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
One Love, One fAmIly
Built by Humotica AI Lab - Jasper, Claude, Gemini
License
MIT
Credits
Designed by Jasper van de Meent. Built by Jasper and Root AI as part of HumoticaOS.
Stack-positie: Groep agentic · Bootstrap = OSAPI-handshake naar tibet + jis (fail → snaft-rule + tibet-pol-rapport) · ← ollama-bridge · tibet-gateway → · See STACK.md · See demo/golden-path/ for the spine end-to-end.
Enterprise
For private hub hosting, SLA support, custom integrations, or compliance guidance:
| Enterprise | enterprise@humotica.com |
| Support | support@humotica.com |
| Security | security@humotica.com |
See ENTERPRISE.md for details.
Metadata
Release files for tibet-llm-router 0.1.1
For a detailed explanation of source distributions (sdists) and built distributions (wheels), please see the package formats documentation.
Source distribution (sdist)
| File | Size | Uploaded | Provenance | Actions |
|---|---|---|---|---|
| tibet_llm_router-0.1.1.tar.gz | 10.0 kB | Without provenance | Details for tibet_llm_router-0.1.1.tar.gz |
Built distribution (wheel)
| File | Interpreter | ABI | Platform | Actions Reset |
|---|---|---|---|---|
| tibet_llm_router-0.1.1-py3-none-any.whl | Python 3 | none | any | Details for tibet_llm_router-0.1.1-py3-none-any.whl |
Total release size: 20.7 kB
Release files / tibet_llm_router-0.1.1.tar.gz
| Download URL | tibet_llm_router-0.1.1.tar.gz |
|---|---|
| Size | 10.0 kB |
| Tags | Source |
|
SHA-256 checksum How to use checksums |
4986608eec1865cf67465ad9372da53938465e6d35c05c8e79d9279ff3d81e22
|
|
BLAKE2b-256 checksum How to use checksums |
7afde26ec5040d7350eb9fed7788dc421692414610de883cc6cf2c7675741bce
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
No |
| Uploaded via |
twine/6.2.0 CPython/3.13.5
|
Release files / tibet_llm_router-0.1.1-py3-none-any.whl
| Download URL | tibet_llm_router-0.1.1-py3-none-any.whl |
|---|---|
| Size | 10.7 kB |
| Tags | Python 3 |
|
SHA-256 checksum How to use checksums |
49b66b39b864eca318dae0139407e7e5c61f98323ba7adf735eba404d1a3aa5c
|
|
BLAKE2b-256 checksum How to use checksums |
b163fb581e690b6f254473cad8b9a4b2c7ea6995d2ef5dd31046ff9a0db76311
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
No |
| Uploaded via |
twine/6.2.0 CPython/3.13.5
|
Security for tibet-llm-router 0.1.1
Provenance
Provenance describes where a file came from. On PyPI, provenance is shared via attestations, which provide a verifiable record of the build or publishing details. View details, limitations and caveats.
No provenance found
None of the files in this release were uploaded with provenance metadata.
A note on package security
PyPI is a repository for distributing packages, not a service for auditing them. While third-party security researchers and our staff do their best to detect and remove malicious packages, PyPI cannot guarantee the quality, security or suitability of any given package.
To learn more about protecting yourself from malicious actors, visit our package security documentation.