freshcrate
Home > MCP Servers > AI-Agents-Orchestrator

AI-Agents-Orchestrator

πŸͺˆ 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

Description

πŸͺˆ 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.

README

AI Coding Tools Orchestrator and Agentic Team Runtime

Claude OpenAI Codex Gemini GitHub Copilot Ollama llama.cpp Python Model Context Protocol FastMCP Flask Pydantic Click Rich HTTPX Tenacity Structlog PyYAML Vue.js Nuxt Vite TailwindCSS Pinia Monaco Socket.IO Axios Prometheus Grafana Bandit Pylint Pytest MyPy Black Flake8 isort Pre-commit Zero Warnings Docker Kubernetes SQLite FTS5 BM25 Sentence Transformers psutil python-dotenv Colorama pyupgrade Terraform NGINX HAProxy GitHub Actions GitLab CI Jenkins Microsoft Azure systemd MIT License Mermaid Diagrams

Five independent systems β€” an AI Orchestrator, an Agentic Team runtime, an MCP Server, a Context Dashboard, and Graphify (project-to-graph intelligence engine) β€” that coordinate cloud and local AI coding assistants (Claude, Codex, Gemini, Copilot, Ollama, llama.cpp) to collaborate on software development tasks. Includes enterprise-grade agentic infrastructure with specialized agents, skills library, 34+ MCP tools, project-scoped graph-based context memory, and Graphify's 22-language code analysis with persistent queryable knowledge graphs, interactive visualization, and REST API.

Overview | Architecture | Agentic Infrastructure | System Comparison | Features | Quick Start | Project Structure | Configuration | Deployment | Testing | MCP Server


Overview

AI Coding Tools ships five independent systems in a single repository:

  1. The Orchestrator runs step-based workflows where AI agents execute tasks in sequence (implement, review, refine).
  2. The Agentic Team runs a free-communication runtime where role-based agents (Project Manager, Architect, Developer, QA, DevOps) discuss a task in turns until the team lead declares the work complete.
  3. Graphify turns any project directory into a queryable knowledge graph β€” classes, functions, imports, call graphs, and design rationale stored in a local SQLite database with FTS5 search.
  4. The MCP Server bridges both engines to IDE-based AI assistants.
  5. The Context Dashboard visualizes the graph memory. Each system carries its own adapters, configuration, UI, and CLI β€” they share zero code and zero imports.

Beyond the core engines, we provide a complete Agentic Infrastructure that empowers AI agents:

  • 9 Specialized Agents for web, backend, security, DevOps, AI/ML, database, mobile, performance, and documentation
  • 22 Reusable Skills across development, testing, security, DevOps, AI/ML, and documentation
  • 34+ MCP Tools for code analysis, security scanning, testing, DevOps, and context memory
  • Graph Context System with hybrid search (BM25 + semantic) for persistent memory and learning
  • Domain Rules encoding best practices for security, database, API design, performance, and AI/ML

Tip

Quickstart with the Orchestrator for structured workflows, or the Agentic Team for open-ended collaboration. Both systems benefit from the shared agentic infrastructure and context memory. See QUICKSTART.md for quick setup instructions to get started in ~2 minutes. Or, see #quick-start below for a detailed walkthrough.

Agentic Infrastructure

graph TB
    subgraph "🧠 Agentic Infrastructure"
        direction LR

        subgraph AGENTS["Specialized Agents (9)"]
            WEB[Web Frontend]
            API[Backend API]
            SEC[Security]
            OPS[DevOps]
            ML[AI/ML]
            DB[Database]
        end

        subgraph SKILLS["Skills Library (22)"]
            DEV[Development]
            TEST[Testing]
            SECS[Security]
            DEVOPS[DevOps]
            AIML[AI/ML]
            DOCS[Documentation]
        end

        subgraph TOOLS["MCP Tools (34+)"]
            CODE[Code Analysis]
            SCAN[Security Scan]
            TTOOLS[Testing]
            DTOOLS[DevOps]
            CTX[Context Memory]
        end

        subgraph CONTEXT["Graph Context"]
            GRAPH[(Graph Store)]
            SEARCH[Hybrid Search]
            EMBED[Embeddings]
        end
    end

    AGENTS --> SKILLS
    SKILLS --> TOOLS
    TOOLS --> CONTEXT
Loading
Component Count Description
Specialized Agents 9 Domain experts for web, backend, security, DevOps, AI/ML, database, mobile, performance, documentation
Skills 22 Reusable task templates across 6 categories
MCP Tools 34+ Code analysis, security scanning, testing, DevOps, context memory
Node Types 10 Conversation, Task, Mistake, Pattern, Decision, CodeSnippet, Preference, File, Concept, Project
Edge Types 12 RELATED_TO, CAUSED_BY, FIXED_BY, SIMILAR_TO, DEPENDS_ON, etc.

