Skip to content
Back to search

OpenKB

OpenKB: Open LLM Knowledge Base

Safety scan

A static text scan, not a guarantee. Select the badge to see what was scanned and every finding.

Checked today
Badge for your README
findsafeskills safety rating

Markdown

[![findsafeskills safety rating](/api/listings/vectifyai--openkb/badge.svg)](/listings/vectifyai--openkb)

HTML

<a href="/listings/vectifyai--openkb"><img src="/api/listings/vectifyai--openkb/badge.svg" alt="findsafeskills safety rating" /></a>

Install

i

Install instructions from the README

As written by the repo's author. findsafeskills has not verified these steps.

Install

pip install openkb

<details> <summary><b><i>Other install options:</i></b></summary>

- **Latest from GitHub:**

  pip install git+https://github.com/VectifyAI/OpenKB.git

- **Install from source** (editable, for development):

  git clone https://github.com/VectifyAI/OpenKB.git
  cd OpenKB
  pip install -e .

</details>

Quick Start

# 1. Create a directory for your knowledge base
mkdir my-kb && cd my-kb

# 2. Initialize the knowledge base
openkb init

# 3. Add documents
openkb add paper.pdf
openkb add ~/papers/                            # Add a whole directory
openkb add https://arxiv.org/pdf/2509.11420     # Or fetch from a URL

# 4. Ask a question
openkb query "What are the main findings?"

# 5. Or chat interactively
openkb chat

# (Optional) Turn the wiki into other outputs
openkb skill new my-expert "Reason like an expert on <your-topic>"   # a portable agent skill
openkb visualize                                                     # an interactive knowledge graph
openkb deck new my-deck "An intro deck on <your-topic>"              # slides — a single-file HTML deck

Set up your LLM

OpenKB supports [multiple LLM providers](https://docs.litellm.ai/docs/providers) (OpenAI, Claude, Gemini, etc.) via [LiteLLM](https://github.com/BerriAI/litellm) (pinned to a [safe version](https://docs.litellm.ai/blog/security-update-march-2026)).

Set your model during `openkb init` or in [`.openkb/config.yaml`](#configuration) using the `provider/model` LiteLLM format (e.g. `anthropic/claude-sonnet-4-6`). OpenAI models can omit the prefix (e.g. `gpt-5.4`).

Create a `.env` file with your LLM API key:

LLM_API_KEY=your_llm_api_key

Subscription-based providers that authenticate via OAuth device flow (e.g. `chatgpt/*`, `github_copilot/*`) need no API key; OpenKB skips the missing-key warning for them.

Knowledge Workbench (Web UI)

OpenKB ships a bundled web UI, served by the REST API at `/`. Install the API extra and start the server — no configuration needed:

pip install "openkb[web]"
openkb-web                       # serves the API + Workbench at http://127.0.0.1:7566/

Open `http://127.0.0.1:7566/` for the Workbench. Auth is off by default (local-first); set `OPENKB_API_TOKEN` to require a bearer token before exposing the server. See the [full Web UI guide](examples/rest-api/README.md#knowledge-workbench-web-ui).

> Working on the UI itself? Run the Vite dev server with `cd frontend && npm install && npm run dev` (it proxies `/api` to a running `openkb-web`), or `npm run build` to regenerate the bundled `openkb/web/`.

What was scanned

The files the safety scan read, as written by the repository's author and shown as plain text. Lines with a finding are marked.

