AI-Agents-Orchestrator and agent-orchestrator

These two tools are competitors, as both aim to provide an intelligent orchestration system for coordinating multiple AI coding assistants, but they differ in their user interface options (REPL/Vue/Nuxt for A versus CLI for B) and B specifically highlights a "next-man-up failover" feature.

agent-orchestrator
43
Emerging
Maintenance 13/25
Adoption 6/25
Maturity 9/25
Community 17/25
Maintenance 13/25
Adoption 7/25
Maturity 9/25
Community 14/25
Stars: 17
Forks: 11
Downloads:
Commits (30d): 0
Language: Python
License: MIT
Stars: 36
Forks: 6
Downloads:
Commits (30d): 0
Language: Python
License: MIT
No Package No Dependents
No Package No Dependents

About AI-Agents-Orchestrator

hoangsonww/AI-Agents-Orchestrator

🪈 Intelligent orchestration system that coordinates multiple AI coding assistants (Claude, Codex, Gemini CLI, Copilot CLI) to collaborate on complex software development tasks via REPL or a Vue/Nuxt UI dashboard. Also includes an Agentic Team runtime with role-based multi-agent open communication & lead-gated final responses.

Supports both cloud CLIs (Claude, Codex, Gemini, Copilot) and local LLM backends (Ollama, llama.cpp-compatible) with automatic failover and offline operation. Built on a Flask backend with Socket.IO/WebSocket real-time communication, Pydantic-validated configuration, and a Vue 3/Nuxt dashboard featuring Monaco editor and Prometheus metrics integration. The standalone Agentic Team runtime enables role-based multi-agent communication with lead-gated response approval, separate from the main orchestrator workflow execution path.

About agent-orchestrator

willynikes2/agent-orchestrator

Three AI agents. One brain. Zero downtime. Multi-agent CLI orchestrator with next-man-up failover for Claude, Codex, and Gemini.

Implements role-based routing with four specialized agent chains (orchestrator, implementation, UI/docs, review) that automatically detect rate limits, quota exhaustion, and auth failures with configurable cooldown recovery. Maintains shared context across agents through an integrated knowledge base server, and uses a single ~1100-line Python file for easy inspection and extension without external dependencies beyond the three CLI subscriptions.

Scores updated daily from GitHub, PyPI, and npm data. How scores work