--- source_path: "agent-tools.md" canonical_url: "https://doc.sensory.com/tnl/7.8/agent-tools/" --- # Coding agents This site publishes a [machine-readable index](https://doc.sensory.com/tnl/7.8/llms.txt) and a [per-page Markdown mirror][llmstxt] designed for AI coding tools. For tools that follow the [`llms.txt`][llmstxt] convention, pointing your editor at the index is the only setup step; after that "how do I push audio?" / "add Sensory to my CMake build" / "enroll a UDT in Java" land on the right page without further configuration. Cursor indexes HTML rather than `llms.txt` and uses a different entry point (see its tab below). [llmstxt]: https://llmstxt.org/ ## Editor setup For tools that follow the [`llms.txt`][llmstxt] convention (Claude Code, Aider, Continue, Cline, and most RAG / programmatic ingestion clients), register [`https://doc.sensory.com/tnl/7.8/llms.txt`](https://doc.sensory.com/tnl/7.8/llms.txt) once and the rest of the bundle is reachable from there. Cursor needs a different entry point — see its tab below. Common editors: **Cursor** Cursor's **Settings → Indexing & Docs → Add Doc** is an HTML crawler scoped to the URL you give it: it follows `` links under that URL's path prefix and converts each page from HTML to Markdown. As of 2026 it does not parse the [`llms.txt`][llmstxt] link list as a crawl seed list ([feature request](https://forum.cursor.com/t/cursor-not-support-llms-txt-standard/108980)), so pasting `https://doc.sensory.com/tnl/7.8/llms.txt` will index that single file and stop — none of the linked SDK pages are reached, because they live as *siblings* of `llms.txt`, not under `llms.txt/`. Instead, register the **rendered HTML site root**: ```text https://doc.sensory.com/tnl/7.8/ ``` Give it a name (e.g. `Sensory TrulyNatural SDK`). Cursor will crawl the MkDocs navigation under `/tnl/7.9/` and index the SDK pages it can reach. Reference the doc set with `@Docs Sensory TrulyNatural SDK` in chat. If Cursor's crawler misses pages (a [reported limitation](https://forum.cursor.com/t/how-can-i-increase-the-indexing-depth-for-docs/77949) on larger doc sites), add [`https://doc.sensory.com/tnl/7.8/llms-full.txt`](https://doc.sensory.com/tnl/7.8/llms-full.txt) as a *second* doc with a distinct name (e.g. `Sensory TrulyNatural SDK (full Markdown)`). This is every page concatenated into one ~1.3 MiB file, which Cursor stores as a single searchable blob — coarser than per-page chunks, but a reliable way to guarantee full coverage. **Claude Code** Add the URL to a project-level `CLAUDE.md` so the agent reads the index on every session: ```markdown # Documentation - TrulyNatural SDK: https://doc.sensory.com/tnl/7.8/llms.txt Use this index to find SDK pages; prefer the linked `.md` URLs over general web search. ``` **Copilot Chat** Reference individual pages with `#fetch` (for example, `#fetch` on the [Inference](https://doc.sensory.com/tnl/7.8/api/inference.md#inference) page — see [`manifest.json`](https://doc.sensory.com/tnl/7.8/manifest.json) for per-page `.md` URLs). Copilot does not ingest a documentation index globally; the per-page `.md` URLs in this site's [`manifest.json`](https://doc.sensory.com/tnl/7.8/manifest.json) are the unit of context. **Aider / Cline** These tools accept Markdown URLs in their `--read` / `/add` / context commands. Point them at individual `.md` pages from `manifest.json` rather than the full bundle: each page is sized for a single chat turn, while [`llms-full.txt`](https://doc.sensory.com/tnl/7.8/llms-full.txt) is a single ~1.3 MiB file better suited to bulk offline indexing. **Other** Any tool that follows an AI-oriented documentation index typically accepts either an `llms.txt`-style entry point or a sitemap of Markdown URLs. The two relevant URLs are: - Index: [`https://doc.sensory.com/tnl/7.8/llms.txt`](https://doc.sensory.com/tnl/7.8/llms.txt) - Per-page mirror: each entry in [`manifest.json`](https://doc.sensory.com/tnl/7.8/manifest.json) carries a `path` (relative to the index) and a `canonical_url` (rendered HTML URL). Both `.md` and HTML serve