By kamaalg
Turn the projects you build with Claude into a walkable voxel kingdom — each repo becomes an estate with an honest plaque and a walkable README. Runs locally on your own Claude Code; your source never leaves your machine.
Turn the projects you build with Claude into a walkable voxel kingdom — each repo becomes an estate with an honest plaque and a walkable README.
Foreman runs entirely on your machine. Inference uses your local Claude Code subscription via claude -p — no API key needed, your source never leaves your machine.
npx foreman-kingdom
Then open http://localhost:5173 and walk your kingdom.
| Key / gesture | Action |
|---|---|
W A S D / arrow keys | Walk |
| Click + drag | Look around |
| Scroll | Zoom |
E (near a building) | Enter — read the estate plaque + README |
V | Toggle first-person view |
M | Toggle minimap |
Esc | Leave the estate |
Foreman reads the projects Claude remembers working on (from local Claude memory), then:
http://localhost:5173.Every visual maps to a real signal: a big building = a lot of code/commits, a lit beacon = active work, the plaque = what it honestly does.
Foreman ships a Claude Code plugin that adds a /foreman:kingdom command and a foreman skill (so you can just ask "build my kingdom").
Install via the Claude Code plugin marketplace (once listed):
/plugin install foreman
Or manually: clone this repo and run /plugin install <path-to-foreman-plugin>.
| Command | What it does |
|---|---|
foreman / npx foreman-kingdom | Scan projects, generate plaques, serve the kingdom |
foreman serve | Serve the already-generated kingdom (fast, no re-scan) |
foreman build | Generate js/data.js without serving |
If you haven't generated your own kingdom yet, Foreman ships with js/data.js pre-populated with sample projects (harbor_api, olive-storefront, etc.) so the world loads immediately. Run foreman once to replace it with your real projects.
MIT — see LICENSE.
Own this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge. GitHub access is read-only (username + org membership).
Sign in to claimOwn this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge. GitHub access is read-only (username + org membership).
Sign in to claimBased on adoption, maintenance, documentation, and repository signals. Not a security audit or endorsement.
npx claudepluginhub kamaalg/foreman --plugin foremanUpstash Context7 MCP server for up-to-date documentation lookup. Pull version-specific documentation and code examples directly from source repositories into your LLM context.
Build and maintain an LLM-curated personal knowledge base in your project — Andrej Karpathy's LLM Wiki pattern, designed to scale to thousands of pages without becoming a context bottleneck. Now with an optional compiled graph layer for typed, provenance-backed relationships.
AI-powered wiki generator for code repositories. Generates comprehensive, Mermaid-rich documentation with dark-mode VitePress sites, onboarding guides, deep research, and source citations. Inspired by OpenDeepWiki and deepwiki-open.
Claude + Obsidian knowledge companion. Sets up a persistent, compounding wiki vault (Karpathy's LLM Wiki pattern). v1.7 "Compound Vault" + v1.8 methodology modes close 5 of 5 priority gaps from the May 2026 compass artifact. Ships: substrate alignment with kepano/obsidian-skills, default Obsidian CLI transport, hybrid retrieval (contextual prefix + BM25 + cosine rerank per Anthropic's Sept 2024 research), per-file advisory locking for multi-writer safety, pre-commit verifier agent, AND methodology modes (LYT / PARA / Zettelkasten / Generic) for first-class organizational support no other Claude+Obsidian competitor offers. v1.7.x audit closure: every BLOCKER + HIGH + MEDIUM + LOW finding from the v1.7.0 audit is CLOSED or DEFERRED-with-rationale. Optional DragonScale Memory extension (log folds, deterministic addresses, semantic tiling lint, boundary-first autoresearch).
Complete AI coding workflow system. Self-correcting memory + persistent FTS5-indexed research wikis + auto-research loop + multi-LLM council on a single SQLite store. 33 skills, 8 agents, 22 commands, 37 hook scripts across 24 events. Cross-agent via SkillKit.
Make your AI agent code with your project's architecture, rules, and decisions.