agent-sovereign
Sovereign and edge deployment toolkit for self-contained agent bundles
Part of the AumOS open-source agent infrastructure portfolio.
Features
- Data sensitivity classifier assigns INFORMATIONAL, ADVISORY, or DECISION_SUPPORT risk tiers based on regulatory rules (HIPAA, GDPR, financial regulations) to determine what data may leave a sovereign boundary
AgentPackagerbundles an agent with its model weights, tools, and config into a self-contained deployment artifact targeting Docker, Kubernetes, Lambda, or bare-metal edge nodesEdgeRuntimevalidates hardware resource constraints (RAM, CPU, GPU), selects the appropriate quantization level (INT4, INT8, GGUF variants), and manages model caching for offline inferenceEdgeSyncorchestrates delta synchronization of knowledge and model updates between edge nodes and a central coordinator, with offline-capable operation when network connectivity is unavailable- Data residency policy engine enforces where data may be stored and processed, mapping sensitivity tiers to approved geographic regions
- Provenance attestation generates signed attestation records for every model inference, establishing a verifiable chain of custody from training data to deployed output
- Deployment validator checks a packaged agent against residency policies, capability declarations, and hardware constraints before authorizing a deployment
Quick Start
Install from PyPI:
pip install agent-sovereign
Verify the installation:
agent-sovereign version
Basic usage:
import agent_sovereign
# See examples/01_quickstart.py for a working example
Documentation
Enterprise Upgrade
For production deployments requiring SLA-backed support and advanced integrations, contact the maintainers or see the commercial extensions documentation.
Contributing
Contributions are welcome. Please read CONTRIBUTING.md before opening a pull request.
License
Apache 2.0 — see LICENSE for full terms.
Part of AumOS — open-source agent infrastructure.
Metadata
Release files for agent-sovereign 0.2.0
For a detailed explanation of source distributions (sdists) and built distributions (wheels), please see the package formats documentation.
Source distribution (sdist)
| File | Size | Uploaded | Provenance | |
|---|---|---|---|---|
| agent_sovereign-0.2.0.tar.gz | 137.3 kB | Without provenance | Details |
Built distribution (wheel)
| File | Interpreter | ABI | Platform | Reset |
|---|---|---|---|---|
| agent_sovereign-0.2.0-py3-none-any.whl | Python 3 | none | any | Details |
Total release size: 248.6 kB
Release files / agent_sovereign-0.2.0.tar.gz
| Download URL | agent_sovereign-0.2.0.tar.gz |
|---|---|
| Size | 137.3 kB |
| Tags | Source |
|
SHA-256 checksum How to use checksums |
87e0fdf988fe13c76d02f04933aa3d60dd4304eb76ad33c4f807305e838305d0
|
|
BLAKE2b-256 checksum How to use checksums |
eeb42bea5b4f7f9b60582738b5aff1702e6145d9d09ba41227f4c5ea53837695
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
No |
| Uploaded via |
twine/6.2.0 CPython/3.11.9
|
Release files / agent_sovereign-0.2.0-py3-none-any.whl
| Download URL | agent_sovereign-0.2.0-py3-none-any.whl |
|---|---|
| Size | 111.3 kB |
| Tags | Python 3 |
|
SHA-256 checksum How to use checksums |
570e39bfea2f355f3f9db560c401ead1f2b4432ac24b81ba5967fedda5e232ca
|
|
BLAKE2b-256 checksum How to use checksums |
54eb90095bd3193cdda485b27b30928c9c08c61396b38ffff0e16c64e46bf731
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
No |
| Uploaded via |
twine/6.2.0 CPython/3.11.9
|
Security for agent-sovereign 0.2.0
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.
No provenance found
None of the files in this release were uploaded with provenance metadata.
A note on package security
PyPI is a repository for distributing packages, not a service for auditing them. While third-party security researchers and our staff do their best to detect and remove malicious packages, PyPI cannot guarantee the quality, security or suitability of any given package.
To learn more about protecting yourself from malicious actors, visit our package security documentation.