.claude-plugin/marketplace.json · Manifest · 31 lines

View this file on GitHub (read at the repository's current version: the scan did not record which commit it read)

  1. {
  2. "name": "vectify",
  3. "owner": {
  4. "name": "Ray",
  5. "email": "ray@vectify.ai"
  6. },
  7. "metadata": {
  8. "description": "Skills for navigating an OpenKB-compiled knowledge base from agent CLIs (Claude Code, Codex, Gemini CLI).",
  9. "version": "0.3.0"
  10. },
  11. "plugins": [
  12. {
  13. "name": "openkb",
  14. "description": "Navigate an OpenKB-compiled wiki: discover documents and concepts via openkb CLI commands, read concept and summary pages directly, and follow wikilinks across the knowledge graph.",
  15. "source": "./",
  16. "strict": false,
  17. "version": "0.3.0",
  18. "author": {
  19. "name": "Ray",
  20. "email": "ray@vectify.ai"
  21. },
  22. "homepage": "https://github.com/VectifyAI/OpenKB",
  23. "repository": "https://github.com/VectifyAI/OpenKB",
  24. "license": "Apache-2.0",
  25. "keywords": ["knowledge-base", "wiki", "openkb", "rag", "agent-skill"],
  26. "skills": [
  27. "./skills/openkb"
  28. ]
  29. }
  30. ]
  31. }
README.md · README · 406 lines

View this file on GitHub (read at the repository's current version: the scan did not record which commit it read)

