Metadata-Version: 2.4
Name: huap-core
Version: 0.1.0b1
Summary: HUAP Core - Build deterministic, traceable AI agents with replay and evaluation
Author: HUAP Team
License-Expression: MIT
Project-URL: Homepage, https://github.com/Mircus/HUAP
Project-URL: Documentation, https://github.com/Mircus/HUAP#readme
Project-URL: Repository, https://github.com/Mircus/HUAP
Keywords: ai,agents,tracing,llm,evaluation,replay
Classifier: Development Status :: 4 - Beta
Classifier: Intended Audience :: Developers
Classifier: Programming Language :: Python :: 3.10
Classifier: Programming Language :: Python :: 3.11
Classifier: Programming Language :: Python :: 3.12
Classifier: Topic :: Scientific/Engineering :: Artificial Intelligence
Requires-Python: >=3.10
Description-Content-Type: text/markdown
Requires-Dist: click>=8.0.0
Requires-Dist: pyyaml>=6.0
Requires-Dist: pydantic>=2.0.0
Requires-Dist: openai>=1.0.0
Provides-Extra: default
Requires-Dist: hu-plugins-hindsight>=0.1.0; extra == "default"
Provides-Extra: dev
Requires-Dist: pytest>=7.0.0; extra == "dev"
Requires-Dist: pytest-asyncio>=0.21.0; extra == "dev"
Requires-Dist: ruff>=0.1.0; extra == "dev"
Provides-Extra: encryption
Requires-Dist: cryptography>=41.0.0; extra == "encryption"

# HUAP Core

**Trace-first primitives for deterministic, testable AI agents.**

HUAP Core provides the foundational toolkit for building AI agent systems that are traceable, deterministic, evaluatable, and CI-gated.

## Quick Start

```bash
pip install huap-core
huap demo
```

## Features

- **Traceable** — every action recorded as replayable JSONL events
- **Deterministic** — stub mode + replay verification for reproducible testing
- **Evaluatable** — cost/quality grading to gate regressions in CI
- **Squad-ready** — specialist model router picks the right model for each task
- **Framework-agnostic** — adapters for CrewAI, LangChain, or wrap any script
- **Human-gated** — pause, review, and approve agent actions via an inbox
- **Pluggable** — plugin SDK for memory backends, tool packs, and providers

## Documentation

Full docs: [github.com/Mircus/HUAP](https://github.com/Mircus/HUAP)
