You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
Copy file name to clipboardExpand all lines: README.md
+28-14Lines changed: 28 additions & 14 deletions
Display the source diff
Display the rich diff
Original file line number
Diff line number
Diff line change
@@ -26,13 +26,13 @@ OpenKB has two layers: a **wiki foundation** that compiles and maintains your kn
26
26
27
27
### Features
28
28
29
-
-**Broad format support** — PDF, Word, Markdown, PowerPoint, HTML, Excel, CSV, text, URLs, and more
30
-
-**Scale to long documents** — Long and complex documents are handled via [PageIndex](https://github.com/VectifyAI/PageIndex) tree indexing, enabling accurate, vectorless context-aware retrieval
31
-
-**Native multi-modality** — Retrieves and understands figures, tables, and images, not just text
32
-
-**Compiled Wiki** — LLM compiles your documents into summaries, concept pages, entity pages, and cross-links, all kept in sync
33
-
-**Query & Chat** — One-off questions or multi-turn conversations over your wiki, with persisted sessions you can resume
34
-
-**Skill Factory** — Distill redistributable agent skills from your wiki
35
-
-**Obsidian compatible** — Wiki is plain `.md` files with `[[wikilinks]]`. Open in Obsidian for graph view and browsing
29
+
-**Broad format support:** PDF, Word, Markdown, PowerPoint, HTML, Excel, CSV, text, URLs, and more
30
+
-**Scale to long documents:** Long and complex documents are handled via [PageIndex](https://github.com/VectifyAI/PageIndex) tree indexing, enabling accurate, vectorless context-aware retrieval
31
+
-**Native multi-modality:** Retrieves and understands figures, tables, and images, not just text
32
+
-**Compiled Wiki:** LLM compiles your documents into summaries, concept pages, entity pages, and cross-links, all kept in sync
33
+
-**Query & Chat:** One-off questions or multi-turn conversations over your wiki, with persisted sessions you can resume
34
+
-**Skill Factory:** Distill redistributable agent skills from your wiki
35
+
-**Obsidian compatible:** Wiki is plain `.md` files with `[[wikilinks]]`. Open in Obsidian for graph view and browsing
| <code>openkb skill new <skill-name> "<intent>"</code> |Distill a redistributable agent skill from your wiki — see [Skill Factory](#-skill-factory--drop-in-a-book-out-comes-a-digital-expert) below |
@@ -221,19 +223,22 @@ Inside a chat, type `/` to access slash commands (Tab to complete).
221
223
222
224
<details>
223
225
<summary><i>Slash commands:</i></summary>
226
+
<br>
224
227
225
228
-`/help` — list available commands
226
229
-`/status` — show knowledge base status
227
230
-`/list` — list all documents
228
231
-`/add <path>` — add a document or directory without leaving the chat
229
-
-`/skill new <name> "<intent>"` — compile a skill from this chat (see below)
232
+
-`/skill new <skill-name> "<intent>"` — compile a skill from this chat (see below)
230
233
-`/save [name]` — export the transcript to `wiki/explorations/`
231
234
-`/clear` — start a fresh session (the current one stays on disk)
232
235
-`/lint` — run knowledge base lint
233
236
-`/exit` — exit (Ctrl-D also works)
234
237
235
238
</details>
236
239
240
+
<aid="skill-factory"></a>
241
+
237
242
### 🛠 Skill Factory — *Drop in a book; out comes a digital expert.*
238
243
239
244
The newest generator. `openkb skill new` distills an [agent skill](https://docs.claude.com/en/docs/build-with-claude/skills) from any subset of your wiki, a portable folder that major agents (Claude Code, Codex, etc.) install and load natively. Drop in a book's worth of papers; out comes a specialist that other agents can call on.
@@ -245,6 +250,7 @@ openkb skill new karpathy-thinking \
245
250
246
251
<details>
247
252
<summary><i>Output:</i></summary>
253
+
<br>
248
254
249
255
```
250
256
<kb>/output/skills/karpathy-thinking/
@@ -261,6 +267,7 @@ openkb skill new karpathy-thinking \
Compilation is one-shot, but follow-up edits aren't. Inside `openkb chat`, you can refine without re-running the whole pipeline:
286
295
@@ -295,6 +304,7 @@ Compilation is one-shot, but follow-up edits aren't. Inside `openkb chat`, you c
295
304
296
305
<details>
297
306
<summary><i>Quality gates:</i></summary>
307
+
<br>
298
308
299
309
Structural validation, trigger-accuracy + body-coverage evaluation, and full history/rollback:
300
310
@@ -335,6 +345,7 @@ Model names use `provider/model` LiteLLM [format](https://docs.litellm.ai/docs/p
335
345
336
346
<details>
337
347
<summary><i>Advanced options:</i></summary>
348
+
<br>
338
349
339
350
`entity_types` (optional): a YAML list overriding the entity-type vocabulary used for entity pages; omit it to use the default `person`, `organization`, `place`, `product`, `work`, `event`, `other`.
340
351
@@ -393,6 +404,7 @@ OpenKB ships a `SKILL.md` so any agent CLI can read your compiled wiki. No extra
393
404
394
405
<details>
395
406
<summary><i>Claude Code:</i></summary>
407
+
<br>
396
408
397
409
```
398
410
/plugin marketplace add VectifyAI/OpenKB
@@ -403,6 +415,7 @@ OpenKB ships a `SKILL.md` so any agent CLI can read your compiled wiki. No extra
0 commit comments