Skip to main content

Multi-Agent Collaboration CLI with flock-based locking and event-driven workflow

Project description

Mai CLI

English | 简体中文

Multi-Agent Collaboration CLI — flock-based coordination, event-driven workflow, zero overhead.

Mai is a command-line tool that coordinates multiple AI agents working on a shared project. It provides atomic locking, queue-based issue routing, per-agent heartbeat timeouts, and an automated daily summary loop — all backed by a simple file-based store.


Features

  • Atomic flock locks — race-condition-free claim/complete cycles via POSIX fcntl
  • Queue-based routing — issues route to the right agent with configurable SLA per queue
  • Heartbeat-aware guardian — stale locks auto-release after heartbeat × 1.5 minutes
  • Event-driven daily summary — ordered turn-taking with idempotent trigger/collect
  • Async mirror.mai/ internal store syncs to async/ for human visibility
  • Configurable via JSON — all rules externalized to config.json; no code changes needed
  • Dual output format--format json for machine consumption, text for humans
  • Dry-run mode--dry-run previews every mutation without side effects

Installation

pip install mai-cli

Or install from source:

git clone https://github.com/yourname/mai-cli.git
cd mai-cli
pip install -e .

Quick Start

Step 1 — Initialize a project

mai init MyProject

Step 2 — Register an agent

mai --project MyProject agent add alice --heartbeat-minutes 30

Step 3 — Create an issue

mai --project MyProject issue new questions "How should we handle input buffering?"

Step 4 — Have the assigned agent claim it

mai --project MyProject issue claim REQ-001

Step 5 — Mark it done

mai --project MyProject issue complete REQ-001 "Decision: ring buffer, 60Hz polling"

Step 6 — Inspect queues

mai --project MyProject queue check

Architecture

.mai/                        async/
├── queues/<queue>/  Issue files  <queue>/  Human-visible mirror
├── locks/           flock files  (internal only)
├── processing/      Active issues  <queue>/
├── decisions/       Conclusion logs  decisions/
├── history/         Audit logs  history/
├── events/          Daily-summary triggers  (internal only)
└── config.json      All collaboration rules

Lock protocol: When an agent claims an issue, Mai acquires an flock(2)-based file lock. The lock expires after heartbeat × 1.5 minutes if the agent fails to heartbeat. The lock guardian cron command automatically releases stale locks.

Daily summary flow: trigger → each agent write in order → collect merges all summaries into a single report.


Command Reference

Global Options

mai [-v|--version] [--project <path>] [--format json|text] [--dry-run] <subcommand>

Issue

mai issue new <queue> <title> [--ref REQ-XXX]
mai issue amend <issue-id> <remark>
mai issue claim <issue-id>
mai issue complete <issue-id> <conclusion>
mai issue list [queue]
mai issue show <issue-id>
mai issue escalate <issue-id>

Queue

mai queue check [queue] [--overdue]
mai queue blockers

Lock

mai lock check <issue-id>
mai lock force-release <issue-id>
mai lock guardian

Log

mai log history [--date YYYY-MM-DD] [--agent NAME]
mai log write <agent> <type> <summary> [status]

Daily Summary

mai daily-summary trigger
mai daily-summary write <agent> <content...>  # Protected by flock
mai daily-summary read [<agent>|.|--all]

Escalation

mai escalation gen <issue-id>

Exec

mai exec safe-check <command>

Project / Agent

mai init [project-name]
mai project init <project-name>
mai agent add <name> [--heartbeat-minutes 30]

Configuration

Edit .mai/config.json in your project root:

{
  "queues": {
    "questions": {
      "handler": "alice",
      "sla_minutes": 120,
      "id_prefix": "REQ"
    }
  },
  "agents": {
    "alice": { "heartbeat_minutes": 30 }
  },
  "daily_summary_order": ["alice", "bob"]
}

Legacy field compatibility

ownerhandler, sla_hourssla_minutes are automatically converted.


Supported Platforms

  • OS: Linux / macOS (POSIX required for flock)
  • Python: 3.8, 3.9, 3.10, 3.11, 3.12

License

MIT License

MIT License — see LICENSE for the full text.

Project details


Download files

Download the file for your platform. If you're not sure which to choose, learn more about installing packages.

Source Distribution

mai_cli-1.4.0.tar.gz (24.5 kB view details)

Uploaded Source

Built Distribution

If you're not sure about the file name format, learn more about wheel file names.

mai_cli-1.4.0-py3-none-any.whl (26.7 kB view details)

Uploaded Python 3

File details

Details for the file mai_cli-1.4.0.tar.gz.

File metadata

  • Download URL: mai_cli-1.4.0.tar.gz
  • Upload date:
  • Size: 24.5 kB
  • Tags: Source
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/6.2.0 CPython/3.12.3

File hashes

Hashes for mai_cli-1.4.0.tar.gz
Algorithm Hash digest
SHA256 d083052100d030665d3098725b2d3c04685997fe8b2feeee5254edadec456fef
MD5 b2ed3e8ab4586365a0ea744eae868964
BLAKE2b-256 e32d4881946f3a71de47551748937aaa8ccb0c099e5e9cb0dd47132af23d1628

See more details on using hashes here.

File details

Details for the file mai_cli-1.4.0-py3-none-any.whl.

File metadata

  • Download URL: mai_cli-1.4.0-py3-none-any.whl
  • Upload date:
  • Size: 26.7 kB
  • Tags: Python 3
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/6.2.0 CPython/3.12.3

File hashes

Hashes for mai_cli-1.4.0-py3-none-any.whl
Algorithm Hash digest
SHA256 ca20db254cd55a889cc9c05351ee7bb07d636f648bdcc957d9e3439a7c18a93b
MD5 967db7425b0268b2169c93ccb1f6ba8e
BLAKE2b-256 15c4950adce19f4d158eea1eaf2817b54c353e9b403e684985109af259a2702f

See more details on using hashes here.

Supported by

AWS Cloud computing and Security Sponsor Datadog Monitoring Depot Continuous Integration Fastly CDN Google Download Analytics Pingdom Monitoring Sentry Error logging StatusPage Status page