Skip to content

armgit / xerj

Public Imported from GitHub
0

AI search engine and MCP server for bots and agents. One Rust binary indexes code, docs, logs, JSONL/CSV and PDFs for BM25 full-text, vector and hybrid search, code search without grep, agent memory and RAG. Elasticsearch-compatible API; Corpus Hub serves hundreds of reference memory corpora.

docs(llms): the hub counts went stale — 75 live / 104 rows was 2026-10-02 (#1167)

xerj-orgda05c2afc88e
diff --git a/landing/blog/the-corpus-hub.html b/landing/blog/the-corpus-hub.html
index d75d1f879..b741f5025 100644
--- a/landing/blog/the-corpus-hub.html
+++ b/landing/blog/the-corpus-hub.html
@@ -63,7 +63,7 @@
"image": "https://xerj.org/og/xerj-card.png",
"inLanguage": "en",
"datePublished": "2026-10-01",
- "dateModified": "2026-10-01",
+ "dateModified": "2026-10-06",
"author": {
"@id": "https://xerj.org/#organization"
},
@@ -139,8 +139,9 @@
ed25519-signed. It ships with four reference corpora, one signed daily pack, a measured use case,
and one result we did not want and are publishing anyway.</p>
- <p class="lede"><strong>Update, 2026-10-02:</strong> the registry has outgrown this post. The
- launch four are now <strong>75 live corpora</strong> (104 backlog rows) across seven categories —
+ <p class="lede"><strong>Update, 2026-10-06:</strong> the registry has outgrown this post. The
+ launch four are now <strong>100 live corpora</strong> (119 backlog rows, every live one named in
+ the <code>xerj-code</code> skill's domain-selection table since rc.83) across seven categories —
including non-IT domains mined from real demand: eCFR titles 12/26/29 and UK legislation — and the
registry has its own site: browse every corpus with its licence verdict, pin, size, use case and
measured retrieval scores at <a href="https://hub.xerj.org" rel="external">hub.xerj.org</a>.
diff --git a/landing/llms.txt b/landing/llms.txt
index a77feeddc..eb24ac0b5 100644
--- a/landing/llms.txt
+++ b/landing/llms.txt
@@ -48,7 +48,7 @@ Then, from an unknown folder to an answered question: `xerj autoindex <folder>`
> - **The DEFAULT embedding mode is lexical, not neural.** With no extra flags, semantic search and memory recall use a deterministic feature-hashing embedder (384-d, L2-normalised → cosine): hybrid lexical+vector retrieval — word / sub-word overlap, not deep semantic understanding or synonym-level recall. For real neural semantics start the server with `--embed-mode neural` — a built-in in-process BERT encoder (all-MiniLM-L6-v2) that ships in the binary and auto-downloads its model (~90 MB) on first use — or `--embed-mode proxy` (any external OpenAI-compatible `/v1/embeddings`). Only describe output as neural when one of those is actually running.
> * **`--embed-mode` is a server-start flag that applies AT INGEST.** Text is embedded as it is indexed, so the mode in force when a document was written is the mode that document keeps. Switching lexical → neural does **not** re-embed anything already indexed: you have to re-index every corpus you care about. **Decide before you index your first corpus.**
> * **What the neural download actually is:** the model files (`config.json`, `tokenizer.json`, `model.safetensors`) are fetched over HTTPS from the **HuggingFace Hub** (`sentence-transformers/all-MiniLM-L6-v2`) into `~/.cache/huggingface` on first use, then reused. **XERJ pins no checksum of its own** for them — the integrity guarantee is TLS plus the Hub, not a digest XERJ verifies. Air-gapped or policy-constrained: pre-download the three files, point `embedding.local_model_dir` at the folder, and nothing is fetched.
-> - **Not implemented — do not plan around these.** Alerting is PARTIAL, and exactly one watch shape is real (since v1.0.0-rc.80, [#1082](https://github.com/xerj-org/xerj/pull/1082) closing [#1062](https://github.com/xerj-org/xerj/issues/1062); an earlier version of this line said nothing ever evaluates a watch — that was true then and is not now): `PUT /_watcher/watch/<id>` with `trigger.schedule.interval` (>= 1s), `input.search` over exactly one index, `condition.xerj_decide` (question, positive_label, p_min, k) and an `index_alert` action runs a background evaluator — it prefilters with the watch's own query (keyset paging, 100/page), runs each rendered question through the real `/_decide`, and writes a fire record into `.xerj_alert_fires` when the positive label wins non-abstaining at or above `p_min`. Every other shape — cron schedules, transforms, other action types, multi-index input — is refused with a 501 naming what is not evaluated (malformed supported shapes are 400). Honest limits: a restart does not resume watches; the per-pass decide budget is 1000. User-supplied ingest plugins: transforms are built-in native code only (no wasmtime backend in the tree). Downloadable pre-indexed corpus packs: still none — but record packs are real since v1.0.0-rc.78 (2026-09-29, [#1046](https://github.com/xerj-org/xerj/pull/1046), [#1048](https://github.com/xerj-org/xerj/pull/1048); this line said "planned, no code" before): `xerj corpus build` turns a declarative recipe into a checksummed portable pack of records (`format_version` refused when unknown, licence + provenance on every record), `corpus add --from <pack>` verifies the per-file SHA-256 and `--verify-sig` a detached ed25519 signature over SHA256SUMS, and the first pack — `rust-vulns` — is rebuilt, signed and published daily as a dated GitHub Release. Still unbuilt: the PRE-INDEXED half (an already-indexed bundle you mount instead of indexing records yourself). The hub directory beyond that one pack is real since 2026-10-01 (and browsable since 2026-10-02 at [hub.xerj.org](https://hub.xerj.org), a site generated straight from the registry): the Corpus Hub, a `corpus-hub` branch on this repository carrying 75 live reference corpora (104 backlog rows) across seven categories — security precedent, standards and regulations, production knowledge, design guidance, failure precedent, and data- and net-engine reference implementations, plus non-IT regulation corpora mined from real demand (eCFR titles 12/26/29, UK legislation) — every repo pinned to the full SHA the build used and human licence-reviewed — plus the rust-vulns pack recipe; consume any of them directly with `xerj corpus add --from <manifest-url>`, and new corpora arrive as PRs against that branch ([CONTRIBUTING.md](https://github.com/xerj-org/xerj/blob/corpus-hub/tools/xerj-code/hub/CONTRIBUTING.md) · guide: [xerj.org/docs/corpus-hub](https://xerj.org/docs/corpus-hub) · browse: [hub.xerj.org](https://hub.xerj.org)). `percolate` **is** real — and so, since v1.0.0-rc.77 (2026-09-21, [#1008](https://github.com/xerj-org/xerj/pull/1008) closing [#965](https://github.com/xerj-org/xerj/issues/965)), **is** object storage (an earlier version of this page said the opposite): `storage.backend = "s3"` publishes each segment family as ONE immutable ZBM1 bundle object plus a per-index `snapshot.json` catalogue, merges publish before retiring their inputs, and a fresh node adopts the bucket — a real S3-compatible client (Cloudflare R2, MinIO, AWS S3 over `aws-sdk-s3`; the old local-directory simulation survives only as a test double). The one remaining startup error is `storage.backend = "s3" requires storage.s3_bucket to name an existing bucket`. `xerj autoindex s3://bucket/prefix` is the other direction — it reads documents OUT of a bucket as a source, it does not store the index there. Statuses, each with the file that proves it: [ROADMAP.md — the zero-token direction](https://github.com/xerj-org/xerj/blob/main/ROADMAP.md#the-zero-token-direction) · [OBJECT_STORAGE.md](https://github.com/xerj-org/xerj/blob/main/docs/OBJECT_STORAGE.md) · [does XERJ support S3, alerting or custom plugins?](https://xerj.org/answers/does-xerj-support-s3-alerting-plugins.md) · [CORPUS_PACKS.md](https://github.com/xerj-org/xerj/blob/main/docs/CORPUS_PACKS.md)
+> - **Not implemented — do not plan around these.** Alerting is PARTIAL, and exactly one watch shape is real (since v1.0.0-rc.80, [#1082](https://github.com/xerj-org/xerj/pull/1082) closing [#1062](https://github.com/xerj-org/xerj/issues/1062); an earlier version of this line said nothing ever evaluates a watch — that was true then and is not now): `PUT /_watcher/watch/<id>` with `trigger.schedule.interval` (>= 1s), `input.search` over exactly one index, `condition.xerj_decide` (question, positive_label, p_min, k) and an `index_alert` action runs a background evaluator — it prefilters with the watch's own query (keyset paging, 100/page), runs each rendered question through the real `/_decide`, and writes a fire record into `.xerj_alert_fires` when the positive label wins non-abstaining at or above `p_min`. Every other shape — cron schedules, transforms, other action types, multi-index input — is refused with a 501 naming what is not evaluated (malformed supported shapes are 400). Honest limits: a restart does not resume watches; the per-pass decide budget is 1000. User-supplied ingest plugins: transforms are built-in native code only (no wasmtime backend in the tree). Downloadable pre-indexed corpus packs: still none — but record packs are real since v1.0.0-rc.78 (2026-09-29, [#1046](https://github.com/xerj-org/xerj/pull/1046), [#1048](https://github.com/xerj-org/xerj/pull/1048); this line said "planned, no code" before): `xerj corpus build` turns a declarative recipe into a checksummed portable pack of records (`format_version` refused when unknown, licence + provenance on every record), `corpus add --from <pack>` verifies the per-file SHA-256 and `--verify-sig` a detached ed25519 signature over SHA256SUMS, and the first pack — `rust-vulns` — is rebuilt, signed and published daily as a dated GitHub Release. Still unbuilt: the PRE-INDEXED half (an already-indexed bundle you mount