Metadata-Version: 2.4
Name: connector_oss
Version: 0.1.0
Classifier: Development Status :: 4 - Beta
Classifier: Intended Audience :: Developers
Classifier: License :: OSI Approved :: Apache Software License
Classifier: Programming Language :: Python :: 3
Classifier: Programming Language :: Python :: 3.10
Classifier: Programming Language :: Python :: 3.11
Classifier: Programming Language :: Python :: 3.12
Classifier: Programming Language :: Python :: 3.13
Classifier: Programming Language :: Rust
Classifier: Topic :: Scientific/Engineering :: Artificial Intelligence
Classifier: Topic :: Security
Requires-Dist: pytest>=7.0 ; extra == 'dev'
Requires-Dist: maturin>=1.0 ; extra == 'dev'
Requires-Dist: twine ; extra == 'dev'
Provides-Extra: dev
Summary: Tamper-proof memory and chain-of-custody for AI agents
Keywords: ai,agents,memory,compliance,hipaa,audit,llm,trust
License: Apache-2.0
Requires-Python: >=3.10
Description-Content-Type: text/markdown; charset=UTF-8; variant=GFM
Project-URL: Bug Tracker, https://github.com/GlobalSushrut/connector-oss/issues
Project-URL: Documentation, https://github.com/GlobalSushrut/connector-oss/blob/main/docs/01_INDEX.md
Project-URL: Homepage, https://github.com/GlobalSushrut/connector-oss
Project-URL: Repository, https://github.com/GlobalSushrut/connector-oss

# Connector Python SDK

Trusted Memory for AI Agents — Python SDK backed by the real Rust kernel.

## Install

```bash
pip install connector-agent
```

## Quick Start

```python
from connector import Connector

# 3 lines: agent with memory
c = Connector("openai", "gpt-4o", "sk-...")
agent = c.agent("assistant", "You help users")
result = agent.run("What is Rust?", user="user:alice")

print(result.text)        # response
print(result.trust)       # 92 (kernel-verified)
print(result.trust_grade) # "A"
print(result)             # beautiful dashboard
```

## Multi-Agent Pipeline

```python
pipe = c.pipeline("support")
pipe.agent("triage", "Classify tickets")
pipe.agent("resolver", "Find answers")
pipe.route("triage -> resolver")
pipe.hipaa()

result = pipe.run("My account is locked", user="user:bob")
print(result.to_json())   # machine-parseable with provenance tags
```

## Observability

```python
result.to_json()       # every field tagged with source (kernel/llm/derived/user)
result.to_otel()       # OTLP-compatible trace export
result.to_llm()        # LLM-friendly summary
result.provenance()    # {"kernel_verified": 5, "trust_percentage": 100.0}
result.is_verified()   # True = zero-fake guarantee
```

## License

Apache-2.0

