mirrors/hermes-agent
1
0
Fork 0
mirror of https://github.com/NousResearch/hermes-agent.git synced 2026-05-03 02:11:48 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions 5

docs: publish llms.txt and llms-full.txt for agent-friendly ingestion (#18276)

Browse source 
Two machine-readable entry points to the Hermes Agent docs:

  /llms.txt         curated index of every doc page, one link per page
                    with short descriptions. ~17 KB, safe to load into
                    an LLM context window.
  /llms-full.txt    every page under website/docs/ concatenated as markdown.
                    ~1.8 MB. For one-shot ingestion by coding agents and
                    RAG pipelines.

Both files are also served from /docs/llms.txt and /docs/llms-full.txt
(Docusaurus serves website/static/ under baseUrl=/docs/). Some agents and
IDE plugins probe the classic site-root path; the deploy workflow now copies
both files to _site root so either URL works.

Conforms to the emerging llmstxt.org spec: H1 project name, blockquote
summary, short install command, GitHub link, then curated sections
mirroring the docs-site navigation (Getting Started, Using Hermes,
Features, Messaging, Integrations, Guides, Developer Guide, Reference).

Generated by website/scripts/generate-llms-txt.py. Wired into prebuild.mjs
so every 'npm run build' and 'npm run start' refreshes the files alongside
the existing skills.json extraction. Both outputs are gitignored (same
precedent as src/data/skills.json).

Descriptions in llms.txt are pulled from each page's frontmatter, so they
stay current automatically. All ~80 section slugs are validated against
the filesystem at generation time; an invalid slug would fail the prebuild.
This commit is contained in:
Teknium 2026-04-30 23:17:14 -07:00 • committed by GitHub
parent cf2b2d31ce
commit c6eebfc25a
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
5 changed files with 367 additions and 22 deletions
Download patch file Download diff file Expand all files Collapse all files

64
website/scripts/prebuild.mjs
View file

@ -1,14 +1,18 @@
#!/usr/bin/env node
// Runs website/scripts/extract-skills.py before docusaurus build/start so
// that website/src/data/skills.json (imported by src/pages/skills/index.tsx)
// exists without contributors needing to remember to run the Python script
// manually. CI workflows still run the extraction explicitly, which is a
// no-op duplicate but matches their historical behaviour.
// Runs website/scripts/extract-skills.py and generate-llms-txt.py before
// docusaurus build/start so that:
// - website/src/data/skills.json (imported by src/pages/skills/index.tsx)
// - website/static/llms.txt (agent-friendly short docs index)
// - website/static/llms-full.txt (full docs concat for LLM context)
// all exist without contributors remembering to run Python scripts manually.
// CI workflows still run the extraction explicitly, which is a no-op duplicate
// but matches their historical behaviour.
//
// If python3 or its deps (pyyaml) aren't available on the local machine, we
// fall back to writing an empty skills.json so `npm run build` still
// succeeds — the Skills Hub page just shows an empty state. CI always has
// the deps installed, so production deploys get real data.
// succeeds — the Skills Hub page just shows an empty state, and llms.txt
// generation is skipped. CI always has the deps installed, so production
// deploys get real data.
import { spawnSync } from "node:child_process";
import { mkdirSync, writeFileSync, existsSync } from "node:fs";
@ -18,6 +22,7 @@ import { fileURLToPath } from "node:url";
const scriptDir = dirname(fileURLToPath(import.meta.url));
const websiteDir = resolve(scriptDir, "..");
const extractScript = join(scriptDir, "extract-skills.py");
const llmsScript = join(scriptDir, "generate-llms-txt.py");
const outputFile = join(websiteDir, "src", "data", "skills.json");
function writeEmptyFallback(reason) {
@ -29,22 +34,37 @@ function writeEmptyFallback(reason) {
);
}
function runPython(script, label) {
if (!existsSync(script)) {
console.warn(`[prebuild] ${label} skipped (script missing)`);
return false;
}
const r = spawnSync("python3", [script], { stdio: "inherit", cwd: websiteDir });
if (r.error && r.error.code === "ENOENT") {
console.warn(`[prebuild] ${label} skipped (python3 not found)`);
return false;
}
if (r.status !== 0) {
console.warn(`[prebuild] ${label} exited with status ${r.status}`);
return false;
}
return true;
}
// 1) skills.json — required for the Skills Hub page.
if (!existsSync(extractScript)) {
writeEmptyFallback("extract script missing");
process.exit(0);
} else {
const r = spawnSync("python3", [extractScript], {
stdio: "inherit",
cwd: websiteDir,
});
if (r.error && r.error.code === "ENOENT") {
writeEmptyFallback("python3 not found");
} else if (r.status !== 0) {
writeEmptyFallback(`extract-skills.py exited with status ${r.status}`);
}
}
const result = spawnSync("python3", [extractScript], {
stdio: "inherit",
cwd: websiteDir,
});
if (result.error && result.error.code === "ENOENT") {
writeEmptyFallback("python3 not found");
process.exit(0);
}
if (result.status !== 0) {
writeEmptyFallback(`extract-skills.py exited with status ${result.status}`);
process.exit(0);
}
// 2) llms.txt + llms-full.txt — agent-friendly docs entrypoints. Non-fatal.
runPython(llmsScript, "generate-llms-txt.py");