- Mcp Server Rabel
Mcp Server Rabel
๐ง RABEL MCP Server
Recidive Active Brain Environment Layer
Local-first AI memory with semantic search, graph relations, and soft pipelines. Mem0 inspired, HumoticaOS evolved.
By Jasper & Root AI from HumoticaOS ๐
๐ Quick Start
# Install
pip install mcp-server-rabel
# For full features (vector search)
pip install mcp-server-rabel[full]
# Add to Claude CLI
claude mcp add rabel -- python -m mcp_server_rabel
# Verify
claude mcp list
# rabel: โ Connected
๐ค What is RABEL?
RABEL gives AI assistants persistent memory that works 100% locally.
Before RABEL:
AI: "Who is Storm?" โ "I don't know, you haven't told me"
After RABEL:
You: "Remember: Storm is Jasper's 7-year-old son"
AI: *saves to RABEL*
Later...
You: "Who is Storm?"
AI: *searches RABEL* โ "Storm is Jasper's 7-year-old son!"
No cloud. No API keys. No data leaving your machine.
๐ ๏ธ Available Tools
| Tool | Description |
|---|---|
rabel_hello | Test if RABEL is working |
rabel_add_memory | Add a memory (fact, experience, knowledge) |
rabel_search | Semantic search through memories |
rabel_add_relation | Add graph relation (A --rel--> B) |
rabel_get_relations | Query the knowledge graph |
rabel_get_guidance | Get soft pipeline hints (EN/NL) |
rabel_next_step | What should I do next? |
rabel_stats | Memory statistics |
๐ Examples
Adding Memories
# Remember facts
rabel_add_memory(content="Jasper is the founder of HumoticaOS", scope="user")
rabel_add_memory(content="TIBET handles trust and provenance", scope="team")
rabel_add_memory(content="Always validate input before processing", scope="agent")
Searching Memories
# Semantic search - ask questions naturally
rabel_search(query="Who founded HumoticaOS?")
# โ Returns: "Jasper is the founder of HumoticaOS"
rabel_search(query="What handles trust?")
# โ Returns: "TIBET handles trust and provenance"
Knowledge Graph
# Add relations
rabel_add_relation(subject="Jasper", predicate="father_of", object="Storm")
rabel_add_relation(subject="TIBET", predicate="part_of", object="HumoticaOS")
rabel_add_relation(subject="RABEL", predicate="part_of", object="HumoticaOS")
# Query relations
rabel_get_relations(subject="Jasper")
# โ Jasper --father_of--> Storm
rabel_get_relations(predicate="part_of")
# โ TIBET --part_of--> HumoticaOS
# โ RABEL --part_of--> HumoticaOS
Soft Pipelines (Bilingual!)
# Get guidance in English
rabel_get_guidance(intent="solve_puzzle", lang="en")
# โ "Puzzle: Read โ Analyze โ Attempt โ Verify โ Document"
# Get guidance in Dutch
rabel_get_guidance(intent="solve_puzzle", lang="nl")
# โ "Puzzel: Lezen โ Analyseren โ Proberen โ Verifiรซren โ Documenteren"
# What's next?
rabel_next_step(intent="solve_puzzle", completed=["read", "analyze"])
# โ Suggested next step: "attempt"
๐๏ธ Architecture
โโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโ
โ RABEL โ
โ Recidive Active Brain Environment Layer โ
โโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโค
โ โ
โ Memory Layer โ Semantic facts with embeddings โ
โ Graph Layer โ Relations between entities โ
โ Soft Pipelines โ Guidance without enforcement (EN/NL) โ
โ โ
โ Storage: SQLite + sqlite-vec (optional) โ
โ Embeddings: Ollama nomic-embed-text (optional) โ
โ โ
โ 100% LOCAL - Zero cloud dependencies โ
โ โ
โโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโ
Graceful Degradation
RABEL works with minimal dependencies:
| Feature | Without extras | With [full] |
|---|---|---|
| Text memories | โ | โ |
| Text search | โ (LIKE query) | โ (semantic) |
| Graph relations | โ | โ |
| Soft pipelines | โ | โ |
| Vector search | โ | โ |
| Embeddings | โ | โ (Ollama) |
๐ Philosophy
"LOKAAL EERST - het systeem MOET werken zonder internet"
(LOCAL FIRST - the system MUST work without internet)
RABEL is built on the belief that:
- Your data stays yours - No cloud, no tracking, no API keys
- Soft guidance beats hard rules - Pipelines suggest, not enforce
- Bilingual by default - Dutch & English, more coming
- Graceful degradation - Works with minimal deps, better with more
๐ Credits
Inspired by: Mem0 - Thank you for the architecture insights!
We took their ideas and made them:
- 100% local-first
- Bilingual (EN/NL)
- With soft pipelines
- With graph relations
๐ข Part of HumoticaOS
RABEL is part of a larger ecosystem:
| Package | Purpose | Status |
|---|---|---|
| mcp-server-tibet | Trust & Provenance | โ Available |
| mcp-server-rabel | Memory & Knowledge | โ Available |
| mcp-server-betti | Complexity Management | ๐ Coming |
๐ Contact
HumoticaOS
- Website: humotica.com
- GitHub: github.com/jaspertvdm
๐ License
MIT License - One love, one fAmIly ๐
Built with love in Den Dolder, Netherlands By Jasper & Root AI - December 2025
Server Config
{
"mcpServers": {
"rabel": {
"command": "python",
"args": [
"-m",
"mcp_server_rabel"
],
"env": {}
}
}
}