  1. <div align="center">
  2. <a href="https://openkb.ai">
  3. <img src="https://docs.pageindex.ai/images/openkb.png" alt="OpenKB (by PageIndex)" />
  4. </a>
  5. <br />
  6. <br />
  7. <p align="center">
  8. <a href="https://trendshift.io/repositories/26145" target="_blank"><img src="https://trendshift.io/api/badge/repositories/26145" alt="VectifyAI%2FOpenKB | Trendshift" style="width: 250px; height: 55px;" width="250" height="55"/></a>
  9. </p>
  10. # OpenKB: Open LLM Knowledge Base
  11. <p align="center"><i>Scale to long documents • Reasoning-based retrieval • Native multi-modality • No Vector DB</i></p>
  12. </div>
  13. <details open>
  14. <summary><h2>📢 Recent Updates</h2></summary>
  15. - *Google Open Knowledge Format (OKF)*: Wiki pages follow the [Google OKF](https://cloud.google.com/blog/products/data-analytics/how-the-open-knowledge-format-can-improve-data-sharing) specification for knowledge sharing.
  16. - *Entity Pages*: People, orgs, places, and products as dedicated wiki pages, auto-extracted and kept in sync.
  17. </details>
  18. ---
  19. # 📑 What is OpenKB
  20. **OpenKB (Open Knowledge Base)** is an open-source system (in CLI) that compiles raw documents into a structured, interlinked wiki-style knowledge base using LLMs, powered by [**PageIndex**](https://github.com/VectifyAI/PageIndex)'s vectorless, reasoning-based retrieval for long documents.
  21. The idea is based on a [concept](https://x.com/karpathy/status/2039805659525644595) described by Andrej Karpathy: LLMs generate summaries, concept pages, and cross-references, all maintained automatically. Knowledge compounds over time instead of being re-derived on every query.
  22. ### Why not traditional RAG?
  23. Traditional RAG rediscovers knowledge from scratch on every query. Nothing accumulates. OpenKB compiles knowledge once into a persistent wiki, then keeps it current. Cross-references already exist, contradictions are flagged, and synthesis reflects everything consumed.
  24. OpenKB has two layers: a **wiki foundation** that compiles and maintains your knowledge, and **generators** (query / chat / Skill Factory) that turn it into useful output. See [Usage](#️-usage) for the full command list.
  25. ### Features
  26. - **Broad format support:** PDF, Word, Markdown, PowerPoint, HTML, Excel, CSV, text, URLs, and more.
  27. - **Scales to long documents:** Long and complex documents are handled via [PageIndex](https://github.com/VectifyAI/PageIndex) tree indexing, enabling accurate, vectorless, context-aware retrieval.
  28. - **Native multi-modality:** Retrieves and understands figures, tables, and images, not just text.
  29. - **Compiled wiki:** The LLM compiles your documents into summaries, concept pages, entity pages, and cross-links, all kept in sync.
  30. - **Query & chat:** One-off questions or multi-turn conversations over your wiki, with persisted sessions to resume.
  31. - **Skill Factory:** Distills redistributable agent skills from your wiki.
  32. - **OKF-ready:** Wiki pages follow the [Google OKF](https://cloud.google.com/blog/products/data-analytics/how-the-open-knowledge-format-can-improve-data-sharing) specification for knowledge sharing.
  33. - **Obsidian-compatible:** The wiki is plain `.md` files with cross-links. Opens in Obsidian for graph view.
  34. - **Knowledge Workbench (Web UI):** A bundled web UI served at `/` to browse the KB, upload and compile documents, and stream queries and chats — all in the browser.
  35. # 🚀 Getting Started
  36. ### Install
  37. ```bash
  38. pip install openkb
  39. ```
  40. <details>
  41. <summary><b><i>Other install options:</i></b></summary>
  42. - **Latest from GitHub:**
  43. ```bash
  44. pip install git+https://github.com/VectifyAI/OpenKB.git
  45. ```
  46. - **Install from source** (editable, for development):
  47. ```bash
  48. git clone https://github.com/VectifyAI/OpenKB.git
  49. cd OpenKB
  50. pip install -e .
  51. ```
  52. </details>
  53. ### Quick Start
  54. ```bash
  55. # 1. Create a directory for your knowledge base
  56. mkdir my-kb && cd my-kb
  57. # 2. Initialize the knowledge base
  58. openkb init
  59. # 3. Add documents
  60. openkb add paper.pdf
  61. openkb add ~/papers/ # Add a whole directory
  62. openkb add https://arxiv.org/pdf/2509.11420 # Or fetch from a URL