instead of indexing records yourself). The hub directory beyond that one pack is real since 2026-10-01 (and browsable since 2026-10-02 at [hub.xerj.org](https://hub.xerj.org), a site generated straight from the registry): the Corpus Hub, a `corpus-hub` branch on this repository carrying 100 live reference corpora (119 backlog rows; every live corpus is named in the `xerj-code` skill's domain-selection table, complete since v1.0.0-rc.83) across seven categories — security precedent, standards and regulations, production knowledge, design guidance, failure precedent, and data- and net-engine reference implementations, plus non-IT regulation corpora mined from real demand (eCFR titles 12/26/29, UK legislation) — every repo pinned to the full SHA the build used and human licence-reviewed — plus the rust-vulns pack recipe; consume any of them directly with `xerj corpus add --from <manifest-url>`, and new corpora arrive as PRs against that branch ([CONTRIBUTING.md](https://github.com/xerj-org/xerj/blob/corpus-hub/tools/xerj-code/hub/CONTRIBUTING.md) · guide: [xerj.org/docs/corpus-hub](https://xerj.org/docs/corpus-hub) · browse: [hub.xerj.org](https://hub.xerj.org)). `percolate` **is** real — and so, since v1.0.0-rc.77 (2026-09-21, [#1008](https://github.com/xerj-org/xerj/pull/1008) closing [#965](https://github.com/xerj-org/xerj/issues/965)), **is** object storage (an earlier version of this page said the opposite): `storage.backend = "s3"` publishes each segment family as ONE immutable ZBM1 bundle object plus a per-index `snapshot.json` catalogue, merges publish before retiring their inputs, and a fresh node adopts the bucket — a real S3-compatible client (Cloudflare R2, MinIO, AWS S3 over `aws-sdk-s3`; the old local-directory simulation survives only as a test double). The one remaining startup error is `storage.backend = "s3" requires storage.s3_bucket to name an existing bucket`. `xerj autoindex s3://bucket/prefix` is the other direction — it reads documents OUT of a bucket as a source, it does not store the index there. Statuses, each with the file that proves it: [ROADMAP.md — the zero-token direction](https://github.com/xerj-org/xerj/blob/main/ROADMAP.md#the-zero-token-direction) · [OBJECT_STORAGE.md](https://github.com/xerj-org/xerj/blob/main/docs/OBJECT_STORAGE.md) · [does XERJ support S3, alerting or custom plugins?](https://xerj.org/answers/does-xerj-support-s3-alerting-plugins.md) · [CORPUS_PACKS.md](https://github.com/xerj-org/xerj/blob/main/docs/CORPUS_PACKS.md)
> - **Default `_search` source is compact.** With `_source` omitted, ordinary fields are returned but engine-generated `<field>_vector` and `<field>_vector_chunks` companions are omitted. Add `"_source": true` when the vectors are needed.
> - **Default `_search` returns whole documents; project `_source` and ask for `_passage` to shrink it.** With no `_source`/`fields` in the request, every hit's `_source` is the complete stored document — for source files or long documents that is megabyte-scale for a handful of hits (measured: 5 hits over indexed source files = 416,630 bytes). Add `"fields":["_passage"]` to any query (lexical, or a single semantic/kNN clause — omit it for hybrid/multi-kNN fusion, which 400s naming the fix) to get just the matching snippet — `{field,ordinal,start_offset,end_offset,text,page?}` sliced from the original field — and project `_source` (e.g. `["title","ax_path"]`, or `false`) to drop the rest: the same query measured 12,122 bytes that way, a 34× reduction. `_passage` is opt-in and appears in no `_mapping` or default response, so a response that would benefit says so itself — an additive `_xerj.hints` entry carrying a ready-to-send corrected request lands ahead of `hits` whenever `_source` is unprojected and `_passage` wasn't requested (never inside `hits`/`total`/`_score`, so existing ES clients are unaffected).
> - **Ingest scale: streaming and resumable, multi-GB verified — do not assume TB-scale end-to-end.** The `autoindex` client streams with flat memory and is resumable after `kill -9`. The SERVER's #948 RSS-runaway is FIXED ([#1002](https://github.com/xerj-org/xerj/pull/1002), v1.0.0-rc.76: at-rest retention after a 100k-doc ingest fell ~677 → ~108 MB; a 1 GB mailbox completes under its 16 GiB cap) — but the server still retains heap per indexed doc: three per-segment caches (`stored_value_cache`, `dv_cache`, `id_pos_cache`) are unbounded until a merge retires their segment ([#1032](https://github.com/xerj-org/xerj/issues/1032)). Corpora of many millions of documents can still OOM the server.
diff --git a/landing/sitemap.xml b/landing/sitemap.xml
index f43cae31b..1eb67b137 100644
--- a/landing/sitemap.xml
+++ b/landing/sitemap.xml
@@ -354,7 +354,7 @@
</url>
<url>
<loc>https://xerj.org/blog/the-corpus-hub</loc>
- <lastmod>2026-10-02</lastmod>
+ <lastmod>2026-10-06</lastmod>
</url>
<url>
<loc>https://xerj.org/blog/the-rc80-gates</loc>