caioross/Trebuchet
O Trebuchet Framework é uma infraestrutura robusta para a criação, execução e orquestração de Agentes de IA autônomos, projetada especificamente para hardware local. Diferente de soluções que dependem exclusivamente de APIs na nuvem, o Trebuchet prioriza a privacidade e o desempenho local utilizando llama-cpp-python para inferência de LLMs e chroma
Trebuchet is a framework for building and running autonomous AI agents directly on your own computer, prioritizing data privacy and local performance. It takes in multimodal inputs (text, images, audio) and outputs decisions and actions that can interact with your operating system. This is for developers, researchers, or advanced users who need to create intelligent automation workflows without relying on cloud-based AI services.
Use this if you need to develop, deploy, and orchestrate complex AI agents that run locally, require privacy for your data, and can interact with your desktop environment using various inputs like text, vision, and audio.
Not ideal if you're looking for a simple, plug-and-play AI solution that doesn't require technical setup or if you prefer to rely entirely on cloud-based AI APIs.
Stars
8
Forks
2
Language
Python
License
AGPL-3.0
Category
Last pushed
Feb 22, 2026
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/agents/caioross/Trebuchet"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Featured in
Higher-rated alternatives
elizaOS/eliza
Autonomous agents for everyone
Agent-Field/agentfield
Framework for AI Backend. Build and run AI agents like microservices - scalable, observable, and...
gptme/gptme
Your agent in your terminal, equipped with local tools: writes code, uses the terminal, browses...
SolaceLabs/solace-agent-mesh
An event-driven framework designed to build and orchestrate multi-agent AI systems. It enables...
langgenius/dify
Production-ready platform for agentic workflow development.