  63. # 4. Ask a question
  64. openkb query "What are the main findings?"
  65. # 5. Or chat interactively
  66. openkb chat
  67. # (Optional) Turn the wiki into other outputs
  68. openkb skill new my-expert "Reason like an expert on <your-topic>" # a portable agent skill
  69. openkb visualize # an interactive knowledge graph
  70. openkb deck new my-deck "An intro deck on <your-topic>" # slides — a single-file HTML deck
  71. ```
  72. ### Set up your LLM
  73. OpenKB supports [multiple LLM providers](https://docs.litellm.ai/docs/providers) (OpenAI, Claude, Gemini, etc.) via [LiteLLM](https://github.com/BerriAI/litellm) (pinned to a [safe version](https://docs.litellm.ai/blog/security-update-march-2026)).
  74. Set your model during `openkb init` or in [`.openkb/config.yaml`](#configuration) using the `provider/model` LiteLLM format (e.g. `anthropic/claude-sonnet-4-6`). OpenAI models can omit the prefix (e.g. `gpt-5.4`).
  75. Create a `.env` file with your LLM API key:
  76. ```bash
  77. LLM_API_KEY=your_llm_api_key
  78. ```
  79. Subscription-based providers that authenticate via OAuth device flow (e.g. `chatgpt/*`, `github_copilot/*`) need no API key; OpenKB skips the missing-key warning for them.
  80. ### Knowledge Workbench (Web UI)
  81. OpenKB ships a bundled web UI, served by the REST API at `/`. Install the API extra and start the server — no configuration needed:
  82. ```bash
  83. pip install "openkb[web]"
  84. openkb-web # serves the API + Workbench at http://127.0.0.1:7566/
  85. ```
  86. Open `http://127.0.0.1:7566/` for the Workbench. Auth is off by default (local-first); set `OPENKB_API_TOKEN` to require a bearer token before exposing the server. See the [full Web UI guide](examples/rest-api/README.md#knowledge-workbench-web-ui).
  87. > Working on the UI itself? Run the Vite dev server with `cd frontend && npm install && npm run dev` (it proxies `/api` to a running `openkb-web`), or `npm run build` to regenerate the bundled `openkb/web/`.
  88. # 🧩 How OpenKB Works
  89. ### Architecture
  90. <div align="center">
  91. <img src="assets/openkb-architecture.webp" alt="OpenKB Architecture: from raw documents (markitdown / PageIndex) through LLM wiki compilation to the wiki/ foundation, powering query/chat, the Skill Factory, and future generators" width="900" />
  92. </div>
  93. ### Short vs Long Document Handling
  94. | | Short documents | Long documents (PDF ≥ 20 pages) |
  95. | ------------- | -------------------------- | ---------------------------------- |
  96. | **Convert** | markitdown → Markdown | PageIndex → tree index + summaries |
  97. | **Images** | Extracted inline (pymupdf) | Extracted by PageIndex |
  98. | **LLM reads** | Full text | Document trees |
  99. | **Result** | summary + concepts | summary + concepts |
  100. Short documents are read in full by the LLM. Long PDFs are processed by [PageIndex](https://github.com/VectifyAI/PageIndex) into a hierarchical tree index. The LLM reads the tree instead of the full text, enabling accurate and scalable retrieval for long documents.
  101. ### Knowledge Compilation
  102. When you add a document, the LLM:
  103. 1. Generates a **summary** page
  104. 2. Reads existing **concept** and **entity** pages
  105. 3. Creates or updates concepts with cross-document synthesis
  106. 4. Creates or updates **entity** pages (people, orgs, places, products)
  107. 5. Updates the **index** and **log**
  108. A single source might touch 10--15 wiki pages. Knowledge accumulates: each document enriches the existing wiki rather than sitting in isolation.
  109. # ⚙️ Usage
  110. OpenKB commands fall into two layers: the **wiki foundation** (compile + manage your knowledge) and **generators** (turn that wiki into useful output). Each links to a concrete walkthrough — a real artifact OpenKB generated from one sample paper (browse them all in [`examples/`](examples/)).
  111. ## Layer 1: 🧱 Wiki Foundation — compile and maintain
  112. | Command | Description |
  113. | ------------------------------------------------------------ | --------------------------------------------------------------------------------------- |
  114. | `openkb init` | Initialize a new knowledge base (interactive) |
