KubeMind Python SDK (kubemind)
The official Python client library for KubeMind — the self-hosted intelligent AI gateway and governance control plane.
Installation
pip install kubemind
Quickstart
from kubemind import KubeMindClient
# Initialize client with API key and workspace ID
client = KubeMindClient(
api_key="your-api-key",
workspace_id="default",
router_url="http://localhost:9080",
mind_url="http://localhost:9081",
sentinel_url="http://localhost:9083",
)
# 1. Chat completion with intent classification & sensitivity governance
completion = client.chat_completion(
model="llama3.1",
messages=[
{"role": "user", "content": "Email alice@example.com the summary report"}
]
)
print("Response:", completion["choices"][0]["message"]["content"])
print("Routing Decision:", completion.get("routing_decision"))
# 2. Semantic prompt routing
route = client.route("What is our company expense policy?")
print("Content:", route.get("content"))
print("Retrieval Status:", route.get("retrieval_status"))
# 3. CFO Cost & Usage Analytics
analytics = client.get_cost_analytics(window_hours=24)
print(f"Total Requests: {analytics['total_requests']}")
print(f"Estimated Spend ($): {analytics['estimated_spend_usd']}")
# 4. Cryptographic Ledger Verification
audit = client.verify_audit_ledger()
print("Ledger Intact:", audit.get("verified"))
Features
- Pre-Dispatch Sensitivity Gating: Inline regex + local offline NER tokenization with in-memory reversible restoration.
- Intent-Driven Routing: Routes prompts dynamically based on classified semantic intent.
- Fail-Closed Grounding: Distinguishes verified corporate knowledge from hallucinations.
- SHA-256 Tamper-Evident Ledger: Verifiable cryptographic audit trail for HIPAA/SOC2 compliance.
- Granular RBAC: Supports role-scoped API keys (
admin,developer,auditor,viewer).
Metadata
Release files for kubemind 0.1.0
For a detailed explanation of source distributions (sdists) and built distributions (wheels), please see the package formats documentation.
Source distribution (sdist)
| File | Size | Uploaded | |
|---|---|---|---|
| kubemind-0.1.0.tar.gz | 4.1 kB | Details |
Built distribution (wheel)
| File | Interpreter | ABI | Platform | Reset |
|---|---|---|---|---|
| kubemind-0.1.0-py3-none-any.whl | Python 3 | none | any | Details |
Total release size: 8.3 kB
Release files / kubemind-0.1.0.tar.gz
| Download URL | kubemind-0.1.0.tar.gz |
|---|---|
| Size | 4.1 kB |
| Tags | Source |
|
SHA-256 checksum How to use checksums |
3a6559fdef290f9240a79a6bb86828b960062790b557b91858d1de7a91e7c523
|
|
BLAKE2b-256 checksum How to use checksums |
5cfe006067a6c4bd1684bfbf77ee012983df8300b40b211c2d20a25b7cf1bd82
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
No |
| Uploaded via |
twine/7.0.0 CPython/3.10.12
|
Release files / kubemind-0.1.0-py3-none-any.whl
| Download URL | kubemind-0.1.0-py3-none-any.whl |
|---|---|
| Size | 4.2 kB |
| Tags | Python 3 |
|
SHA-256 checksum How to use checksums |
64a3a1d3afb7551b992e9e79bf07f0888943feaf0d9362306c11d04fa7cd47c2
|
|
BLAKE2b-256 checksum How to use checksums |
a3470f5fb46b48211824ecc61da19be9e3f8c602d502855c04861f0bfe2bb28f
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
No |
| Uploaded via |
twine/7.0.0 CPython/3.10.12
|