agentmesh-context 3.6.0

A pure, logic-only library for routing context, handling RAG fallacies, and managing context windows. Layer 1 Primitive - no agent dependencies.

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

Part of Agent OS - Kernel-level governance for AI agents

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

pip install agentmesh-context

Quick Start

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 for development setup and guidelines.

License

MIT License — see LICENSE for details.