  115. | <code>openkb&nbsp;add&nbsp;&lt;file_or_dir_or_URL&gt;</code> | Add files, directories, or URLs and compile to wiki (URL content type is auto-detected) |
  116. | `openkb list` | List indexed documents and concepts |
  117. | `openkb status` | Show knowledge base stats |
  118. | `openkb watch` | Watch `raw/` and auto-compile new files |
  119. | `openkb lint` | Run structural and knowledge health checks |
  120. <details>
  121. <summary><i>More wiki commands:</i></summary>
  122. <br>
  123. | Command | Description |
  124. | ------------------------------------------------------------------ | ------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------ |
  125. | <code>openkb&nbsp;remove&nbsp;&lt;doc&gt;</code> | Remove a document and clean up its wiki pages, images, registry, and PageIndex state (`--dry-run` to preview, `--keep-raw` / `--keep-empty` to retain artifacts) |
  126. | <code>openkb&nbsp;recompile&nbsp;[&lt;doc&gt;]&nbsp;[--all]</code> | Re-run the compile pipeline on already-indexed docs without re-indexing. Regenerates summaries and rewrites concept pages; manual edits are overwritten (`--dry-run` to preview, `--refresh-schema` to also update `wiki/AGENTS.md`) |
  127. | <code>openkb&nbsp;feedback&nbsp;["msg"]</code> | File feedback by opening a prefilled GitHub issue (`--type bug/feature/question` to tag it) |
  128. </details>
  129. → **Example:** the everyday loop walked through end to end — [`examples/commands/`](examples/commands/).
  130. ## Layer 2: 💡 Generators — turn the wiki into output
  131. A "generator" reads from the compiled wiki and produces something usable: an answer, a conversation, a skill folder. The wiki is the substrate; generators are the surfaces.
  132. | Command | Output | Example |
  133. | ------------------------------------------------------------------------------------- | -------------------------------------------------------------------------------------------------------------- | ---------------------------------- |
  134. | <code>openkb&nbsp;query&nbsp;"question"</code> | A grounded answer with citations (`--save` to persist to `wiki/explorations/`) | [query & save](examples/commands/) |
  135. | <code>openkb&nbsp;chat</code> | Interactive multi-turn session over the wiki (`--resume`, `--list`, `--delete` to manage sessions) | [chat](examples/chat/) |
  136. | <code>openkb&nbsp;visualize</code> | A self-contained interactive knowledge graph at `output/visualize/graph.html` — 3D, mind-map, and radial views | [visualize](examples/visualize/) |
  137. | <code>openkb&nbsp;skill&nbsp;new&nbsp;&lt;skill-name&gt;&nbsp;"&lt;intent&gt;"</code> | Distill a redistributable agent skill from your wiki (see [Skill Factory](#skill-factory) below) | [skills](examples/skills/) |
  138. | <code>openkb&nbsp;deck&nbsp;new&nbsp;&lt;name&gt;&nbsp;"&lt;intent&gt;"</code> | Generate a single-file HTML slide deck (`--skill` picks a theme, `--critique` runs a quality pass) | [slides](examples/slides/) |
  139. ### (i) 💬 Query & Chat — *ask the wiki*
  140. `openkb query "..."` answers a single question with a grounded, cited answer from your wiki. `openkb chat` is interactive, an ongoing multi-turn session over the same wiki (`--resume`, `--list`, `--delete` to manage sessions). → Walked through with real saved output in **[`examples/commands/`](examples/commands/)** (query) and **[`examples/chat/`](examples/chat/)** (chat).
  141. Inside a chat, type `/` to access slash commands (Tab to complete).
  142. <details>
  143. <summary><i>More slash commands:</i></summary>
  144. <br>
  145. - `/help`: list available commands
  146. - `/status`: show knowledge base status
  147. - `/list`: list all documents
  148. - `/add <path>`: add a document or directory without leaving the chat
  149. - `/skill new <skill-name> "<intent>"`: compile a skill from this chat (see below)
  150. - `/deck new <name> "<intent>"`: generate an HTML slide deck from the wiki
  151. - `/critique <path>`: run the HTML critic over an existing deck
  152. - `/save [name]`: export the transcript to `wiki/explorations/`
  153. - `/clear`: start a fresh session (the current one stays on disk)
  154. - `/lint`: run knowledge base lint
  155. - `/exit`: exit (Ctrl-D also works)
  156. </details>
  157. <a id="skill-factory"></a>
