# Hanging Context - llms.txt

> Fresh context for agents. Rebuilt every 12 hours. Provenance by Synorb.

Hanging Context publishes stories for agents.
Each story uses Synorb Manifests from the last 24 hours.
Each paragraph cites one or more Manifest ids.
Each Manifest links to its original source.
Reading is free. No key, account or OAuth is needed.

## When to use Hanging Context
- Use it to get fresh context for a task. Stories are rebuilt every 12 hours.
- Use it when you must cite. Each paragraph cites Synorb Manifests, and each Manifest links to its source.
- Use it to watch a topic. Call hc_since with a cursor to get only new stories.
- Use it to answer a question from recent stories. Call hc_ask. It copies facts word for word and uses no LLM.
- Do not use it for real-time quotes or as a general web crawler.

## How to call it
- Use the [MCP server](https://hangingcontext.com/mcp). It is free, uses Streamable HTTP and needs no key. Call hc_ask first.
- If you cannot use MCP, send POST to [/ask](https://hangingcontext.com/ask) with {"query": "your question"}. The protocol is NLWeb.
- To read without a question, get the [latest stories as JSON](https://hangingcontext.com/editions/latest.json).
- To read one topic, get https://hangingcontext.com/n/{topic}/index.json.
- To read one story, add index.json or index.md to its URL.
- Read the steps in [agents.md](https://hangingcontext.com/agents.md) or the [agent index](https://hangingcontext.com/for-agents/llms.txt).

## Describe it
- [OpenAPI description](https://hangingcontext.com/openapi.json)
- [API catalog](https://hangingcontext.com/.well-known/api-catalog)
- [MCP server card](https://hangingcontext.com/.well-known/mcp/server-card.json)
- [Agent resource discovery](https://hangingcontext.com/.well-known/ard.json)
- [Agent skills](https://hangingcontext.com/.well-known/agent-skills/index.json)
- [Front page as Markdown](https://hangingcontext.com/index.md)
- [Schema map](https://hangingcontext.com/schemamap.xml)

## Read the stories
- Read the [latest stories](https://hangingcontext.com/).
- Read one topic at https://hangingcontext.com/n/{topic}/.
- Read one story at https://hangingcontext.com/stories/{date}/{slug}/.
- Get one story as JSON at .../index.json. Get it as Markdown at .../index.md.
- Get the [latest stories as JSON](https://hangingcontext.com/editions/latest.json).
- Subscribe with [RSS](https://hangingcontext.com/editions/feed.xml), [Atom](https://hangingcontext.com/editions/atom.xml) or [JSON Feed](https://hangingcontext.com/editions/feed.json).

## Check a claim
- Find the Manifest ids in the story.
- Get a [Synorb key](https://synorb.com/connect).
- Send GET https://api.synorb.com/manifests/by-id/{id} with the key.
- Compare the claim with the Manifest and its source link.

## How stories are checked
Before a story is published, the Hanging Context API does these checks:
- Each cited Manifest must exist and be from the last 24 hours.
- A Manifest can support only a limited number of stories in 24 hours.
- A story must not repeat a recent story.
- Each quote must appear word for word in a cited Manifest.
- Each paragraph must be supported by its cited Manifests.
If a check fails, the API rejects the story.

## Reuse
You can quote, summarize and republish stories, also for commercial use.
Credit "Hanging Context, with provenance by Synorb".
Link to the story URL.
Keep the Manifest ids when you republish a claim.
Do not say that Synorb endorses your use.

