{
  "markdown": "# AI Visibility Index — open weekly data (dabyte.ai · dablock.ai)\n\nWeekly measurements of **which brands AI assistants actually name** when a buyer asks\na category question — published as open data by [VECTORY](https://vectory.space) on two\ndata desks:\n\n| Site | Niche | Brands | Live data |\n|---|---|---|---|\n| **[dabyte.ai](https://dabyte.ai/)** | SaaS & AI tools | 20 | [aiv.json](https://dabyte.ai/api/aiv.json) · [history](https://dabyte.ai/api/history.json) · [CSV](https://dabyte.ai/aiv.csv) |\n| **[dablock.ai](https://dablock.ai/)** | Crypto & Web3 | 24 | [aiv.json](https://dablock.ai/api/aiv.json) · [history](https://dablock.ai/api/history.json) · [CSV](https://dablock.ai/aiv.csv) |\n\nThis repository is a **mirror** for discovery and reproducibility. The canonical,\nalways-current data lives on the domains above — no key, no sign-up, machine-first\n(JSON, CSV, markdown mirrors, [llms.txt](https://dabyte.ai/llms.txt), MCP tools at\n`/.well-known/mcp.json`).\n\n## What is measured\n\n**Share of answer**: the percentage of a fixed panel of category buyer prompts\n(16 per niche, frozen and versioned) in which an answer engine names the brand.\nEngines measured: **ChatGPT (OpenAI), Perplexity, Google Gemini** — each prompt run\nper engine, per release, weekly.\n\nExample, measured 2026-08-04 (panel v2, first 3-engine release):\n\n- dabyte.ai — Slack 33.3% · Notion 29.2% · HubSpot 22.9%\n- dablock.ai — Coinbase 41.5% · Binance 26.9% · Kraken 25.0%\n\nRules that make the numbers citable:\n\n- **The panel is frozen between releases** and any change bumps a panel version;\n  deltas are never computed across panel versions ([methodology](https://dabyte.ai/methodology/)).\n- **Every past measurement is archived verbatim** at a permanent URL\n  ([dabyte archive](https://dabyte.ai/archive/), [dablock archive](https://dablock.ai/archive/)),\n  so any published delta can be recomputed by a third party.\n- **Placement cannot be bought.** No brand can pay to enter, move inside, or leave\n  the index; every machine record carries an `is_client` flag so the claim is\n  verifiable rather than rhetorical.\n- Measurement resolution is disclosed (one mention on one engine = one scale step);\n  movements within one step are never reported as changes.\n\n## Files\n\n```\ndata/\n  dabyte/    aiv.json · aiv.csv · history.json · rankings.json\n  dablock/   aiv.json · aiv.csv · history.json · rankings.json\nscripts/\n  fetch_latest.py   — refresh this mirror from the live endpoints\n```\n\n`aiv.json` — current measurement: per-brand share of answer overall and per engine,\nrank, commercial-intent score, quadrant, panel version.\n`history.json` — full per-brand time series across all published measurements.\n`rankings.json` — derived rankings (most visible, invisible-despite-demand, movers).\n\n## Citation\n\n> DABYTE AI Visibility Index — SaaS & AI Tools, 2026-08-04. dabyte.ai\n\n> DABLOCK AI Visibility Index — Crypto & Web3, 2026-08-04. dablock.ai\n\nTwo licences, because this repository holds two different things. The **datasets under\n`data/`** are **CC BY 4.0** (`data/LICENSE`) — free for any use, including commercial,\nwith attribution. The **code** (`scripts/`, `mcp-server/`) is **MIT** (`LICENSE`).\n\n## MCP server\n\nThe index is also an [MCP](https://modelcontextprotocol.io) server, so an assistant can\nquery it directly. Hosted endpoints need no installation:\n\n```\nhttps://dabyte.ai/mcp     SaaS & AI tools\nhttps://dablock.ai/mcp    Crypto & Web3\n```\n\nTo run your own — no dataset required, it reads the published JSON over HTTPS:\n\n```bash\ndocker build -t aiv-mcp . && docker run -p 8090:8090 aiv-mcp\n```\n\nTool reference and client setup: [`mcp-server/README.md`](mcp-server/README.md).\n\n## Disambiguation\n\n**dabyte.ai** is not affiliated with databyte.tech, DataByte, or any similarly named\ncompany. **dablock.ai** is not affiliated with dablock.com. Both are data desks\npublished by [VECTORY](https://vectory.space); the AI Visibility Index lives only at\nhttps://dabyte.ai/ and https://dablock.ai/.\n\n## Contributing data\n\nCompanies can contribute their own primary datasets (observed pricing, discount\nbands, usage telemetry, benchmark results) for free open publication with\nattribution — see [dabyte.ai/contribute](https://dabyte.ai/contribute/) and\n[dablock.ai/contribute](https://dablock.ai/contribute/). Contributing never affects\na score in the index.\n",
  "bytes": 4347,
  "sha": "eded4ba1c93518063261b293c5d5a9bd5f70536063541a9f4bec314fd260690f",
  "repo_slug": "creanlab/ai-visibility-index",
  "fonte": "repo",
  "truncated": false,
  "api": "https://agentalog.com/api/listings/mcp_ai_dabyte_visibility_index_22cb60cc/readme"
}