when work needs isolation, durable sessions, human approval, and an audit trail. Use containers for speed or VMs for a separate kernel.

Copy the secure setup prompt
People

AIWG Cockpit

Observe sessions, approve decisions, inspect state, and stop work.

Your infrastructure

Agentic Sandbox

Self-hosted container and VM execution with resource policy and audit evidence.