Context System

Both the Orchestrator and Agentic Team maintain independent graph-based context databases for persistent memory and cross-session learning. A unified Context Dashboard aggregates both stores for visualization.

graph TB
    subgraph "Context System Architecture"
        direction TB

        subgraph ORCH_CTX["Orchestrator Context<br/>~/.ai-orchestrator/context.db"]
            OM[models/ β€” Node & edge schemas]
            OS[store/ β€” Graph persistence]
            OX[search/ β€” BM25 + semantic + hybrid]
            OO[ops/ β€” Analytics, export, pruning, versioning]
        end

        subgraph TEAM_CTX["Agentic Team Context<br/>~/.agentic-team/context.db"]
            TM[models/ β€” Node & edge schemas]
            TS[store/ β€” Graph persistence]
            TX[search/ β€” BM25 + semantic + hybrid]
            TO[ops/ β€” Analytics, export, pruning, versioning]
        end

        subgraph DASH["Context Dashboard :5003"]
            APP[app.py β€” Flask aggregator]
            VIZ[templates/ β€” Interactive visualization]
        end
    end

    ORCH_CTX --> DASH
    TEAM_CTX --> DASH

    style ORCH_CTX fill:#1a365d,color:#fff
    style TEAM_CTX fill:#1a365d,color:#fff
    style DASH fill:#2d3748,color:#fff
Loading

Node Types β€” 10 types of knowledge stored in the graph:

Node Type Description
Conversation Past chat sessions with full message history
Task Completed tasks with outcomes, agent used, and duration
Mistake Errors with corrections and prevention strategies
Pattern Reusable code patterns and best practices
Decision Architectural decisions with rationale and trade-offs
CodeSnippet Useful code fragments with language and context
Preference Learned user preferences (tools, style, workflows)
File Source files with language, size, and framework metadata
Concept Abstract concepts and domain knowledge
Project Registered project roots with scan metadata

Edge Types β€” 12 relationship types connecting nodes:

Edge Type Description
RELATED_TO General semantic relationship
CAUSED_BY Causal chain (mistake β†’ root cause)
FIXED_BY Resolution link (mistake β†’ fix)
SIMILAR_TO Similarity link (patterns, tasks)
DEPENDS_ON Dependency relationship
PRECEDED_BY Temporal ordering (earlier event)
FOLLOWED_BY Temporal ordering (later event)
LEARNED_FROM Knowledge derivation (preference β†’ conversation)
USED_IN Usage relationship (pattern β†’ task)
REFERENCES Cross-reference between nodes
DERIVED_FROM Derived knowledge (snippet β†’ pattern)
EVOLVED_INTO Evolution tracking (v1 pattern β†’ v2)

Hybrid Search combines three retrieval strategies via Reciprocal Rank Fusion (RRF):

  1. BM25 β€” Keyword-based search using term frequency–inverse document frequency
  2. Semantic β€” Embedding-based similarity using vector cosine distance
  3. Hybrid β€” Fused ranking of BM25 + semantic results using RRF for best-of-both-worlds retrieval

Project-Scoped Context Graphs

Both systems support project-scoped context graphs for full portability. When a user points the system at their project directory, agents automatically scan and build a rich context graph of the codebase.

graph TB
    subgraph "Project Context Scoping"
        direction TB

        USER[User configures PROJECT_PATH] --> SCAN[ProjectScanner]
        SCAN --> PID["project_id = SHA-256[:16] of path"]

        subgraph "Isolated Project Graphs"
            P1["Project A<br/>pid=a1b2c3..."]
            P2["Project B<br/>pid=d4e5f6..."]
            P3["Global Scope<br/>pid='' (no project)"]
        end

        PID --> P1 & P2
        SCAN --> FILES[File Nodes]
        SCAN --> PATTERNS[Pattern Nodes]
        SCAN --> DECISIONS[Decision Nodes]
        SCAN --> EDGES[Relationship Edges]
    end

    style P1 fill:#2b6cb0,stroke:#2c5282,color:#fff
    style P2 fill:#276749,stroke:#22543d,color:#fff
    style P3 fill:#744210,stroke:#975a16,color:#fff
Loading

Key features:

  • Deterministic IDs: project_id is a SHA-256 prefix of the normalized absolute path β€” idempotent and reproducible
  • Multi-project isolation: Each project gets its own graph partition; queries filter by project_id
  • Global scope: Nodes with project_id="" are universal (patterns, reference knowledge) β€” shared across all projects
  • Automatic scanning: ProjectScanner detects languages, frameworks, file structure, and config patterns
  • Portability: Set PROJECT_PATH environment variable or settings.project_path in config YAML β€” the system handles the rest
  • Incremental updates: rescan_project() rebuilds the graph atomically; delete_project_graph() cleanly removes all project nodes

Tip

Auto-seeding: Run scripts/seed_context_graphs.py to populate both context databases with generic reference knowledge (patterns, mistakes, decisions) on first use. Seed data contains no hallucination-prone fake tasks or conversations β€” only universally applicable best practices.

