# Free Agentic Publication Digester — Daily Federal Digest

> An automated, citation-bound, opinion-agnostic daily digest of official United States government publications — congressional, executive, and judicial — built only from primary sources. This site is explicitly built for AI-agent
> ingestion as well as human reading: see /agents.html.

## Core
- [Latest digest](https://fapd.info/2026-11-06.html)
- [All digests (index)](https://fapd.info/index.html) (the home page lists the 7 most recent days and links the archive; it is NOT a complete enumeration — digests.json is)
- [Digest archive](https://fapd.info/archive.html) — every published day as a calendar of links, one page per year (https://fapd.info/archive/YYYY.html for earlier years). Human navigation; agents should read digests.json instead.
- [Machine-readable digest index](https://fapd.info/digests.json)
- [Atom feed of digests](https://fapd.info/feed.xml)
- [API catalog (RFC 9727)](https://fapd.info/.well-known/api-catalog) and [OpenAPI description](https://fapd.info/openapi.json)
- [AI catalog](https://fapd.info/.well-known/ai-catalog.json)
- [Agent skills](https://fapd.info/.well-known/agent-skills/index.json) — step-by-step instructions for reading and citing the digest
- [MCP service](https://fapd.info/agents.html#mcp) — read-only, no inference: https://fapd.info/mcp
  - list_digests — Lists published digest days, newest first: date, page URL, canonical Markdown path and teaser.
  - get_digest — Returns the canonical Markdown digest for a published day, verbatim; with section, one heading block of it. The digest summarizes a rule-selected subset of the day and counts the rest — for every item an agency or collection published, use get_day_listing.
  - get_live_day — Returns today's PRELIMINARY observed items with the day's disclosures and counts. Items the publisher dates earlier are excluded unless include_backfill is true; collection narrows to one collection; agency keeps one agency's items (exact name, case ignored) — facets.tags in the result lists the agencies present.
  - list_day_views — Lists the days that have a frozen observed listing, newest first.
  - get_day_listing — Returns a finished day's complete frozen observed listing — every item, including the ones the digest only counted — with its disclosures and counts. Items the publisher dates earlier are excluded unless include_backfill is true; collection narrows to one collection; agency keeps one agency's items (exact name, case ignored) — facets.tags in the result lists the agencies present.
  - list_sources — Lists the source directory as a summary per source: identity, method, status and health label. get_source returns one source's full record including daily activity; the source-directory resource is the whole file.
  - get_source — Returns one source's full record: registry entry, ingestion statistics, health and daily activity.
  - get_agent_guide — Returns llms.txt: the plain-text guide to every published surface.
- [auth.md](https://fapd.info/auth.md) — no authentication exists
- [Today — live in-progress day, PRELIMINARY](https://fapd.info/today.html) (also /today.json, whose `facets.tags` gives keyword counts and whose items carry the same tags for client-side filtering. READ THE FLAGS: items[] includes entries the human page excludes — filter on is_backfill=false for the day's own news (backfill_count states how many are excluded), and check day_context (null on federal business days; a weekend/holiday object explains a quiet stream). Items may change until the end-of-day gates freeze the dated digest)
- [Source guide — what we ingest and why](https://fapd.info/sources.html)
- Per-source pages: https://fapd.info/sources/<source-id>.html — one page per registry entry (active, planned, and unavailable alike): identity, ingestion method and politeness posture, measured statistics at 24-hour / 14-day / all-time windows with day-by-day charts, health label history, and — where stored — model-written orientation and assessment blocks, labeled as such. Source ids are listed in /sources.json.
- Frozen day views: https://fapd.info/day/YYYY-MM-DD.html and https://fapd.info/day/YYYY-MM-DD.json — the complete observed listing for a finished publication day, mechanical rules applied, frozen at end of day (or reconstructed from the stored observation journal, disclosed in place). The dated digest at /<YYYY-MM-DD>.html remains the canonical record; days before the observation journal began have no day view, and the JSON mirrors today.json's shape and labels.
- [Source health and statistics, machine-readable](https://fapd.info/sources.json) (per source: items ingested over a trailing window and their per-day rate, average/median content length, delivery mode, our request outcomes by HTTP status class, and a health label with the thresholds that produced it, so any label can be recomputed from the numbers in the same file. These describe OUR INGESTION — items we recorded and requests we made — and are not a measurement of any agency or publisher. Not part of the official record; do not cite as government publication.)
- [Blog — notes on how this project is built](https://fapd.info/blog.html) (commentary ABOUT the project: not digest content, not part of the official record, and not government publication. Cite it as commentary, never as a source for what the government did.)
- [About this project](https://fapd.info/about.html)
- [Accessibility](https://fapd.info/accessibility.html)
- [How AI Built This](https://fapd.info/ai-development.html)
- [Our crawler](https://fapd.info/bot.html)
- [Frequently Asked Questions](https://fapd.info/faq.html)
- [Methods](https://fapd.info/methods.html)
- [Privacy & licensing](https://fapd.info/privacy.html)
- [Selection rules](https://fapd.info/rules.html)
- [Free Agentic Publication Digester (FAPD)](https://fapd.info/readme.html)
- [Access guide for agents](https://fapd.info/agents.html)

## Notes
- Digest URLs are stable: /<YYYY-MM-DD>.html
- Official text vs model-generated text is labeled in place;
  every item cites its official record (govinfo for the govinfo
  collections; the publisher's own page for agency releases,
  recorded votes, bill actions, and presidential actions).
- Canonical Markdown + provenance manifests live in the public repository: https://github.com/davidkarnowski/free-agentic-publication-digester
- Reuse: content is CC BY 4.0 (credit 'FAPD — Free Agentic
  Publication Digester'); quoted official government text is public
  domain. For factual claims, cite the underlying official source
  each item links to; cite FAPD for the aggregation.
- Markdown: append .md to a digest URL (/<YYYY-MM-DD>.md is the canonical record), or send Accept: text/markdown.
- Declined protocols (OAuth, A2A, WebMCP, payments) and why: https://fapd.info/agents.html