agent-operations-sdk
Give Python agents the ability to operate real organization systems — CRMs, WMSes, email, databases, admin consoles, arbitrary web apps — with onboarding-time integration discovery, security scanning, autonomy rules, human-in-the-loop primitives, and test-before-publish staging.
Status: Alpha (0.1.0, in development). Extracted from iv-bknd's AT (Agent Technology Department) agent, consolidating patterns from
skill-builder,nanoclaw, andmcp-tester. Pre-release — seedocs/TODO.md.
Why this exists
Every agent framework needs to let agents do things in the real world. Building that safely means solving nine hard problems simultaneously:
- Discover how to talk to a system (API? scraper? browser?)
- Generate a working client
- Scan it for dangerous patterns
- Register it as agent-callable tools
- Permission-gate who can use what
- Pause the agent and ask a human when needed
- Escalate high-risk actions to HITL
- Roll back when something breaks
- Audit every decision for later
This SDK bundles all nine. One install, one configuration, done.
Install (pre-release)
pip install -e 'git+https://github.com/95percent-ai/agent-operations-sdk.git#egg=agent-operations-sdk[all]'
Once published, just:
pip install agent-operations-sdk
Quickstart
import asyncio
from agentops.agent import AgentTechDept
from agentops.runtime import MemoryChannel, ToolOutcome
from agentops.credentials import Credential
from agentops.credentials.store import AuthType
async def main():
# 1. Spin up the ops agent — one line, everything wired up
at = AgentTechDept(channel=MemoryChannel())
await at.load_default_policy() # reads allowed, writes ask, rest deny
# 2. Register an integration (auto-scans for security)
status = await at.register_remote(
name="crm",
url="https://crm.example.com/sse",
token="...",
)
# status is IntegrationStatus.GREEN / AMBER / RED / PENDING
# 3. Store credentials so the agent doesn't see tokens
await at.credentials.store.put(
"crm", Credential("real-token", auth_type=AuthType.BEARER, system="crm"),
)
# 4. Grant an agent scoped access
await at.assign("sales-bot", "crm", allowlist=["get_contact", "create_order"])
# 5. Hand the agent a Toolbelt; executor is YOUR business logic
async def executor(qualified, params):
# Use at.credentials.authorized_client("crm") or your own dispatch
return {"ok": True, "called": qualified}
tools = at.for_agent("sales-bot", executor=executor)
# 6. Agent calls tools — autonomy gate + HITL + audit automatic
r = await tools.execute_capability("crm.get_contact", params={"id": "C-1"})
assert r.outcome == ToolOutcome.OK
asyncio.run(main())
See examples/minimal/autonomy_hitl.py for a complete runnable version showing all four decision outcomes (ALLOW / ASK / HITL / DENY) with a 3-layer policy.
Components
| Module | Purpose |
|---|---|
agentops.registry |
Register / resolve / unregister integrations (MCP, OpenAPI, REST, local). |
agentops.security |
Schema + code + pattern scanning; quarantine for red flags. |
agentops.discover |
12-tier integration discovery — HTTPS → TLS fingerprint → Playwright → cache relay. |
agentops.capability |
Capability generation, staging, test-before-publish with automated rollback. |
agentops.autonomy |
Rule-based decision engine with audit trail. |
agentops.runtime |
Agent-facing toolbelt + pluggable HITL channel. |
agentops.credentials |
Credential proxy — secrets never visible to agent code. |
agentops.worker |
Background task queue + health loops. |
agentops.agent.AgentTechDept |
Battery-included reference agent. |
agentops.integrations.langgraph |
First-class LangGraph nodes. |
agentops.integrations.deepagents |
deepagents wrapper. |
agentops.integrations.generic |
Framework-agnostic adapter. |
agentops.testing |
Fake MCP + fake target system + pytest fixtures for users' tests. |
Design principles
- Extract, don't copy. Patterns from production (
AT,skill-builder,nanoclaw) are ported with added tests that prove real behavior. - No mockup success. Every feature has at least one test that exercises it against a realistic fake server and asserts on observable behavior — not "function returned True."
- Rollback-first. Any state-modifying action can be reverted.
- Credentials never cross the agent boundary. Proxy injects auth; agent code cannot read secrets.
- Autonomy is data. Rules are readable, editable, auditable — never hardcoded.
- Security as a layer, not a feature. Every registration / generation / assignment passes through Scanner.
License
MIT. Free for commercial use, no obligations.
Metadata
Release files for agent-operations-sdk 0.5.0
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 | Actions |
|---|---|---|---|---|
| agent_operations_sdk-0.5.0.tar.gz | 92.3 kB | Without provenance | Details for agent_operations_sdk-0.5.0.tar.gz |
Built distribution (wheel)
| File | Interpreter | ABI | Platform | Actions Reset |
|---|---|---|---|---|
| agent_operations_sdk-0.5.0-py3-none-any.whl | Python 3 | none | any | Details for agent_operations_sdk-0.5.0-py3-none-any.whl |
Total release size: 162.6 kB
Release files / agent_operations_sdk-0.5.0.tar.gz
| Download URL | agent_operations_sdk-0.5.0.tar.gz |
|---|---|
| Size | 92.3 kB |
| Tags | Source |
|
SHA-256 checksum How to use checksums |
600fc2458eca8fce112f7da7cc6441068ade80912a974340c0c955035e865bc8
|
|
BLAKE2b-256 checksum How to use checksums |
ebd5111a61c4cbdb4476a5028b75d8c41823787754e93f50a785c4bc4c7c24c1
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
No |
| Uploaded via |
twine/6.2.0 CPython/3.11.1
|
Release files / agent_operations_sdk-0.5.0-py3-none-any.whl
| Download URL | agent_operations_sdk-0.5.0-py3-none-any.whl |
|---|---|
| Size | 70.3 kB |
| Tags | Python 3 |
|
SHA-256 checksum How to use checksums |
6c965a757e26a8ccc62ef6989a205b16cc2d52ee3257be45c8ea92cee1a748e7
|
|
BLAKE2b-256 checksum How to use checksums |
03b66dd10ccab8a65def5f44d2a4728a5ae0f4a73c2547397009b001ab2ea8f7
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
No |
| Uploaded via |
twine/6.2.0 CPython/3.11.1
|
Security for agent-operations-sdk 0.5.0
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.