Production control plane for agentic AI: guardrails, confidence decisioning, immutable audit logging
Project description
Agent Sentinel
Agent Sentinel is a lightweight production control plane for agentic AI:
- Guardrails (max steps/tool calls/cost, deterministic mode)
- Confidence-based decisions (accept vs human_review)
- Immutable audit logging (append-only events; Delta optional)
Not an agent framework — it wraps your agent logic with safety, governance, and auditability.
Local install (dev)
pip install agent-roi
Download files
Download the file for your platform. If you're not sure which to choose, learn more about installing packages.
Source Distribution
agent_roi-0.1.0.tar.gz
(8.5 kB
view details)
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
agent_roi-0.1.0-py3-none-any.whl
(13.1 kB
view details)
File details
Details for the file agent_roi-0.1.0.tar.gz.
File metadata
- Download URL: agent_roi-0.1.0.tar.gz
- Upload date:
- Size: 8.5 kB
- Tags: Source
- Uploaded using Trusted Publishing? No
- Uploaded via: twine/6.2.0 CPython/3.11.9
File hashes
| Algorithm | Hash digest | |
|---|---|---|
| SHA256 |
63506328b0bc8512e845b7cc465a0dfb6aa06db4efeb41a97e6ef5e85bbaef0b
|
|
| MD5 |
b2d7365efbd49167eba28c7e4e014370
|
|
| BLAKE2b-256 |
7fbcb8e82ceca47fd2777b0dd44052337a111868e3269f8d1eab38308062bafb
|
File details
Details for the file agent_roi-0.1.0-py3-none-any.whl.
File metadata
- Download URL: agent_roi-0.1.0-py3-none-any.whl
- Upload date:
- Size: 13.1 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 |
2da6524332f6587e3ddb91cd863080af7f300816aa665988f61247a7f699f0f5
|
|
| MD5 |
b23391c621ca42812109a8418f4b0dd9
|
|
| BLAKE2b-256 |
930801f9e36702b9b5fb15b5413682bf8ca4b29fafb351e64d8512f87a43333f
|