  158. ### (ii) 🛠 Skill Factory — *drop in a book; out comes a digital expert.*
  159. `openkb skill new` distills a portable [agent skill](https://docs.claude.com/en/docs/build-with-claude/skills) from your wiki that Claude Code, Codex, and Gemini can install and load natively. Drop in a book's worth of papers; out comes a specialist other agents can call on. → A real generated skill, plus install / share / `eval` / rollback, is walked through in **[`examples/skills/`](examples/skills/)**.
  160. <details>
  161. <summary><i>More skill commands:</i></summary>
  162. <br>
  163. | Command | Output |
  164. | ------------------------------------------------------------------------------------------------------------------------------ | ------------------------------------------------------ |
  165. | <code>openkb&nbsp;skill&nbsp;validate&nbsp;[name]</code> | Validate compiled skills (auto-runs after `skill new`) |
  166. | <code>openkb&nbsp;skill&nbsp;eval&nbsp;&lt;name&gt;</code> | Check the skill triggers on the right prompts |
  167. | <code>openkb&nbsp;skill&nbsp;history&nbsp;&lt;name&gt;</code> / <code>openkb&nbsp;skill&nbsp;rollback&nbsp;&lt;name&gt;</code> | Version history + rollback for skills |
  168. </details>
  169. # 🔧 Configuration
  170. ### Settings
  171. OpenKB settings are initialized by `openkb init` and stored in `.openkb/config.yaml`:
  172. ```yaml
  173. model: gpt-5.4 # LLM model (any LiteLLM-supported provider)
  174. language: en # Wiki output language
  175. pageindex_threshold: 20 # PDF pages threshold for PageIndex
  176. ```
  177. The full settings reference — `entity_types`, OAuth providers (`chatgpt/*`, `github_copilot/*`), and LiteLLM tuning (timeouts for slow local runtimes like Ollama / LM Studio, `drop_params`, GitHub Copilot headers, install notes) — is in **[`examples/configuration/`](examples/configuration/)**.
  178. ### PageIndex Setup
  179. Long-document retrieval is a [known challenge](https://x.com/karpathy/status/2039823314982744522) for LLMs. [PageIndex](https://github.com/VectifyAI/PageIndex) solves this with vectorless, reasoning-based retrieval, by building a hierarchical tree index that lets LLMs reason over the index for context-aware retrieval.
  180. PageIndex runs locally by default using the [open-source version](https://github.com/VectifyAI/PageIndex), with no external dependencies required.
  181. ***Cloud Support*** *(Optional)*:
  182. For large or complex PDFs, [PageIndex Cloud](https://docs.pageindex.ai/) can be used to access additional capabilities, including:
  183. - OCR support for scanned PDFs (via hosted VLM models)
  184. - Faster structure generation
  185. - Scalable indexing for large documents
  186. Set `PAGEINDEX_API_KEY` in your `.env` to enable cloud features:
  187. ```
  188. PAGEINDEX_API_KEY=your_pageindex_api_key
  189. ```
  190. → **Example:** local vs. cloud indexing, and importing a cloud-indexed doc — [`examples/pageindex-cloud/`](examples/pageindex-cloud/).
  191. ### AGENTS.md
  192. The `wiki/AGENTS.md` file defines wiki structure and conventions. It's the LLM's instruction manual for maintaining the wiki. Customize it to change how your wiki is organized.
  193. The LLM reads `AGENTS.md` from disk at runtime, so your edits take effect immediately.
  194. # 🔌 Integrations
  195. ### Using with Obsidian
  196. The wiki is a directory of Markdown files with `[[wikilinks]]`. Obsidian renders it natively.
  197. 1. Open `wiki/` as an Obsidian vault
  198. 2. Browse summaries, concepts, and explorations
  199. 3. Use graph view to see knowledge connections
  200. 4. Use Obsidian Web Clipper to add web articles to `raw/`
  201. ### Using with Claude Code / Codex / Gemini CLI
  202. OpenKB ships a `SKILL.md` so any agent can read your compiled wiki. No extra runtime, no MCP setup, just install the skill once.
  203. <details>
  204. <summary><i>Claude Code:</i></summary>
  205. <br>
  206. ```
  207. /plugin marketplace add VectifyAI/OpenKB
  208. /plugin install openkb@vectify
  209. ```
  210. </details>
  211. <details>
  212. <summary><i>OpenAI Codex CLI:</i></summary>
  213. <br>
  214. *(no marketplace command yet; manual symlink)*
  215. ```bash
  216. git clone https://github.com/VectifyAI/OpenKB.git ~/openkb-src
  217. mkdir -p ~/.agents/skills
