AI King engine — guards, runtime, ZIQ, FieldRead, PSYCHE, Cerno (AGPL-3.0-or-later or commercial)
Project description
aiking-core
The substantive engine of the AI King distribution. Wires together the governance stack (Concinno guards + Sancio runtime), ZIQ retrieval, FieldRead memory, PSYCHE chat-completion gateway, and the Cerno 7-step mother-agent cycle.
Install
pip install aiking-core # base engine
pip install "aiking-core[body]" # adds persona-api adapters (see caveat)
You normally do not install aiking-core directly — pip install aiking
pulls it transitively and exposes the curated public surface.
Entry points (group aiking.core_engine)
ziq = aiking_core.ziq:get_engine
fieldread = aiking_core.fieldread:get_engine
cerno = aiking_core.cerno:get_engine
The aiking shell discovers these via importlib.metadata rather than
direct imports, preserving the Apache-2.0 / AGPL boundary.
License
Dual-licensed:
- AGPL-3.0-or-later with §7 Additional Terms — see
LICENSE. - Commercial license for entities that cannot or will not comply with
AGPL §13 (network-use / SaaS clause), or whose policy bans AGPL-licensed
dependencies — see
COMMERCIAL_LICENSE.md.
If you are not sure which applies, the AGPL terms govern by default.
Migration window (1.0.x)
aiking_core.ziq.retrieval imports concinno.core.state_store.StateStore,
and several governance / hooks submodules import from concinno.* and
persona.* during the Phase 2 migration. The relevant concinno>=5.3.0
dep is declared automatically; persona-api>=2.1.0 is opt-in via the
[body] extra because persona-api 2.1.0 has an upstream
from .engine import PersonaEngine self-import bug. Wait for 2.1.1 if
you need the body-engine path.
Source
Project details
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 aiking_core-1.0.1.tar.gz.
File metadata
- Download URL: aiking_core-1.0.1.tar.gz
- Upload date:
- Size: 98.8 kB
- Tags: Source
- Uploaded using Trusted Publishing? No
- Uploaded via: twine/6.2.0 CPython/3.11.9
File hashes
| Algorithm | Hash digest | |
|---|---|---|
| SHA256 |
4a017b3c8cdf546f5d968d045f6408b64a4a389e90cacf9ee3e0df6d4188759c
|
|
| MD5 |
f3a589b694470b7545b5606ec86facd0
|
|
| BLAKE2b-256 |
0ed3ce3973462b767225c5ffa1b60841bfaddeb1321371b158b9861b82a4d92e
|
File details
Details for the file aiking_core-1.0.1-py3-none-any.whl.
File metadata
- Download URL: aiking_core-1.0.1-py3-none-any.whl
- Upload date:
- Size: 110.8 kB
- Tags: Python 3
- Uploaded using Trusted Publishing? No
- Uploaded via: twine/6.2.0 CPython/3.11.9
File hashes
| Algorithm | Hash digest | |
|---|---|---|
| SHA256 |
3842a2a8b840fa7e4fb6fcdd78b77473fe7805dc482b739b4fa73cd0e91f73cc
|
|
| MD5 |
a0eeb0805a2a2c3dce5bab7137213de9
|
|
| BLAKE2b-256 |
f861da20c58a4bc94eacaa3790178f08eafe064ff952fea6f4f1dedd73b02660
|