aqm-framework

aqm-framework / aqm

Public

An orchestration framework for AI agents to pass tasks through explicit queues. Build pipelines in YAML, run locally with SQLite, and power them with Claude Code.

11
0
100% credibility
Found Mar 25, 2026 at 11 stars -- GitGems finds repos before they trend. Get early access to the next one.
Sign Up Free
AI Analysis
Python
AI Summary

aqm is a framework for creating shareable teams of AI agents that collaborate on tasks through simple descriptions, with a dashboard to watch and guide their work.

How It Works

1
🏠 Set up in your project

Go to your work folder and start the easy setup wizard to prepare everything.

2
✨ Build your AI team

Describe the helpers you need, like a planner, builder, and checker, and it creates your custom team automatically.

3
▶️ Give them a job

Tell your team what to do, such as 'add a login button', and they start working together.

4
📊 Watch them collaborate

Open the dashboard to see your AI helpers passing work along, reviewing each other in real time.

5
Need your input?
✅
Approve it

Say yes and they continue smoothly.

❌
Suggest fixes

Point out issues and they revise right away.

🌟 Task complete!

Your job is done perfectly, and you can reuse or share your team with others.

Sign up to see the full architecture

4 more

Sign Up Free

Star Growth

See how this repo grew from 11 to 11 stars Sign Up Free
Repurpose This Repo

Repurpose is a Pro feature

Generate ready-to-use prompts for X threads, LinkedIn posts, blog posts, YouTube scripts, and more -- with full repo context baked in.

Unlock Repurpose
AI-Generated Review

# aqm

What is aqm?

aqm orchestrates AI agents through explicit queues defined in shareable YAML pipelines. Agents hand off tasks with gates for approval/rejection, fan-out parallelism, and agent-decided routing via output directives. Run locally with SQLite persistence, power via CLI LLMs like Claude Code, Gemini, or Codex—no API keys needed. Includes chunk decomposition for task breakdown, conversational sessions for multi-agent consensus (round-robin or moderator-led), and token-optimized context strategies. Web dashboard for monitoring, CLI for management, and GitHub registry for pulling/publishing pipelines. This ai agent orchestration github tool focuses on agent orchestration github workflows like planning-review-implement cycles.

Why is it gaining traction?

Stands out with YAML pipelines over Python code—easy to version, share via open registry, and remix with imports/extends. Unique session nodes enable real multi-agent orchestration github discussions until consensus, unlike batch-only frameworks. CLI-driven multi-LLM support (Claude Code orchestration github) leverages existing logins, plus MCP for tools like GitHub/filesystem. Beats LangGraph/CrewAI on declarative fan-out, chunk tracking, and built-in web UI without paid tiers.

Who should use this?

Backend devs prototyping orchestration framework ai agents for code review, feature planning, or ops automation. Teams needing multi agent orchestration github without SDK complexity—ideal for claude code orchestration github fans tired of manual graphs. Suited for local experimentation before scaling to production queues.

Verdict

Promising alpha for agent orchestration github (11 stars, 1.0% credibility)—YAML simplicity and sessions hook quick wins, but expect rough edges in stability/docs. Solid for local pipelines; monitor for maturity before team use. Install and `aqm init` a test flow today.

Sign up to read the full AI review Sign Up Free

Similar repos coming soon.