tibet-llm-router 0.1.0

Smart LLM routing with TIBET provenance - route queries to Ollama/OpenAI/Anthropic automatically

TIBET LLM Router

Smart LLM routing with TIBET provenance - route queries to Ollama/OpenAI/Anthropic automatically

Note: This package replaces tibet-router. The name tibet-router is reserved for TIBET token routing (like jis-router for RABEL).

Quick Start

from llm_router import LLMRouter

# Simple usage
llm = LLMRouter()
response = llm.generate("Hello!")

# Auto-routing (picks best model for your query)
llm = LLMRouter(auto_route=True)
response = llm.generate("Write a Python function")  # Routes to code model
response = llm.generate("Quick question")  # Routes to fast model

Installation

pip install tibet-llm-router

# With TIBET provenance tracking
pip install tibet-llm-router[tibet]

Features

• Auto-Routing: Automatically selects the best model for your query
• Code Detection: Routes code queries to specialized code models
• Complexity Analysis: Complex queries go to reasoning models
• TIBET Provenance: Full audit trail of all LLM calls
• Ollama Integration: Works with any Ollama-compatible backend

CLI Usage

# Generate text
llm-router gen "Write a haiku about AI"

# Auto-route
llm-router gen --auto "Complex philosophical question"

# Preview routing
llm-router route "Write Python code"
# Output: Model: deepseek-coder:6.7b, Reason: code query detected

# Interactive chat
llm-router chat --auto

# Check status
llm-router status

With TIBET Provenance

from llm_router import LLMRouter
from tibet_core import Provider

# Track all LLM calls
tibet = Provider(actor="my_app")
llm = LLMRouter(tibet=tibet, auto_route=True)

response = llm.generate("Explain quantum computing")
# Full provenance chain: who, what, when, why

Model Configuration

from llm_router import LLMRouter, ModelRouter, ModelConfig, ModelCapability

# Custom router
router = ModelRouter()
router.add_model(ModelConfig(
    name="my-custom-model:7b",
    size="7b",
    capabilities=[ModelCapability.CODE, ModelCapability.FAST],
    priority=50  # Higher = preferred
))

llm = LLMRouter(router=router, auto_route=True)

Environment Variables

Variable	Default	Description
OLLAMA_URL	http://localhost:11434	Ollama API URL

Part of Humotica Stack

LLM Router is part of the Humotica AI ecosystem:

Package	Description
tibet-core	TIBET provenance tracking
oomllama	.oom format Q2/Q4 quantization
rapid-rag	Local RAG with semantic search

Links

• PyPI Package
• Humotica
• TIBET Documentation

---

One Love, One fAmIly

Built by Humotica AI Lab - Jasper, Claude, Gemini