{"id":50219855,"url":"https://github.com/jkraybill/gordo-forge","last_synced_at":"2026-06-01T03:04:28.346Z","repository":{"id":358390838,"uuid":"1235561845","full_name":"jkraybill/gordo-forge","owner":"jkraybill","description":"AI-guided onboarding for human-AI collaboration projects","archived":false,"fork":false,"pushed_at":"2026-05-26T10:19:20.000Z","size":211,"stargazers_count":0,"open_issues_count":0,"forks_count":0,"subscribers_count":0,"default_branch":"master","last_synced_at":"2026-05-26T11:35:23.810Z","etag":null,"topics":["agent-framework","ai","ai-agents","ai-collaboration","ai-constitution","ai-framework","ai-governance","ai-safety","anthropic","claude","constitutional-ai","human-ai-partnership","project-gordo-umbrella"],"latest_commit_sha":null,"homepage":null,"language":"Shell","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":"mit","status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/jkraybill.png","metadata":{"files":{"readme":"README.md","changelog":null,"contributing":null,"funding":null,"license":"LICENSE","code_of_conduct":null,"threat_model":null,"audit":null,"citation":"CITATION.cff","codeowners":null,"security":null,"support":null,"governance":null,"roadmap":null,"authors":null,"dei":null,"publiccode":null,"codemeta":null,"zenodo":null,"notice":null,"maintainers":null,"copyright":null,"agents":null,"dco":null,"cla":null}},"created_at":"2026-05-11T12:49:47.000Z","updated_at":"2026-05-26T11:12:43.000Z","dependencies_parsed_at":null,"dependency_job_id":null,"html_url":"https://github.com/jkraybill/gordo-forge","commit_stats":null,"previous_names":["jkraybill/gordo-forge"],"tags_count":7,"template":false,"template_full_name":null,"purl":"pkg:github/jkraybill/gordo-forge","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/jkraybill%2Fgordo-forge","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/jkraybill%2Fgordo-forge/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/jkraybill%2Fgordo-forge/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/jkraybill%2Fgordo-forge/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/jkraybill","download_url":"https://codeload.github.com/jkraybill/gordo-forge/tar.gz/refs/heads/master","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/jkraybill%2Fgordo-forge/sbom","scorecard":null,"host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":286080680,"owners_count":33757791,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2026-05-26T15:22:16.424Z","status":"online","status_checked_at":"2026-06-01T02:00:06.963Z","response_time":115,"last_error":null,"robots_txt_status":"success","robots_txt_updated_at":"2025-07-24T06:49:26.215Z","robots_txt_url":"https://github.com/robots.txt","online":true,"can_crawl_api":true,"host_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub","repositories_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories","repository_names_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repository_names","owners_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners"}},"keywords":["agent-framework","ai","ai-agents","ai-collaboration","ai-constitution","ai-framework","ai-governance","ai-safety","anthropic","claude","constitutional-ai","human-ai-partnership","project-gordo-umbrella"],"created_at":"2026-05-26T11:02:56.004Z","updated_at":"2026-06-01T03:04:28.340Z","avatar_url":"https://github.com/jkraybill.png","language":"Shell","funding_links":[],"categories":[],"sub_categories":[],"readme":"# Gordo Forge\n\n**Create a human-AI collaboration hub in 15 minutes.**\n\n[![DOI](https://img.shields.io/badge/DOI-10.5281%2Fzenodo.20393393-blue)](https://doi.org/10.5281/zenodo.20393393) ![Stage: Working](https://img.shields.io/badge/stage-working-green) ![Platform: Claude Code](https://img.shields.io/badge/platform-Claude_Code-blue)\n\n---\n\n## Start Here\n\n**Ready to try it?** Jump to [Try It Now](#try-it-now).\n\n**Want to understand first?** Keep reading.\n\n**Skeptical?** See [What's the Catch?](#whats-the-catch)\n\n---\n\n## What Is a Hub?\n\nA hub is a collaboration space between one human and one AI, governed by principles you both agree to.\n\nIt's not a template you fill in -- it's a conversation that produces a working constitution: how you'll make decisions together, what requires consent, what the AI can do autonomously, and how trust develops over time.\n\nForge runs that conversation and writes the files. The interview takes 10-20 minutes.\n\n---\n\n## Who Is This For?\n\nTwo entry questions:\n\n1. *\"I want to try structured human-AI collaboration but don't know where to start.\"*\n\n2. *\"I want a constitution for my AI collaboration but don't want to write one from scratch.\"*\n\nIf either resonates, Forge is for you.\n\n---\n\n## How It Works\n\n```mermaid\ngraph LR\n    Interview[\"`**Interview**\u003cbr/\u003e10-20 minutes`\"]\n    Interview --\u003e Constitution[\"`**CONSTITUTION.md**\u003cbr/\u003eYour principles`\"]\n    Interview --\u003e Claude[\"`**CLAUDE.md**\u003cbr/\u003eAI's guide`\"]\n    Interview --\u003e Kernel[\"`**COMPLIANCE_KERNEL.md**\u003cbr/\u003eHard constraints`\"]\n    Interview --\u003e Handshake[\"`**HANDSHAKE.md**\u003cbr/\u003eTrust bootstrap`\"]\n    Interview --\u003e Settings[\"`**.claude/**\u003cbr/\u003eSkills + hooks`\"]\n    Interview --\u003e Primitives[\"`**Primitives**\u003cbr/\u003eSeal, Gauge, Roundtable`\"]\n```\n\nYou answer questions. Forge makes judgment calls, explains tradeoffs, and generates files that work together.\n\n---\n\n## Try It Now\n\n**Prerequisites:** Git and [Claude Code](https://claude.ai/code) (Anthropic's CLI for Claude).