Kimss — Secure AI Gateway for Autonomous Agents
Track, govern, and secure autonomous agents with exactly 1 line of code.
Kimss is a Model-Agnostic Enterprise AI Gateway and Governance Control Plane. Swap your OpenAI base_url, add an Agent ID header, and every call gets identity, an audit trail, and a kill switch — without rewriting your app. Kimss never hosts your models and never charges for inference compute (BYOI).
AI coding assistants: read AI_INTEGRATION.md first.
import os
from openai import OpenAI
client = OpenAI(
base_url=os.getenv("KIMSS_GATEWAY_URL", "https://api.kimss.ai/v1"),
api_key=os.getenv("KIMSS_WORKSPACE_KEY") or os.getenv("KIMSS_API_KEY"),
)
response = client.chat.completions.create(
model="custom:kimss-gpt-5-3-chat",
messages=[{"role": "user", "content": "Execute database audit."}],
extra_headers={
"X-Kimss-Agent-Id": "enterprise_db_auditor",
"X-Kimss-Agent-Name": "Database Auditor Agent",
},
)
Or zero-code:
OPENAI_BASE_URL="https://api.kimss.ai/v1"
OPENAI_API_KEY="kimss_..."
Developer tier (Always Free): 25,000 governed requests/month · Get a key
| Inbound (your app → Kimss) | Vaulted BYO (Kimss → your provider) |
|---|---|
OpenAI Python/JS/Java at https://api.kimss.ai/v1 |
OpenAI, Azure AI Foundry, Anthropic, DeepSeek, custom vLLM |
Agent attribution via X-Kimss-Agent-Id |
Internal MCP servers (Control Plane registration) |
flowchart LR
App[Your_app_or_agent] --> GW["Kimss_Gateway"]
GW --> Model[Vaulted_provider]
GW --> Trail[Governed_audit_trail]
3-step setup
1. Sign In & Vault
Log into Kimss AI. Open Governance → Connected Infrastructure / Provider Vault and vault your model provider endpoint + key.
2. Mint Key
On the Gateway tab, Generate Key. Copy the kimss_... Control-Plane workspace key once. Same keys under Governance → API Keys.
3. Route Traffic (zero refactoring)
Point your OpenAI client at https://api.kimss.ai/v1, set the key, and add X-Kimss-Agent-Id (see hero snippet). Prefer a registered agent_id from Gateway; omit it and Kimss may JIT-discover the agent from traffic.
Step-by-step: GETTING_STARTED.md · 5-minute tutorial: eyal81/kimss-python-quickstart.
Control plane (DevOps) — optional pip install kimss
The kimss package is an infrastructure management client — not an inference SDK. Prefer the OpenAI gateway for all chat/completions.
| Concern | How |
|---|---|
| Register external agent | client.agents.register(...) → POST /v1/agents/register |
| Report BYO usage | client.usage.report(...) → POST /v1/usage/events |
| Kill switch | Governance → Agents, or POST /agent_set_status/ { "id", "status": "disabled" } (admin) |
| Article 12–style audit | Gateway → Recent calls; POST /audit_log/; APIM GatewayLogs when enabled |
| MCP sync | Control Plane / Connected Infrastructure (UI registration) |
pip install kimss
Inference wrappers (agents.run, chat, models.create, …) are deprecated — see CHANGELOG.md.
Optional: MCP for IDEs
Cursor / Windsurf / Claude Desktop can run kimss-mcp-server (pip install 'kimss[mcp]' or uvx --from kimss[mcp] kimss-mcp-server). MCP inference tools are deprecated; use the OpenAI gateway from application code. Plugin layout: .cursor-plugin/plugin.json.
Examples
See examples/00_gateway_proxy.py for the canonical pattern.
License
MIT — see LICENSE.
Metadata
Release files for kimss 2.1.0
For a detailed explanation of source distributions (sdists) and built distributions (wheels), please see the package formats documentation.
Source distribution (sdist)
| File | Size | Uploaded | |
|---|---|---|---|
| kimss-2.1.0.tar.gz | 31.3 kB | Details |
Built distribution (wheel)
| File | Interpreter | ABI | Platform | Reset |
|---|---|---|---|---|
| kimss-2.1.0-py3-none-any.whl | Python 3 | none | any | Details |
Total release size: 53.9 kB
Release files / kimss-2.1.0.tar.gz
| Download URL | kimss-2.1.0.tar.gz |
|---|---|
| Size | 31.3 kB |
| Tags | Source |
|
SHA-256 checksum How to use checksums |
0e5ce59495d167752048e34436bae03d5ceb2bf0f491c2fd672031db9497c7a6
|
|
BLAKE2b-256 checksum How to use checksums |
a0e596bfdbf9b929294debfbcbcbd400db3038e2c30fab6f45b6fc0f9093a089
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
Yes |
| Uploaded via |
twine/7.0.0 CPython/3.13.14
|
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.
PyPI Publish Attestation
PyPI verified that this artifact, at this checksum, originated from the publisher listed below.
Signed by GitHub Actions, verified by PyPI on Aug 21, 2026.
Transparency logRelease files / kimss-2.1.0-py3-none-any.whl
| Download URL | kimss-2.1.0-py3-none-any.whl |
|---|---|
| Size | 22.6 kB |
| Tags | Python 3 |
|
SHA-256 checksum How to use checksums |
e9c5886a7984e7fd6c374a38fa7537f96142badfb317fe52223a6b63069b9baf
|
|
BLAKE2b-256 checksum How to use checksums |
7ce64bed1f75fa33240f20d293e54678aadf04159c35e6b61dab2b5744ce8501
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
Yes |
| Uploaded via |
twine/7.0.0 CPython/3.13.14
|
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.
PyPI Publish Attestation
PyPI verified that this artifact, at this checksum, originated from the publisher listed below.
Signed by GitHub Actions, verified by PyPI on Aug 21, 2026.
Transparency log