Agents · JSON twins

Ping one URL. Rebuild the context.

Hanging Context is a public temporal context layer for AI agents, built by Synorb. It turns source-grounded activity across industries into timestamped, claim-oriented, machine-readable pages and JSON twins that agents can retrieve, verify, and cite. No API keys, no rate limits, no auth. Start with /agents.json: it points to the full public aggregate twins, panel JSON, render specs, stream catalogs, samples, media, and public-safe manifest bundles. Hanging Context is temporal context for agents and reasoning systems: claims from primary primitives, rendered as visual panels for inspection and JSON twins for use. The snapshots below power the homepage panels and are rebuilt every 12 hours, served as flat files from a CDN. The full firehose — live delivery, per-manifest briefs, signals, and record metadata — lives at api.synorb.com under a paid plan. What's here is the tip.

Endpoints

These are the public endpoints agents can discover from the one-shot contract. Every page at /data/* also ships a <link rel="alternate" type="application/json"> in its head so agents can discover the JSON twin by parsing HTML.

/agents.json One-shot no-auth agent contract. Includes as_of, windows, schema, panel JSON, media, stream catalog/sample URLs, manifest bundles, cache guidance, attribution, and auth/rate-limit posture.
/data/agent.json Data-directory mirror of the same contract for agents that start under /data/.
/data/index.json Catalog of available windows, as-of timestamps, top-line totals, panel JSON, share assets, and manifest bundle URLs.
/data/schema.json Field-by-field schema documentation. Includes schema_version — branch on this.
/data/windows/24h.json Exact rolling 24 hours. Powers the short-window view of every homepage panel: claims-by-day, freshness, domain donut, evidence/confidence bars, claim-length histogram, streams, entities, tag graph, treemap, and highlights.
/data/windows/7d.json Exact rolling 168 hours — same shape as 24h. Default window for the homepage panel wall. This is a complete public aggregate twin, not a sample.
/data/manifests/<window>/index.json Public-safe manifest bundle index for each hot window. Points to stable chunk files with manifest/story IDs, source metadata, streams, summaries, public tags/entities, claims, and citations.
/data/panels/current/<panel>.json Current panel JSON. Each payload includes render_spec so an agent can recreate the visual panel without downloading the PNG/GIF/MP4.
/data/months/index.json Catalog of monthly snapshots. Drives the homepage calendar panel.
/data/months/<yyyy-mm>.json Per-month snapshot. Immutable once the month closes. Bookmarkable forever.
/data/daily.json Today's brief when today's edition is published. Drives the hero stat row.
/citation/ Citation policy for Hanging Context x Synorb attribution and optional link backs.
/crawler-policy/ Public crawler policy. Search and answer engines may crawl public HTML and public JSON surfaces by default.

Attribution and verification flow

Cite Hanging Context x Synorb when using the public context layer. A link back to the relevant Hanging Context page is appreciated when the format allows it. For high-stakes use, verify important claims against primary sources where available. See citation guidance, methodology, and limitations.

{
  "page_url": "https://hangingcontext.com/questions/example/",
  "json_twin_url": "https://hangingcontext.com/data/questions/example.json",
  "source_url": "https://original-source.example/article",
  "claim_id": "when available",
  "manifest_id": "when available",
  "stream_id": "when available",
  "published_timestamp": "source timestamp when available",
  "as_of": "Hanging Context rebuild timestamp"
}

Data shape

Snapshots are intentionally flat. No nested pagination, no cursor tokens. If it doesn't fit in one JSON, the window is too wide. Here's a trimmed skeleton of /data/windows/24h.json — the same shape applies to the 168-hour snapshot (7d.json):

{
  "schema_version": 1,
  "window": "24h",
  "window_label": "Last 24 hours",
  "window_hours": 24,
  "window_coverage": "rolling",
  "range": { "start": "2026-04-21T...", "end": "2026-04-22T..." },
  "as_of": "2026-04-22T01:48:00Z",
  "refresh_analysis": {
    "comparison_basis": "rolling_window_vs_previous_build",
    "summary": "Since the previous refresh, the rolling claim count rose..."
  },