identical content. ## What's in the bundle Three files share the same content rendered three ways: - [`llms.txt`](https://doc.sensory.com/tnl/7.8/llms.txt) — orientation index (~27 KiB). Curated **Common tasks** and **Start here** routes plus a section by path prefix. This is the file most tools want. - [`manifest.json`](https://doc.sensory.com/tnl/7.8/manifest.json) — a JSON index of every page with `path`, `bytes`, `title`, `canonical_url`, an optional `headings` outline on reference pages, an optional `last_modified` (ISO 8601 UTC) for incremental re-ingest, and a top-level `symbols` array (per-heading `bindings` for C/Java/Python). Useful for budgeting context size or programmatically picking pages. - [`llms-full.txt`](https://doc.sensory.com/tnl/7.8/llms-full.txt) — every Markdown page concatenated into one file (~1.3 MiB), with a `` header per page. Reserve this for bulk offline indexing; for day-to-day chat, fetch individual `.md` URLs instead so the model isn't carrying the whole SDK in its context window. ## Day-to-day usage tips - **Prefer per-page `.md` URLs over the full bundle.** Each rendered page also exists as a `.md` next to its HTML (e.g. [`api/inference.md`](https://doc.sensory.com/tnl/7.8/api/inference.md) beside the rendered [Inference](https://doc.sensory.com/tnl/7.8/api/inference.md#inference) page). Pasting one of these into a chat is usually enough context. - **Use `#fragment` URLs for narrow questions.** All H2/H3/H4 headings have stable anchors. For a question like "what does `snsrLoad` return?", paste the [Inference](https://doc.sensory.com/tnl/7.8/api/inference.md#inference) page with a `#load` fragment rather than the whole page. The `## Symbols` section of `llms.txt` lists every C/Java/Python entry point with its anchor for direct deep-linking. - **Use Common tasks for typical work.** The first section of `llms.txt` is curated to match natural-language prompts: "first program", "build integration", "push audio", "wake word then LVCSR or STT", "enroll a UDT in Java", and a dozen more. Most agent prompts will resolve through one of these routes. - **Re-pin the URL on each SDK upgrade.** This site publishes a per-version doc tree (`/tnl/7.9/`); when you move to a new SDK release, point your editor at the new version's index — `llms.txt` for tools that follow the convention, or the rendered HTML site root for Cursor. The [`/tnl/latest/`](/tnl/latest/llms.txt) alias always redirects to the most recent published version if you'd rather track HEAD. ## Programmatic ingestion If you're writing a tool, not registering URLs in an editor: ```python import json, urllib.request base = "https://doc.sensory.com/tnl/7.8/llms.txt".rsplit("/", 1)[0] with urllib.request.urlopen(f"{base}/manifest.json") as r: manifest = json.load(r) # manifest["version"] == 3; manifest["entries"] is a list of dicts. # manifest["symbols"] maps concept names to per-binding identifiers. for page in manifest["entries"]: if page["bytes"] < 8192: # small reference page with urllib.request.urlopen(f"{base}/{page['path']}") as r: text = r.read().decode("utf-8") # ingest `text` keyed on page["canonical_url"] ``` The `canonical_url` field is the most stable join key across the two representations: the same string identifies a page in the loose on-host mirror, in `manifest.json`, in `llms-full.txt`'s `` headers, and as a hyperlink target inside other pages. ## See also - The [`llms.txt` proposal][llmstxt] this site implements. - The [Coding agents callout](https://doc.sensory.com/tnl/7.8/index.md#home) on the home page. - The [changelog entry](https://doc.sensory.com/tnl/7.8/changes/index.md#v7.8.0) describing the bundle. *[API]: Application Programming Interface *[LVCSR]: Large Vocabulary Continuous Speech Recognition model, feed-forward neural net acoustic model with FST decoder *[SDK]: Software Development Kit *[STT]: Speech To Text: transformers with language model and CTC decoding *[TNL]: TrulyNatural, Sensory's large-vocabulary speech recognition technology *[UDT]: User-Defined Trigger: enrolled wake words and command sets