The open-source ACP orchestrator. One API. Five agents. Infinite possibilities.

---

What is AIntegriX?

AIntegriX is the first open-source ACP orchestrator — a server that coordinates multiple Agent Client Protocol agents through a single API.

What is ACP?

The Agent Client Protocol (ACP) is the open standard that connects code editors with AI coding agents — the same way LSP standardized language servers. Every major coding agent now speaks ACP: Kiro, GitHub Copilot, Claude Code, OpenCode, Codex CLI, and 30+ more.

The Problem

Each ACP agent runs independently. You can't:

• Ask one agent to delegate work to another
• Send the same prompt to multiple agents and compare
• Chain agents in a pipeline (generate → review → fix)
• Auto-trigger agents on Git events

The Solution

AIntegriX acts as an ACP multiplexer. It spawns agents as subprocesses, speaks JSON-RPC 2.0 over stdio with each one, and exposes them all through a single MCP/REST endpoint.

Your Agent (any MCP-compatible tool)
       │
       ▼ MCP / REST
┌─────────────────────────────────┐
│         AIntegriX               │
│   Route • Orchestrate • Stream  │
│         (ACP Client)            │
└──┬──────┬──────┬──────┬──────┬──┘
   │      │      │      │      │   JSON-RPC 2.0 / stdio
   ▼      ▼      ▼      ▼      ▼
 Kiro  Copilot OpenCode Claude Codex
 (ACP)  (ACP)   (ACP)  (ACP)  (ACP)

One prompt. Any agent. Real results.

---

Why AIntegriX?

Problem	Solution
Each agent has different strengths	Smart routing picks the best agent for each task
Can't compare agent responses	Orchestration sends to N agents in parallel
No way to chain agent work	Pipelines feed output from one agent to the next
Agents can't read your latest code	Auto-clone from your Git remote or direct local filesystem
Responses arrive all at once	SSE streaming shows chunks in real-time
Manual code review requests	Webhooks auto-trigger review on MR open

---

Workflow

┌─────────────────────────────────────────────────────────────┐
│                    YOUR DEVELOPMENT FLOW                      │
├─────────────────────────────────────────────────────────────┤
│                                                              │
│  1. Code locally                                             │
│       │                                                      │
│  2. Ask AIntegriX:                                           │
│       "Review src/ for security issues"                      │
│       │                                                      │
│  3. AIntegriX routes to Claude (security expert)             │
│       │                                                      │
│  4. Claude reads your files, analyzes, responds              │
│       │                                                      │
│  5. You get the review in your agent's context               │
│                                                              │
│  ─── OR ───                                                  │
│                                                              │
│  Pipeline: OpenCode generates → Claude reviews → Kiro fixes  │
│                                                              │
│  ─── OR ───                                                  │
│                                                              │
│  Race: Send to 3 agents, first response wins                 │
│                                                              │
└─────────────────────────────────────────────────────────────┘

---

Quick Start

Local (recommended for development)

# Install
git clone git@github.com:alfonsodg/aintegrix.git
cd aintegrix
cargo build --release
./configs/install.sh ~/.local/share/aintegrix

# Add to your agent's MCP config
{
  "mcpServers": {
    "aintegrix": {
      "command": "mcp-proxy",
      "args": ["-H", "Authorization", "Bearer aintegrix-local-key-2026",
               "--transport", "streamablehttp", "http://localhost:8050/mcp"],
      "env": {}
    }
  }
}

Remote (for teams / CI)

{
  "mcpServers": {
    "aintegrix": {
      "url": "https://your-server.example.com/mcp",
      "type": "http",
      "headers": {"Authorization": "Bearer <token>"}
    }
  }
}

---

Agents

Agent	Model	Best For
🧠 Kiro	claude-opus-4.6	Rust, architecture, complex reasoning
🤖 Copilot	gpt-5.3-codex	Frontend, React, quick edits
⚡ OpenCode	mimo-v2.5-pro	Fast analysis, multi-file reads
🔍 Claude	minimax-2.7	Security review, deep analysis
🛠️ Codex	gpt-5.5-xhigh	Python, refactoring, generation

---

Features

Core

• 5 ACP agents with real subprocess management
• MCP server — any agent can use AIntegriX as a tool
• REST API with Bearer auth
• SSE streaming of agent responses in real-time

Orchestration

• Parallel — send to N agents, collect all responses
• Race — first response wins, cancel others
• Jury — N agents respond, a judge picks the best
• Pipelines — sequential multi-step workflows

Intelligence

• Auto-routing — YAML rules pick the best agent by keywords/file patterns
• Prompt rewriting — per-agent prefix/suffix
• Git-aware sessions — inject branch, commits, diff as context
• Context injection — auto-load steering files
• ACP capability negotiation — auto-detect and use agent features (set_model, embeddedContext, fork, resume, mcpServers)

Operations

• Auto-clone repos — fresh checkout from your Git remote (remote mode)
• Local filesystem — direct access to your code (local mode)
• Webhook triggers — MR/PR → auto code review
• Session fork — try same conversation with different agent
• Cost tracking — usage per agent/session/model
• Live status — agent idle/busy with session counts

---

API

Method	Endpoint	Description
POST	/api/v1/sessions	Create session
POST	/api/v1/sessions/{id}/prompt	Send prompt
POST	/api/v1/sessions/{id}/fork	Fork to another agent
POST	/api/v1/sessions/{id}/model	Change model mid-session
POST	/api/v1/orchestrate	Multi-agent (parallel/race/jury)
POST	/api/v1/pipelines	Sequential agent chaining
POST	/api/v1/stream	Create + stream SSE
POST	/api/v1/webhooks/git	Receive webhook events
GET	/api/v1/agents/status	Live agent status
GET	/api/v1/usage	Cost tracking
POST	/mcp	MCP JSON-RPC endpoint

---

Documentation

• Installation
• Configuration
• API Reference
• Architecture
• Development Standards
• Diagrams

---

Tech Stack

Layer	Technology
Language	Rust (latest stable)
Runtime	tokio
HTTP	axum
Protocol	ACP (JSON-RPC 2.0 over stdio)
Database	SQLite (sqlx)
Config	YAML

---

License

Apache-2.0

---

_{Built with 🦀 Rust • Powered by ACP}