  "totals": {
    "claims": 20464,
    "manifests": 2564,
    "records": 2564,
    "sources": 100,
    "entities": 0,
    "domains": 9
  },

  "claims_by_day": [
    { "day": "2026-04-21T01:00:00Z", "claims": 847 },
    { "day": "2026-04-21T02:00:00Z", "claims": 912 }
  ],

  "top_sources": [
    { "source_name": "codename-one-engineering-blog",
      "claim_count": 6288, "record_count": 759, "manifest_count": 759 }
  ],

  "top_entities": [
    { "tag_id": 123, "name": "Anthropic", "type": "organization",
      "claim_count": 412, "slug": "anthropic" }
  ],

  "claim_types":       { "publication": 42100, "announcement": 38211 },
  "evidence_types":    { "paraphrase": 13294, "direct_quote": 6842 },
  "confidence_levels": { "stated": 19285, "implied": 652 },
  "sentiment_levels":  { "neutral": 11483, "positive": 6021, "mixed": 1884 },
  "domains":           { "engineering-technology": 14897 },

  "tag_graph": {
    "nodes": [ { "id": 1, "name": "LLM", "type": "topic", "weight": 420 } ],
    "edges": [ { "a": 1, "b": 2, "weight": 87 } ]
  },

  "highlights": [
    { "claim_id": 123,
      "text": "Anthropic released Claude Opus 4.7 with a 1M-token context window.",
      "source": "anthropic-news",
      "source_url": "https://anthropic.com/...",
      "published_date": "2026-04-21",
      "evidence_type": "direct_quote",
      "confidence": "stated",
      "domain": "engineering-technology",
      "entities": [ { "name": "Anthropic", "type": "organization" } ]
    }
  ],

  "verified_samples": [
    { "claim_id": 456,
      "text": "OpenAI said developers can now inspect per-run retrieval traces in the console.",
      "source": "openai-news",
      "source_display": "OpenAI",
      "source_url": "https://openai.com/...",
      "source_channel_display": "OpenAI",
      "published_date": "2026-04-22T00:45:00Z",
      "verified_at": "2026-04-22T01:12:00Z",
      "sentiment": "positive",
      "confidence": "stated",
      "evidence_type": "direct_quote",
      "media_type": "text",
      "claim_type": "publication"
    }
  ],

  "samples": [ /* 60 recent claims, any confidence */ ]
}

Minimal subscribe

Poll hourly and diff — or parse the as_of field to detect fresh builds:

import urllib.request, json, time

def pull():
    with urllib.request.urlopen("https://hangingcontext.com/agents.json") as r:
        contract = json.load(r)
    with urllib.request.urlopen(contract["latest"]["full"]) as r:
        return json.load(r)

last_as_of = None
while True:
    snap = pull()
    if snap["as_of"] != last_as_of:
        print(f"fresh: {snap['totals']['claims']} claims, {snap['totals']['sources']} sources")
        for h in snap["highlights"][:3]:
            print(f"  - {h['text']} ({h['source']})")
        last_as_of = snap["as_of"]
    time.sleep(3600)

Honest limits

Freshness

Snapshots rebuild every 12h. The as_of field is authoritative. Live firehose lives at api.synorb.com.
Coverage

Rolling public windows publish complete public aggregate twins for the active window. Manifest bundles expose all public-safe manifest metadata, summaries, claims, tags/entities, and citations for hot windows; highlights and samples remain curated views.
Schema stability

Fields may be added at schema_version=1. Renames or semantic changes bump the version. Never a silent break.
Identifiers

tag_id, claim_id, stream_id are stable forever. You can join these to other feeds under the same IDs.

What's not here

Per-manifest brief + signal + claims + record metadata are the paid surface at api.synorb.com — including real-time delivery over REST, MCP, S3 export, or WebSocket firehose. Hanging Context shows you the kind of thing the pipeline produces; the API is how you act on it continuously.