AI-Agents-Orchestrator
Active·★ 96·MIT·Updated 2026-09-27
AI Coding Tools Orchestrator and Agentic Team Runtime is a self-contained system that coordinates cloud and local AI coding assistants through step-based workflows or free-role communication. It features enterprise-grade agentic infrastructure with specialized agents, skills library, MCP tools, and project-scoped graph-based context memory. Both the Orchestrator and Agentic Team share zero code and run independently with their own CLIs, Web UIs, configurations, and context databases.
#agentic-ai#ai-agents#claude#codex#copilot#docker#flake8#flask
01
Features
017 built-in workflows with customizable step-based pipelines
02Multi-agent support (Claude, Codex, Gemini, Copilot, Ollama, llama.cpp)
03Interactive CLI (REPL) and Web UI with real-time streaming
04Resilience with retry, fallback, and offline mode
05Enterprise observability with Prometheus metrics, structured logging, and HTML reports
02
Compatibility
Claude
Claude (Anthropic)
Verified via docs
Codex
OpenAI Codex
Verified via docs
Gemini
Gemini (Google)
Verified via docs
Copilot
GitHub Copilot
Verified via docs
Ollama
Ollama (Local)
Verified via docs
llama.cpp
llama.cpp (GGUF)
Verified via docs
03
Quick start
1
$ git clone https://github.com/hoangsonww/AI-Agents-Orchestrator.git
2
$ cd AI-Agents-Orchestrator
3
$ python3 -m venv venv
4
$ source venv/bin/activate
5
$ pip install -r requirements.txt
6
$ chmod +x ai-orchestrator
04
Use cases
↳Structured code development pipelines (implement, review, refine)
↳Open-ended multi-role collaboration (PM, Architect, Developer, QA, DevOps)
↳Code review, documentation generation, and local-only development with offline mode
05
Alternatives
⚡Top VS:
better-code-review-graph★ 76
Knowledge graph for token-efficient code reviews — fixed search, qualified call resolution, dual-mode embedding (ONNX + multi-provider cloud)
zabbix-mcp-server★ 244
MCP server for the complete Zabbix API — 220 tools, multi-server support, bearer auth, systemd ready. Works with ChatGPT, Claude, VS Code, Codex, JetBrains and any MCP client.
agency-orchestrator★ 2.4k
One sentence → multiple AI roles collaborate → complete plan in minutes. 179 expert roles, zero-code YAML, 9 LLM providers. 一句话让多个AI角色自动协作，几分钟出完整方案。
systemprompt-template★ 29
AI Governance Infrastructure — local evaluation. The governance layer for AI agents: a single compiled Rust binary that authenticates, authorises, rate-limits, logs, and costs every AI interaction. Self-hosted, air-gap capable, provider-agnostic.
code-context-engine★ 435
Save 94% on AI coding tokens. Index your codebase, agents search instead of reading files. Works with Claude Code, Codex, Copilot, Cursor, Gemini CLI. Local MCP server, free, open source.
pdf-mcp★ 155
MCP server that lets Claude Code and other AI agents read large PDFs without hitting context limits. Chunked reading, hybrid search, OCR, table and image extraction, SQLite cache.
Comments
Log in to leave a comment
No comments yet. Be the first!