Cabeza: Configurable Agentic Search Harness
What it is
Cabeza is a Python library providing a configurable inference harness for long-horizon agentic search tasks. It offers a unified `Agent` factory that supports multiple LLM families, pluggable context management strategies, page-based memory, and multi-agent topologies, along with built-in web search and visit tools.
The problem it solves
Developing and testing long-horizon agentic search systems requires complex, custom implementations for context management, memory, and multi-agent coordination, which are often tightly coupled to specific LLM providers.
What you could use it for
- Building autonomous agents that perform multi-step web research
- Evaluating different LLM providers and context management strategies for search tasks
- Implementing long-horizon agents with persistent memory and summarization
Read the source ↗Back to the library →
Summary written by an AI model from the source; check the source before you rely on it.