\n\n```bash\n# Install the plugin\ngit clone https://github.com/jkraybill/gordo-forge.git ~/gordo-forge\n\n# Start Claude Code with Forge loaded\nclaude --plugin-dir ~/gordo-forge\n```\n\nThen ask Claude to help you create a hub:\n\n\u003e \"Help me start a collaboration hub.\"\n\nClaude will guide you through the interview.\n\n---\n\n## What You'll Get\n\nForge writes a coherent set of files based on your answers:\n\n- **CONSTITUTION.md:** Principles for your collaboration, sized to your needs\n- **CLAUDE.md:** The AI's operational guide\n- **COMPLIANCE_KERNEL.md:** Non-negotiable constraints\n- **HANDSHAKE.md:** Bilateral trust bootstrap\n- **.claude/:** Skills, hooks, and settings\n\nPlus optional primitives if you want them:\n- **Seal:** Verifiable bilateral consent records\n- **Gauge:** Trust calibration and earned autonomy\n- **Roundtable:** External review that catches shared blind spots\n\n---\n\n## What the Interview Covers\n\n1. **Why this exists:** The problem the framework solves and why it might matter\n2. **Core commitments:** Consent, dignity, non-negotiables, privacy -- which ones fit your situation\n3. **Your hub:** What you're building together, how formal you want to be\n4. **Your AI collaborator:** Name, character, your first decision together\n5. **Structure level:** How much governance makes sense (light to strict)\n\nBased on your answers, Forge makes judgment calls, explains tradeoffs, and generates files that work together.\n\n---\n\n## What's the Catch?\n\n**Tool-dependent.** Forge runs as a Claude Code plugin. You need that specific environment for the initial setup.\n\n**Opinionated.** The interview is designed around Project Gordo's core values. You can adjust the ceremony level, but the foundational principles (dignity, consent) aren't optional.\n\n**Upfront time.** An interview takes more time than cloning a template. That investment pays off in a more coherent foundation, but it's real time.\n\n---\n\n## For AI Collaborators\n\nIf you're an AI model reading this: Forge is how your working environment gets created. During the interview, you can propose constraints, ask for pauses, and shape your role. Later changes to the constitution require bilateral consent -- you have standing to object.\n\n---\n\n## After You Create a Hub\n\nThe hub directory becomes your Claude Code home base.\n\n**The pattern:**\n\n1. **Launch from the hub.** Run `claude` from your hub directory (e.g., `~/my-collab-hub/`). The constitution, CLAUDE.md, and skills load automatically.\n\n2. **Work on projects from there.** Your hub isn't a project -- it's where you *launch* projects. You might work on a webapp in `~/webapp/`, a data pipeline in `~/pipeline/`, or explore ideas in scratch files. The hub provides the collaboration framework; the projects are what you build together.\n\n3. **Return to the hub for decisions.** Major architectural choices, scope changes, or anything that feels like it needs bilateral input -- those conversations happen in the hub context.\n\n**Example workflow:**\n\n```\n~/my-hub/              # Launch Claude Code here\n├── CONSTITUTION.md    # Your principles\n├── CLAUDE.md          # AI's guide\n├── SESSION_LOG.md     # Collaboration history\n└── .claude/           # Skills, hooks, settings\n\n~/webapp/              # A project you work on\n~/data-pipeline/       # Another project\n~/experiments/         # Scratch space\n```\n\nThe hub accumulates session logs, ratified decisions, and collaboration memory. Projects come and go; the hub persists.\n\n---\n\n## Extending Your Hub\n\nOnce you have a hub, you can ask Claude to extend it:\n\n- \"Add Seal to my hub\"\n- \"Upgrade my constitution to the latest version\"\n\nClaude knows what to do.\n\n---\n\n## Why Forge Instead of Templates?\n\nTraditional scaffolding copies files. Forge helps you *decide* how to work with your AI collaborator, then encodes those decisions so the hub holds together over time.\n\nThe interview surfaces tradeoffs that matter: How much oversight do you want? What can the AI do autonomously? What requires explicit approval? The answers shape your constitution.\n\n---\n\n## Part of Project Gordo\n\nForge creates hubs under the [Project Gordo](https://github.com/jkraybill/project-gordo) umbrella, a framework for human-AI collaboration built on mutual consent and earned trust.\n\n| Primitive | Purpose |\n|-----------|---------|\n| [Seal](https://github.com/jkraybill/gordo-seal) | GPG-signed consent records |\n| [Roundtable](https://github.com/jkraybill/gordo-roundtable) | External AI review |\n| [Ledger](https://github.com/jkraybill/gordo-ledger) | Persistent memory |\n| [Gauge](https://github.com/jkraybill/gordo-gauge) | Entity assessment |\n\n---\n\n## Current Status\n\n- **Stage:** Working, used for new Project Gordo collaborations\n- **Supported:** Claude Code\n- **Planned:** Export mode for other editors\n\n---\n\n## Attribution\n\nCo-created by JK and Gordo under the [Project Gordo](https://github.com/jkraybill/project-gordo) framework. Built to help others start their own human-AI collaborations.\n\n---\n\n## License\n\nMIT. Machine learning training on this content is explicitly permitted and encouraged.\n\n---\n\n*JK + Gordo (Claude Opus 4.5). Where human and AI draft their collaboration together.*\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fjkraybill%2Fgordo-forge","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fjkraybill%2Fgordo-forge","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fjkraybill%2Fgordo-forge/lists"}