wjayesh/mahilo

mahilo: Multi-Agent Human-in-the-Loop Framework is a flexible framework for creating multi-agent systems that can each interact with humans while sharing relevant context internally.

57
/ 100
Established

Supports framework integration through adapters (LangGraph agents) and multi-provider LLM routing via LiteLLM, enabling seamless use of models from OpenAI, Anthropic, Azure, and others. Communication topology is controlled via `can_contact` lists for peer-to-peer or hierarchical patterns, with context sharing managed by AgentManager that exposes conversation history across agents. Built on WebSocket-based real-time transport with voice capability through OpenAI's Realtime API, session persistence, and message validation policies to prevent harmful content and communication loops.

470 stars and 41 monthly downloads. No commits in the last 6 months. Available on PyPI.

Stale 6m
Maintenance 0 / 25
Adoption 14 / 25
Maturity 25 / 25
Community 18 / 25

How are scores calculated?

Stars

470

Forks

61

Language

Python

License

Last pushed

Apr 02, 2025

Monthly downloads

41

Commits (30d)

0

Dependencies

14

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/agents/wjayesh/mahilo"

Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.