ARPAHLS/rooms
A secure, local-first Python framework for orchestrating complex multi-agent think tanks with dynamic expertise-weighted routing.
Implements three turn-orchestration modes—round-robin, argumentative, and dynamic expertise-weighted—where agents can `PASS` turns or be directly addressed via `@AgentName` syntax. Built on `LiteLLM` for unified API routing to local models (Ollama) or commercial providers, with support for custom Python inference functions as agent logic. Features timestamped session memory, per-agent generative controls, and an optional global orchestrator moderator that fires at configurable intervals without creating runaway loops.
Stars
8
Forks
3
Language
Python
License
—
Category
Last pushed
Mar 09, 2026
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/agents/ARPAHLS/rooms"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
InfinitiBit/graphbit
GraphBit is the world’s first enterprise-grade Agentic AI framework, built on a Rust core with a...
autogluon/autogluon-assistant
Multi-Agent System Powered by LLMs for End-to-end Multimodal ML Automation
samholt/L2MAC
🚀 The LLM Automatic Computer Framework: L2MAC
pguso/agents-from-scratch
Build AI agents from first principles using a local LLM - no frameworks, no cloud APIs, no...
wjayesh/mahilo
mahilo: Multi-Agent Human-in-the-Loop Framework is a flexible framework for creating multi-agent...