Metadata-Version: 2.1
Name: agentmesh-context
Version: 3.4.0
Summary: A pure, logic-only library for routing context, handling RAG fallacies, and managing context windows. Layer 1 Primitive - no agent dependencies.
Home-page: https://github.com/microsoft/agent-governance-toolkit
Author: Microsoft Corporation
License: MIT
Project-URL: Homepage, https://github.com/microsoft/agent-governance-toolkit
Project-URL: Repository, https://github.com/microsoft/agent-governance-toolkit
Project-URL: Documentation, https://github.com/microsoft/agent-governance-toolkit/tree/main/docs
Project-URL: Issues, https://github.com/microsoft/agent-governance-toolkit/issues
Keywords: context,rag,document-processing,ai,nlp,context-extraction,context-routing,context-window,rag-fallacies,stateless,primitive
Platform: UNKNOWN
Classifier: Development Status :: 3 - Alpha
Classifier: Intended Audience :: Developers
Classifier: Programming Language :: Python :: 3
Classifier: Programming Language :: Python :: 3.8
Classifier: Programming Language :: Python :: 3.9
Classifier: Programming Language :: Python :: 3.10
Classifier: Programming Language :: Python :: 3.11
Classifier: Programming Language :: Python :: 3.12
Classifier: Topic :: Software Development :: Libraries :: Python Modules
Classifier: Topic :: Scientific/Engineering :: Artificial Intelligence
Requires-Python: >=3.8
Description-Content-Type: text/markdown
Provides-Extra: dev
Provides-Extra: test
Provides-Extra: hf
Provides-Extra: all
License-File: LICENSE

# Context-as-a-Service (CaaS) — Public Preview

> **Part of [Agent OS](https://github.com/microsoft/agent-governance-toolkit)** - Kernel-level governance for AI agents

[![PyPI](https://img.shields.io/pypi/v/caas-core.svg)](https://pypi.org/project/caas-core/)
[![License: MIT](https://img.shields.io/badge/License-MIT-yellow.svg)](https://opensource.org/licenses/MIT)

**Context management for RAG systems.**

CaaS provides stateless utilities for routing, prioritizing, and filtering context in retrieval-augmented generation (RAG) pipelines. It manages what information gets sent to the LLM, reducing token waste and improving response quality.

## Installation

```bash
pip install agentmesh-context
```

## Quick Start

```python
from caas import DocumentStore, VirtualFileSystem

store = DocumentStore()
store.add_document({"content": "API auth uses JWT", "timestamp": "2025-01-15"})

vfs = VirtualFileSystem()
vfs.create_file("/project/main.py", "print('hello')", agent_id="agent-1")
```

## Features

- Document storage with time-based prioritization
- Virtual File System for multi-agent collaboration
- Context routing to appropriate model tiers
- Stateless design with no framework dependencies

## Contributing

See [CONTRIBUTING.md](CONTRIBUTING.md) for development setup and guidelines.

## License

MIT License — see [LICENSE](LICENSE) for details.