Note

Context Dashboard: Launch with python -m context_dashboard (port 5003) to visualize both context graphs, inspect nodes/edges, and search across all stored knowledge. See context_dashboard/README.md for details.

Skills Library & Agent Definitions

AI coding agents are enhanced with specialized role definitions, reusable skills, and domain rules that are automatically loaded based on context.

graph LR
    subgraph "Agent Ecosystem"
        direction TB

        subgraph CLAUDE[".claude/"]
            CA["agents/ (11)"]
            CS["skills/ (23)"]
            CR["rules/ (11)"]
            CC[CLAUDE.md]
        end

        subgraph CODEX[".codex/"]
            XA["agents/ (13)"]
            XC[config.toml]
            XR[rules/]
        end

        AGENTS_MD[AGENTS.md β€” Shared instructions]
    end

    CA --> CS
    CA --> CR
    AGENTS_MD --> CLAUDE
    AGENTS_MD --> CODEX

    style CLAUDE fill:#7c3aed,color:#fff
    style CODEX fill:#059669,color:#fff
Loading

Claude Agents β€” 11 specialized agents in .claude/agents/:

Agent File Domain
Web Frontend web-frontend.md React, Vue, CSS, accessibility, responsive design
Backend API backend-api.md REST, GraphQL, databases, Flask/FastAPI
Security Specialist security-specialist.md OWASP, vulnerability analysis, secure coding
DevOps Infrastructure devops-infrastructure.md Docker, Kubernetes, CI/CD, cloud
AI/ML Engineer ai-ml-engineer.md ML pipelines, embeddings, LLM integration
Database Architect database-architect.md Schema design, query optimization, migrations
Mobile Developer mobile-developer.md iOS, Android, React Native, Flutter
Performance Engineer performance-engineer.md Profiling, load testing, optimization
Documentation Writer documentation-writer.md API docs, architecture, tutorials
Code Reviewer code-reviewer.md Code quality, best practices, PR reviews
Test Runner test-runner.md Test execution, coverage, failure diagnosis

Codex Agents β€” 13 specialized agents in .codex/agents/:

Agent File Domain
Code Reviewer code-reviewer.toml Code quality and review automation
Explorer explorer.toml Codebase exploration and research
Security Specialist security-specialist.toml Security auditing and vulnerability scanning
Web Frontend web-frontend.toml Frontend development and UI patterns
DevOps Infrastructure devops-infrastructure.toml Infrastructure and deployment automation
Implementer implementer.toml Feature implementation and coding
Database Architect database-architect.toml Database design and optimization
Performance Engineer performance-engineer.toml Performance profiling and optimization
Test Runner test-runner.toml Test suite execution and diagnosis
AI/ML Engineer ai-ml-engineer.toml ML pipelines and AI system design
Backend API backend-api.toml Backend services and API development
Documentation Writer documentation-writer.toml Technical documentation
Mobile Developer mobile-developer.toml Mobile application development

Skills Library β€” 24 reusable skill templates in .claude/skills/ across 7 categories:

Category Count Skills
Development 6 react-components, rest-api-design, python-async, database-queries, graphql-development, error-handling
Testing 4 unit-testing, integration-testing, test-driven-development, performance-testing
Security 4 input-validation, authentication, secure-coding, vulnerability-assessment
DevOps 3 docker-containerization, ci-cd-pipelines, kubernetes-deployment
AI/ML 3 embeddings-retrieval, llm-integration, rag-pipeline
Documentation 3 api-documentation, architecture-docs, code-documentation
Context 1 context-graph-builder

Four additional standalone skills (context-graph-builder, generate-reports, health-check, run-tests) provide operational task automation.

Domain Rules β€” 11 rule files in .claude/rules/ encoding best practices:

Rule File Enforces
Adapters adapters.md Adapter pattern, base class contracts
API Design api-design.md RESTful conventions, versioning, error formats
Testing testing.md Pytest patterns, coverage requirements, fixtures
Performance performance.md Profiling, caching, async patterns
Config config.md YAML config, environment variables, validation
AI/ML ai-ml.md Model integration, embeddings, prompt patterns
Observability observability.md Logging, metrics, health checks
Frontend frontend.md Component patterns, accessibility, state management
CI/CD ci-cd.md Pipeline design, deployment gates, rollback
Security security.md Input validation, auth, secrets management
Database database.md Schema design, migrations, query safety

Note

Agents automatically inherit access to all skills and rules in their scope. When Claude Code is invoked with a specialized agent (e.g., @security-specialist), it loads the agent definition, relevant skills, and applicable domain rules to provide expert-level guidance.

