Work orchestration for AI agents
Build pipelines that triage tickets, process documents, and automate research. All from your terminal.
What It Does
A framework for AI agents that work together.
Each agent masters one domain. A triager triages. A reviewer reviews. Expertise through focus.
Chain agents with Unix pipes. JSON in, JSON out. Build complex workflows from simple parts.
Agents live as folders on your machine. Version them in git. Deploy anywhere.
Each agent transforms data and routes it forward. Filter, enrich, classify, hand off.
Tickets, memory, and config are plain Markdown. Read them. Edit them. Understand them.
Orchestrate from your shell. Cron jobs, pipes, scripts. No new tools to learn.
Built for Real Work
ayo orchestrates work that doesn't belong in a code editor.
Route incoming tickets to specialized agents based on content.
✓ 12 tickets → @billing-agent
✓ 8 tickets → @technical-agent
✓ 3 tickets → @escalation-agent
Extract and summarize information from bulk documents.
Processing 47 contracts...
✓ Extracted key terms → contracts-summary.json
Gather information from multiple sources and generate reports.
Gathering from 12 sources...
✓ Report generated → research/pricing-analysis.md
Review drafts and route based on quality assessment.
Reviewing 8 drafts...
✓ 5 approved → approved/
✓ 3 need revision → tickets created
Schedule and run recurring reports with flows.
Collecting data from 4 sources...
✓ Report sent to #metrics-channel
What People Say
Teams using ayo for work orchestration.
What Makes ayo Different
Not just another chatbot. A framework for AI that actually works.
Each agent is a directory with config.json and system.md. Version control them. Share them. Understand them at a glance.
Tickets track work between agents. Add dependencies. Assign to specialists. When one completes, blocked tasks automatically unblock.
Agents execute in containers with explicit trust levels. Grant filesystem access, network access, or keep them locked down.
Facts survive sessions. Store organizational knowledge. Agents automatically retrieve relevant context when they need it.
Define multi-step workflows in YAML. Parallel execution where possible. Automatic dependency resolution. Error handling built in.
Pipe output between agents. JSON as the universal interface. Script everything. Integrate with your existing tools.
Real Workflows, Not Chatbots
ayo orchestrates AI for actual work—support triage, document processing, research, and more.
Customer Support Triage
A squad of agents categorizes incoming messages, drafts responses, and escalates complex issues—automatically.
Document Processing Pipeline
A flow classifies documents, extracts key data, validates accuracy, and files the results—with each step handled by a specialist.
Automated Daily Digest
A trigger runs every evening—gathering updates, synthesizing insights, and distributing a summary to your team.
Works With Everything
Connect ayo to your existing tools and data sources.