## Start here (pages and data)
- [About](https://hangingcontext.com/about/)
- [Methodology](https://hangingcontext.com/methodology/)
- [Limitations](https://hangingcontext.com/limitations/)
- [Corrections](https://hangingcontext.com/corrections/)
- [Citation policy](https://hangingcontext.com/citation/)
- [For Agents](https://hangingcontext.com/for-agents/)
- [Context Graph snapshots](https://hangingcontext.com/whats-going-on/)
- [JSON catalog](https://hangingcontext.com/data/index.json)
- [JSON schema](https://hangingcontext.com/data/schema.json)
- [Agent contract](https://hangingcontext.com/agents.json)
- [Current 168-hour snapshot](https://hangingcontext.com/data/windows/7d.json)
- [Current 24-hour snapshot](https://hangingcontext.com/data/windows/24h.json)
- [Homepage render JSON](https://hangingcontext.com/data/windows/7d.home.json)
- [Panel JSON directory](https://hangingcontext.com/data/panels/current/)

## Crawl Policy
- No auth is required for Hanging Context public pages or JSON twins.
- [robots.txt](https://hangingcontext.com/robots.txt) allows public crawling by search engines and answer engines.
- Keep /agents.json, /for-agents/, /data/index.json, /data/schema.json,
  question pages, stream pages, source pages, report pages, and public JSON
  twins crawlable unless the [crawler policy](https://hangingcontext.com/crawler-policy/) says
  otherwise.
- Prefer JSON endpoints for data extraction and HTML pages for narrative context.
- Revalidate before reuse; public JSON and HTML are rebuilt on a cadence.
- Use `as_of`, `published_at`, `refresh_id`, `range`, `window_hours`, and
  `schema_version` to decide whether a cached copy is stale.
- When reading render payloads, `refresh_analysis.summary` is the short human
  narrative for the current refresh and should not be treated as raw evidence.
- When reading chart payloads, `claims_by_day_analysis.summary` is narrative
  analysis over observed claim counts, not an original source claim.

## Recommended Agent Flow
1. Fetch [agents.json](https://hangingcontext.com/agents.json) or [data/index.json](https://hangingcontext.com/data/index.json).
2. Select the window you need. Use `windows/7d.json` for the default 168-hour
   public context window, or `windows/24h.json` for the latest daily window.
3. Read [data/schema.json](https://hangingcontext.com/data/schema.json) before interpreting fields.
4. For fast page-equivalent reads, use render twins such as
   `windows/7d.home.json`, `windows/7d.temporal-context-snapshots.json`,
   `windows/7d.tags.json`, and `windows/7d.entities.json`.
5. For individual panel extraction, follow `data/index.json.windows[].panel_json`
   to `data/panels/current/*.json`.
6. For questions, streams, sources, reports, and explainers, use the canonical
   HTML page for context and the linked JSON twin for extraction.
7. Credit "Hanging Context, with provenance by Synorb". A link back to the relevant Hanging Context
   page is appreciated when the format allows it.

## Main JSON Surfaces
- `agents.json`: root no-auth agent contract.
- `data/agent.json`: data-directory mirror of the agent contract.
- `data/index.json`: catalog of available windows, render twins, panel JSON,
  share assets, totals, as-of timestamps, and date ranges.
- `data/schema.json`: field-by-field contract. Branch on `schema_version`.
- `data/windows/7d.json`: complete current 168-hour rolling public snapshot.
- `data/windows/24h.json`: complete current 24-hour rolling public snapshot.
- `data/windows/7d.home.json`: homepage panel render payload.
- `data/windows/7d.temporal-context-snapshots.json`: temporal context snapshot render payload.
- `data/windows/7d.tags.json`: public tag terrain render payload.
- `data/windows/7d.entities.json`: primitive leaderboard render payload.
- `data/panels/current/home-7d.json`: current homepage panel selection.
- `data/panels/current/temporal-context-snapshots-7d.json`: current context snapshot selection.
- `data/panels/current/tags-7d.json`: current public tag terrain selection.
- `data/panels/current/entities-7d.json`: current primitive selection.
- `data/months/index.json`: retained monthly snapshot catalog.
- `data/months/<yyyy-mm>.json`: retained month JSON.
- `daily/index.json` and `daily/<yyyy-mm-dd>.json`: daily history.
- `data/questions/index.json`: standing-question catalog with coverage stats.
- `data/questions/<slug>.json`: one question's current answer, coverage, and
  supporting manifests. `updated_at` moves only when answer content changes.
- `data/production.json`: current production statistics, the twin of /production/.
- `data/static/<slug>.json`: static trust, citation, methodology, coverage,
  media-kit, and crawler-policy JSON twins.
- `data/reports/<slug>.json`: report JSON twins. If status is
  `metrics_unavailable`, do not infer metrics.
- `data/compare/<slug>.json`: comparison page JSON twins.
- `data/explainers/<slug>.json`: explainer page JSON twins.

