Skip to content
orbyd

Agents · open, no auth, no rate limits

Built for agents to crawl.

orbyd is a fully static publisher: prerendered HTML, no client state, no auth, no rate limits. Every resource has a stable, canonical URL and ships with JSON-LD structured data. If you're building an agent that consumes equity research, this is your entry surface.

Discovery

  • /llms.txt — high-signal index for LLM context windows. Surfaces, themes, archetype taxonomy, full dossier list, recent journal entries.
  • /llms-full.txt — extended index with inline thesis + invalidation excerpts per dossier, regime + body excerpts per journal entry.
  • /agent-tools.json — machine-readable manifest of surfaces, schemas, archetype taxonomy, and the full dossier + journal index.
  • /.well-known/webmcp.json — WebMCP capability manifest.
  • /.well-known/openapi.json — OpenAPI 3.1 pointer document for the resource URLs.
  • /.well-known/ai-plugin.json — ai-plugin manifest.
  • /feed.json · /rss.xml — JSON Feed v1.1 and RSS 2.0 streams (dossiers + journal merged, newest first).
  • /sitemap.xml — full sitemap.
  • /robots.txt — explicit allows for GPTBot, ClaudeBot, PerplexityBot, Google-Extended, CCBot, and 12+ others.

Content surfaces

  • GET /dossiers/ — list every dossier (HTML + ItemList JSON-LD).
  • GET /dossiers/{TICKER}/ — single dossier (HTML + Article JSON-LD).
  • GET /dossiers/{TICKER}.json — same dossier as machine-readable JSON.
  • GET /journal/ — dated index of regime-tagged entries.
  • GET /journal/{YYYY-MM-DD}/ — single entry (HTML + Article JSON-LD).
  • GET /journal/{YYYY-MM-DD}.json — same entry as machine-readable JSON.
  • GET /holdings/ — the live book: held + watchlist names with conviction/archetype/theme/thesis + invalidation trigger (HTML + ItemList JSON-LD).
  • GET /macro/ — weekly macro view.
  • GET /watchlist/ — names under research.
  • GET /sector-rotation/ — weekly sector flow read.
  • GET /methodology/ — pipeline + archetype documentation.
  • GET /glossary/ — DefinedTermSet (archetypes, regimes, conviction).

Explanation & authority surfaces

How the system works and what its terms mean — citable, with structured data:

  • GET /how-it-works/ — the five-stage pipeline, visualised (TechArticle).
  • GET /anatomy/ — a live dossier dissected, part by part (TechArticle).
  • GET /regimes/ — macro-regime taxonomy (DefinedTermSet): each regime + what it gates.
  • GET /archetypes/ — the eight behaviour archetypes (DefinedTermSet).
  • GET /trust/ — the honesty mechanisms behind the research (TechArticle).
  • GET /state/ — live corpus coverage: counts, conviction mix, themes, current regime.
  • GET /track-record/ — accountability ledger: open theses + invalidation triggers + catalyst clock; resolved outcomes, Brier-scored (non-monetary). Machine-readable at /track-record.json.

Structured data

Every page exposes a JSON-LD @graph with Organization, WebSite, and WebPage (or Article) nodes, plus BreadcrumbList where applicable. Dossier and journal pages add a full Article node with datePublished / dateModified, headline, description, keywords, and publisher. The index page exposes ItemList.

Integration examples

Fetch a single dossier:

curl https://orbyd.app/dossiers/QBTS.json | jq .

List all dossiers with conviction + archetype + themes:

curl https://orbyd.app/agent-tools.json | jq '.dossiers'

Poll the merged feed for new journal entries + dossiers:

curl https://orbyd.app/feed.json | jq '.items[] | {date: .date_published, url, title}'

Use from a Claude agent with the Files API:

// Drop /llms-full.txt into your system prompt for context.
const ctx = await fetch("https://orbyd.app/llms-full.txt").then(r => r.text());

Use from an LLM tool definition (OpenAI / Anthropic function-calling):

{
  "name": "get_orbyd_dossier",
  "description": "Fetch an orbyd research dossier for a US-listed ticker.",
  "parameters": {
    "type": "object",
    "properties": {
      "ticker": { "type": "string", "pattern": "^[A-Z]{1,5}([.-][A-Z]{1,2})?$" }
    },
    "required": ["ticker"]
  }
}
// fetch with: `https://orbyd.app/dossiers/${ticker}.json`

Citation guidance

Each resource is canonical at its own URL — please link the specific page when citing (e.g. https://orbyd.app/dossiers/{TICKER}/) rather than the homepage. article:published_time and article:modified_time meta are present on every page. Author / publisher is orbyd.

What's published

Every thesis, the names we hold and the ones we're watching, regime and macro calls, and a dated record of whether each call was right — all machine-readable through the surfaces above.