jev-pilot ⚡
Fast System-1 Decision, Arbitration & Safety Engine for AI Agents
Works with any LLM: Claude, GPT, Gemini, Llama, Hermes, DeepSeek.
📦 1. Install
pip install jev-pilot
🚀 2. Quickstart
Get a free key at console.typesafe.ai.
Pass your key with save=True once — it is remembered permanently on your machine:
from jev_pilot import JevPilot
# Run once with your key:
pilot = JevPilot(api_key="your_key_here", save=True)
# 1. Pick the best solution (Best-of-N in 0.3s):
decision = pilot.arbitrate(
context="Build a high-performance web crawler",
candidates={
"opt_a": "Requests with for loops",
"opt_b": "Asyncio + aiohttp",
"opt_c": "Scrapling framework"
}
)
print(f"Winner: {decision.winner}")
# 2. Block dangerous commands:
safety = pilot.guard("rm -rf /var/lib/mysql/*", "Production database")
if not safety.allowed:
print("Action blocked for safety!")
From now on, in any script or agent you can simply call:
pilot = JevPilot()
📄 License
MIT © 2026 Reza Rajabzadeh.
Release files for jev-pilot 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 | |
|---|---|---|---|
| jev_pilot-0.1.1.tar.gz | 10.8 kB | Details |
Built distribution (wheel)
| File | Interpreter | ABI | Platform | Reset |
|---|---|---|---|---|
| jev_pilot-0.1.1-py3-none-any.whl | Python 3 | none | any | Details |
Total release size: 20.9 kB
Release files / jev_pilot-0.1.1.tar.gz
| Download URL | jev_pilot-0.1.1.tar.gz |
|---|---|
| Size | 10.8 kB |
| Tags | Source |
|
SHA-256 checksum How to use checksums |
43ae70a953010e6139265c83e674f89f314bd883bc276ee7072faed4d57d66c3
|
|
BLAKE2b-256 checksum How to use checksums |
7ad54600e5fcf19ab8585e9915ae53390ef88212a9507d82e1ffa9c94e2b1f74
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
No |
| Uploaded via |
twine/7.0.0 CPython/3.12.3
|
Release files / jev_pilot-0.1.1-py3-none-any.whl
| Download URL | jev_pilot-0.1.1-py3-none-any.whl |
|---|---|
| Size | 10.1 kB |
| Tags | Python 3 |
|
SHA-256 checksum How to use checksums |
8c2e79bf2fcb6ebca1c95ff498b3c319f7083dbb7058e80fad32aa6520856820
|
|
BLAKE2b-256 checksum How to use checksums |
2fc6f729444f642c20efdaa5f7691b2189289136072719ceca0a7375f5128770
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
No |
| Uploaded via |
twine/7.0.0 CPython/3.12.3
|