zimam
Earned-autonomy governance for AI agents — the Python package.
Zimam (Arabic: زمام, "reins") is an open-source governance layer in which AI agents earn autonomy the way employees earn trust: actions are classified by blast radius, judged against per-class trust levels (L0–L3), and every decision produces a signed, verifiable receipt. The reference runtime lives at zimamhq/zimam.
Status: this package ships the shared vocabulary of the Zimam protocol — action classes and trust levels — so Python code can already speak the same language as the runtime. The full Python SDK (policy evaluation, trust accounting, receipt verification) is planned for 2027 and will land here.
Install
pip install zimam
Usage
import zimam
zimam.ACTION_CLASSES # ("READ", "WRITE_INTERNAL", "COMM_EXTERNAL", "FINANCIAL", "DESTRUCTIVE")
zimam.TRUST_LEVELS # ("L0", "L1", "L2", "L3")
zimam.is_action_class("FINANCIAL") # True
zimam.is_action_class("YOLO") # False
License
Download files
Download the file for your platform. If you're not sure which to choose, learn more about installing packages.
Source Distribution
Built Distribution
Filter files by name, interpreter, ABI, and platform.
If you're not sure about the file name format, learn more about wheel file names.
Copy a direct link to the current filters
File details
Details for the file zimam-0.0.1.tar.gz.
File metadata
- Download URL: zimam-0.0.1.tar.gz
- Upload date:
- Size: 14.2 kB
- Tags: Source
- Uploaded using Trusted Publishing? No
- Uploaded via: twine/6.2.0 CPython/3.9.6
File hashes
| Algorithm | Hash digest | |
|---|---|---|
| SHA256 |
ccdf6bf7d41e1b4872bb9b37a864ba269551791498336c25e16989c04938e232
|
|
| MD5 |
c287422981b67990a888880163642be5
|
|
| BLAKE2b-256 |
fe18590189fb6ddf9ba73456e2421a46dbeb84aea4ad7b3d2435ae944bd2a0d3
|
File details
Details for the file zimam-0.0.1-py3-none-any.whl.
File metadata
- Download URL: zimam-0.0.1-py3-none-any.whl
- Upload date:
- Size: 14.8 kB
- Tags: Python 3
- Uploaded using Trusted Publishing? No
- Uploaded via: twine/6.2.0 CPython/3.9.6
File hashes
| Algorithm | Hash digest | |
|---|---|---|
| SHA256 |
e3115ce3e1f26502fe147106785bca8d32ee0825424380a5a47b7f087153b7b1
|
|
| MD5 |
e7f4bba454949128d49ea413a7d6c5e4
|
|
| BLAKE2b-256 |
3615ce899183b8ca35de7ddb983f6efcae97330c94b9b246f35c624cf1f8e065
|