According to AlphaMoat, as of 2026-09, ClawRAG - Self-hosted RAG & Memory has 2,886 downloads and 0 stars — ranked #3,806 of 5,078 AI skills overall, and #327 of 442 in Knowledge.

Installs

123

Downloads

2.9K

Stars

Overall Rank

#3,806

Top 75% overall · Top 74% in Knowledge

Platform	Installs	Downloads	Stars	Comments
ClawHub ↗	83	2.6K	-	-
SkillHub ↗	123	2.9K	-	—

Platforms count differently and update at different times.

What this skill does

It supports ingesting PDF, DOCX, TXT, and Markdown documents and returning source-cited results through semantic and keyword hybrid search; Docker is required, with a cloud LLM as an option. Before installation, review and pin repository, container-image, and MCP-package versions, inspect mounts, ports, and environment handling, and limit container and MCP access to files and credentials.

Profile published 2026-10-29

What you can do with it

Build a searchable knowledge base from local documents
Search by semantic similarity and keywords with source citations
Plan a connection between OpenClaw and a self-hosted RAG service

When to use it

When documents are appropriate for a local knowledge base and container permissions, mounts, and model data flows have been reviewed

Example prompts

Generated from the skill’s documentation as examples; not results of actual runs.

Design a local document-retrieval workflow without installing containers or connecting MCP.

List image, source-version, mount, port, and credential boundaries to check before deploying ClawRAG.

Monthly Trend

Downloads2.9K

Stars-

The counting method changed in 2026-09: skills with the same name are now counted separately by author, and the full catalog is covered. Dashed lines show months before the change; they are not compared with later months, and no growth is computed across the change.

Month	Downloads	MoM	Stars
2026-09	2.9K	—	-
2026-08	2.5K	+5.4%	-
2026-07	2.4K	+11.9%	-
2026-06	2.1K	+7.8%	-
2026-05	2.0K	—	-
2026-03	1.4K	—	-

SKILL.md (original)

The author’s original file, shown as plain text without edits or review by AlphaMoat. Links are not clickable; check commands before running them. Fetched 2026-10-23.

2.7 KB · ClawHub v1.2.0

# ClawRAG Connector

**The Brain for OpenClaw** - Self-hosted RAG engine with hybrid search.

> ⚠️ This skill requires Docker. It connects OpenClaw to your local ClawRAG instance.

## What is ClawRAG?

Production-ready RAG infrastructure that keeps your data local:
- 🔒 **Privacy-first**: Vector DB runs on your machine

Show all (94 lines)

- 🔍 **Hybrid Search**: Semantic + Keyword (BM25) + RRF ranking
- 📄 **Smart Ingestion**: PDFs, Office docs, Markdown via Docling
- 🧠 **MCP-native**: Seamless OpenClaw integration

## Installation

### Step 1: Start ClawRAG (Docker)
```bash
git clone https://github.com/2dogsandanerd/ClawRag.git
cd ClawRag
cp .env.example .env
docker compose up -d
```

Wait for http://localhost:8080/health to return OK.

### Step 2: Connect OpenClaw
```bash
openclaw mcp add --transport stdio clawrag npx -y @clawrag/mcp-server
```

### Verification
Test your setup:
```bash
curl http://localhost:8080/api/v1/rag/collections
```

## Features

| Capability | Description |
|------------|-------------|
| Document Upload | PDF, DOCX, TXT, MD via API or folder |
| Hybrid Query | Vector similarity + keyword matching |
| Citations | Source tracking for all answers |
| Multi-Collection | Organize knowledge by project |

## Requirements

- Docker + Docker Compose
- 4GB+ RAM (8GB recommended for local LLM)
- Or: OpenAI/Anthropic API key for cloud LLM

## Architecture

```
OpenClaw ◄──MCP──► @clawrag/mcp-server ◄──HTTP──► ClawRAG API (localhost:8080)
                                           │
                                           ▼
                                    ┌─────────────┐
                                    │  ChromaDB   │
                                    │  (vectors)  │
                                    └─────────────┘
```

## Links

- 📚 Full Docs: https://github.com/2dogsandanerd/ClawRag#readme
- 🔧 API Reference: http://localhost:8080/docs (when running)
- 🐛 Issues: https://github.com/2dogsandanerd/ClawRag/issues
- 📦 MCP Package: https://www.npmjs.com/package/@clawrag/mcp-server

## Tags

rag, vector, memory, search, documents, self-hosted, privacy, mcp, local-ai

---

## Metadata für ClawHub-Upload:

| Feld | Wert |
|------|------|
| **Slug** | `clawrag` |
| **Display name** | `ClawRAG - Self-hosted RAG & Memory` |
| **Version** | `1.2.0` |
| **Tags** | `rag`, `vector`, `memory`, `search`, `documents`, `self-hosted`, `privacy`, `mcp`, `local-ai` |

## Changelog für Version 1.2.0

### 1.2.0 - Initial ClawHub Release

- Connector skill for OpenClaw integration
- MCP server support (@clawrag/mcp-server v1.1.0)
- Docker-first deployment
- Hybrid search (Vector + BM25)