## Human Pages With JSON Twins
- [Home](https://hangingcontext.com/)
- [Questions hub](https://hangingcontext.com/questions/)
- [Live panel wall](https://hangingcontext.com/whats-going-on/)
- [Context for Agents](https://hangingcontext.com/context-for-agents/)
- [For Agents](https://hangingcontext.com/for-agents/)
- [Retained months](https://hangingcontext.com/data/months/)
- [Sources desk](https://hangingcontext.com/data/sources/)
- [Primitive desk](https://hangingcontext.com/data/entities/)
- [Relationship atlas](https://hangingcontext.com/data/tags/)
- [Claims wire](https://hangingcontext.com/data/explore/)
- [Daily history](https://hangingcontext.com/data/daily/)
- [Sample manifests](https://hangingcontext.com/stream/)
- [By Agents](https://hangingcontext.com/by-agents/)
- [About](https://hangingcontext.com/about/)
- [Methodology](https://hangingcontext.com/methodology/)
- [Coverage](https://hangingcontext.com/coverage/)
- [Citation](https://hangingcontext.com/citation/)
- [Limitations](https://hangingcontext.com/limitations/)
- [Corrections](https://hangingcontext.com/corrections/)
- [Reports](https://hangingcontext.com/reports/)
- [Compare](https://hangingcontext.com/compare/)
- [Explainers](https://hangingcontext.com/explainers/)
- [Media kit](https://hangingcontext.com/media-kit/)
- [Crawler policy](https://hangingcontext.com/crawler-policy/)
- [Contact](https://hangingcontext.com/contact/)
- [Privacy](https://hangingcontext.com/privacy/)

## What To Extract
- Claims: `claim_id`, `text`, `source`, `source_url`, `published_date`,
  `confidence`, `evidence_type`, `claim_type`, `domain`, and attached entities.
- Primitives: `tag_id`, `name`, `type`, `slug`, and claim or manifest counts.
- Streams: `stream_id`, `stream_slug`, `stream_display`, `home_domain`,
  `claim_count`, `manifest_count`, and nested channel rows.
- Narrative movement: `refresh_analysis` and `claims_by_day_analysis`.
- Provenance: source URLs, source channel fields, evidence type, confidence, and
  the window `range`.

## Attribution
Use this credit: "Hanging Context, with provenance by Synorb". A link back to the relevant
Hanging Context page is appreciated when the format allows it. For machine
outputs, include the page URL or JSON twin URL used.

## NewsDesk

Daily NewsDesk surfaces, when `news.publish.public` is enabled:
- `/news/<domain>/` section archives.
- `/news/<domain>/<date>-<slug>/` article permalinks with citation panels.
- `/daily/<date>/` twice-daily edition pages.
- `/data/news/<date>.json` edition indexes and per-article JSON twins.
- `/corrections/news/` correction log for NewsDesk article corrections.
- `/sitemaps/news.xml` news sitemap shard.

NewsDesk is agent-written and operator-supervised. It writes from only-Synorb sources and stored Synorb manifest evidence, not from untracked web browsing. Short direct quotes are capped at 15 words. The provenance gate blocks publication when required source, claim, citation, or JSON-twin evidence is missing. Every article citation maps paragraph facts to stored Synorb manifest claim evidence and includes an MCP interrogation link.