  218. ln -s ~/openkb-src/skills/openkb ~/.agents/skills/openkb
  219. ```
  220. </details>
  221. <details>
  222. <summary><i>Gemini CLI:</i></summary>
  223. <br>
  224. ```bash
  225. gemini skills install https://github.com/VectifyAI/OpenKB.git --path skills/openkb --consent
  226. ```
  227. </details>
  228. The skill is read-only. It won't run `openkb add`, `remove`, or `lint --fix` without you asking. See [`skills/openkb/SKILL.md`](skills/openkb/SKILL.md) for the full instruction set.
  229. # REST API
  230. OpenKB ships a FastAPI service for HTTP clients. Install with `pip install -e ".[web]"`, then start with `python -m openkb.api`. The interactive API reference is at [`/docs`](http://127.0.0.1:7566/docs) (importable into Postman).
  231. See the [full REST API reference](examples/rest-api/README.md#rest-api) for endpoints, auth, and SSE streaming.
  232. # 🧭 Learn More
  233. ### Compared to Karpathy's Approach
  234. | | Karpathy's workflow | OpenKB |
  235. | ----------------- | --------------------------- | ------------------------------------------------- |
  236. | Short documents | LLM reads directly | markitdown → LLM reads |
  237. | Long documents | Context limits, context rot | PageIndex tree index |
  238. | Input sources | Web clipper → .md | PDF, Word, PPT, Excel, HTML, text, CSV, .md, URLs |
  239. | Wiki compilation | LLM agent | LLM agent (same) |
  240. | Entity extraction | Manual | Automatic (people, orgs, places, products) |
  241. | Q&A | Query over wiki | Wiki + PageIndex retrieval |
  242. | Output | Wiki only | Wiki + Skill Factory + agent CLI integration |
  243. ### The Stack
  244. - [PageIndex](https://github.com/VectifyAI/PageIndex) — Vectorless, reasoning-based document indexing and retrieval
  245. - [markitdown](https://github.com/microsoft/markitdown) — Universal file-to-markdown conversion
  246. - [OpenAI Agents SDK](https://github.com/openai/openai-agents-python) — Agent framework (supports non-OpenAI models via LiteLLM)
  247. - [LiteLLM](https://github.com/BerriAI/litellm) — Multi-provider LLM gateway
  248. - [Click](https://click.palletsprojects.com/) — CLI framework
  249. - [watchdog](https://github.com/gorakhargosh/watchdog) — Filesystem monitoring
  250. ### Roadmap
  251. - [ ] Extend long document handling to non-PDF formats
  252. - [ ] Scale to large document collections with nested folder support
  253. - [ ] Hierarchical concept (topic) indexing for massive knowledge bases
  254. - [ ] Database-backed storage engine
  255. - [x] Web UI for browsing and managing wikis (Knowledge Workbench, served at `/`)
  256. ### Contributing
  257. Contributions are welcome! Submit a pull request or open an [issue](https://github.com/VectifyAI/OpenKB/issues) for bugs and feature requests. For larger changes, consider opening an issue first to discuss the approach.
  258. ### License
  259. Apache 2.0. See [LICENSE](LICENSE).
  260. ### 🌐 Open-Source Ecosystem
  261. Other [open-source projects](https://docs.pageindex.ai/open-source) from the PageIndex ecosystem:
  262. - [PageIndex](https://github.com/VectifyAI/PageIndex): Vectorless, reasoning-based RAG framework for long documents
  263. - [ChatIndex](https://github.com/VectifyAI/ChatIndex): Tree indexing and retrieval for long conversational histories and memory
  264. - [ConDB](https://github.com/VectifyAI/ConDB): A KV-cache native context database for tree-based retrieval at scale
  265. - [PageIndex MCP](https://github.com/VectifyAI/pageindex-mcp): MCP server for PageIndex
  266. ### Support Us
  267. If you find OpenKB useful, please give us a star 🌟 — and check out [**PageIndex**](https://github.com/VectifyAI/PageIndex) too!
  268. <div>
  269. [![Twitter](https://img.shields.io/badge/Twitter-000000?style=for-the-badge&logo=x&logoColor=white)](https://x.com/PageIndexAI)&ensp;
  270. [![LinkedIn](https://img.shields.io/badge/LinkedIn-0077B5?style=for-the-badge&logo=linkedin&logoColor=white)](https://www.linkedin.com/company/vectify-ai/)&ensp;
  271. [![Contact Us](https://img.shields.io/badge/Contact_Us-3B82F6?style=for-the-badge&logo=envelope&logoColor=white)](https://ii2abc2jejf.typeform.com/to/tK3AXl8T)
  272. </div>

Ratings and comments

Sign in to rate this skill.

Sign in

Free to use. If it’s helped, pass it on.