Configuration Files

File Purpose
.claude/CLAUDE.md Main instructions for Claude Code β€” imports AGENTS.md and sets project context
.claude/settings.json Claude project settings (permissions, model preferences)
.codex/config.toml Codex project configuration
.codex/agents/*.toml Codex agent role definitions with system prompts
AGENTS.md Shared instructions read by all AI coding agents (Codex, Gemini CLI, etc.)
AGENTIC_INFRA.md Full documentation of the agentic infrastructure

Architecture

High-Level Overview

graph TD
    subgraph Repository["AI Coding Tools Repository"]
        direction TB

        subgraph Orchestrator["orchestrator/"]
            O_CLI["CLI Shell"]
            O_UI["Web UI<br/>Nuxt 3 + Flask + Socket.IO"]
            O_CORE["Core Engine<br/>Workflow Manager<br/>Task Manager"]
            O_ADAPT["Adapters<br/>Claude | Codex | Gemini<br/>Copilot | Ollama | llama.cpp"]
            O_RESIL["Resilience<br/>Retry | Fallback | Offline"]
            O_OBS["Observability<br/>Prometheus | Logging | Health"]
            O_SEC["Security Module<br/>Validation | Rate Limiting | Audit"]
            O_INFRA["Infra<br/>Cache | Async Executor | Config Manager"]
            O_CONF["orchestrator/config/agents.yaml"]
        end

        subgraph AgenticTeam["agentic_team/"]
            A_CLI["CLI REPL"]
            A_UI["Web UI<br/>Nuxt 3 + Flask + Socket.IO"]
            A_ENGINE["Engine<br/>Free Communication<br/>Lead-Gated Output"]
            A_ADAPT["Adapters<br/>Claude | Codex | Gemini<br/>Copilot | Ollama | llama.cpp"]
            A_FALLBACK["Fallback + Offline"]
            A_CONF["orchestrator/config/agents.yaml"]
        end
    end

    O_CLI --> O_CORE
    O_UI --> O_CORE
    O_CORE --> O_ADAPT
    O_CORE --> O_RESIL
    O_CORE --> O_OBS
    O_CORE --> O_SEC
    O_CORE --> O_INFRA
    O_ADAPT --> ExtCloud["Cloud CLIs<br/>claude | codex | gemini | copilot"]
    O_ADAPT --> ExtLocal["Local Backends<br/>Ollama | llama.cpp"]

    A_CLI --> A_ENGINE
    A_UI --> A_ENGINE
    A_ENGINE --> A_ADAPT
    A_ENGINE --> A_FALLBACK
    A_ADAPT --> ExtCloud
    A_ADAPT --> ExtLocal

    style Orchestrator fill:#1a1a2e,stroke:#16213e,color:#e0e0e0
    style AgenticTeam fill:#1a2e1a,stroke:#162e16,color:#e0e0e0
Loading

Orchestrator Workflow Execution

The Orchestrator processes tasks through a configurable pipeline of AI agents. Each step in a workflow maps to a specific agent and role.

sequenceDiagram
    participant User
    participant CLI as CLI / Web UI
    participant Engine as Core Engine
    participant WF as Workflow Manager
    participant Codex as Codex Adapter
    participant Gemini as Gemini Adapter
    participant Claude as Claude Adapter
    par

Release History

VersionChangesUrgencyDate
v1.0.0## What's Changed * introduces comprehensive CI/CD pipelines for CircleCI, GitHub Actions (Azure), and GitLab, enabling automated testing, security scanning, Docker image building, and blue-green deployments for the AI Orchestrator project by @hoangsonww in https://github.com/hoangsonww/AI-Agents-Orchestrator/pull/1 * docs: update documentation for clarity and consistency and add GitHub CI by @hoangsonww in https://github.com/hoangsonww/AI-Agents-Orchestrator/pull/2 ## New Contributors * @Low11/29/2025

Dependencies & License Audit

Loading dependencies...

Similar Packages

refragπŸš€ Enhance retrieval with REFRAG, using micro-chunking and fast indexing for optimized RAG systems that improve efficiency and effectiveness.main@2026-04-21
mcp-audit🌟 Track token consumption in real-time with MCP Audit. Diagnose context bloat and unexpected spikes across MCP servers and tools efficiently.main@2026-04-21
mcp-rag-agentπŸ” Build a production-ready RAG system that combines LangGraph and MCP integration for precise, context-aware AI-driven question answering.main@2026-04-21
Cognio🧠 Enhance AI conversations with Cognio, a persistent memory server that retains context and enables meaningful semantic search across sessions.main@2026-04-21
fast-mcp-telegramTelegram MCP Server and HTTP-MTProto bridge | Multi-user, web setup, Docker and MTProto-Proxy ready0.16.4