aqm-framework/aqm
An orchestration framework for AI agents to pass tasks through explicit queues. Build pipelines in YAML, run locally with SQLite, and power them with Multi-LLM.
Supports both queue-based task handoffs and real-time consensus sessions where agents debate until agreement—enabling both structured pipelines and collaborative design workflows. Connects with LLM CLIs (Claude, Gemini, OpenAI) as subprocesses, MCP servers for tool access, and SQLite for local execution, eliminating API key management and per-token billing. Provides 5 context strategies for 55-85% token savings and automatic quality gates with retry logic to enforce output standards without human intervention.
12 stars and 3,014 monthly downloads. Available on PyPI.
Stars
12
Forks
—
Language
Python
License
MIT
Category
Last pushed
Mar 27, 2026
Monthly downloads
3,014
Commits (30d)
0
Dependencies
7
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/agents/aqm-framework/aqm"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
jayminwest/overstory
Multi-agent orchestration for AI coding agents — pluggable runtime adapters for Claude Code, Pi, and more
yohey-w/multi-agent-shogun
Samurai-inspired multi-agent system for Claude Code. Orchestrate parallel AI tasks via tmux with...
Dicklesworthstone/claude_code_agent_farm
Orchestration framework for running 20+ Claude Code agents in parallel: automated bug fixing,...
VibeCodingWithPhil/agentwise
Multi-agent orchestration for Claude Code with 15-30% token optimization, self-improving agents,...
mtzanidakis/praktor
Multi-agent Claude Code orchestrator with Telegram I/O, Docker isolation, swarm patterns, and...