@QingQ77: Manage AI coding tasks through the browser, using multi-agent collaboration to complete the full workflow from planning, coding to QA review. https://github.com/dataseeek/MagesticAI… MagesticAI - a browser-based AI task management and agent orchestration platform.
Summary
MagesticAI is a browser-based AI task management and multi-agent orchestration platform that supports full workflow collaboration from planning, coding to QA.
View Cached Full Text
Cached at: 05/21/26, 09:40 PM
Manage AI coding tasks through a browser, using multi-agent collaboration to complete the entire workflow from planning, coding to QA review. https://github.com/dataseeek/MagesticAI… MagesticAI is a browser-based AI task management and agent orchestration platform, adopting the SDD (Spec-Driven Development) model. The platform provides a Kanban task board, real-time terminal, Monaco code editor and other interfaces, with the backend composed of three agents – Planner, Coder, and QA – collaborating to complete tasks.
Overview
MagesticAI is a browser-based platform for managing AI-powered coding tasks through coordinated autonomous agents. It provides a modern web interface for task creation, execution monitoring, terminal access, and code review - all accessible from any browser.
Key Features
- Kanban Task Board - Visual task management with drag-and-drop
- Multi-Agent Orchestration - Planner, Coder, and QA agents work together
- Real-time Terminal - Full PTY terminal access in browser
- Monaco Code Editor - VS Code-like editing experience
- Git Worktree Isolation - Safe, isolated builds per task
- AI-Powered QA - Automated code review and validation
- Multi-Provider Support - Claude, Codex, Gemini, and any OpenAI-compatible endpoint (Ollama, LM Studio, vLLM, OpenRouter, Together, Groq, LocalAI…) with native agentic tool calling (Read, Write, Edit, Bash, Glob, Grep) — no API fallback needed
- Graphiti Memory - Cross-session learning and knowledge retention
- Multi-Project Support - Manage multiple repositories
- Internationalization - English, French, Portuguese (Brazil)
Screenshots
| View | Preview |
|---|---|
| Kanban task board | kanban |
| Task creation wizard | task-wizard |
| Built-in PTY terminal | terminal |
| Monaco code editor | editor |
| Settings & onboarding | settings |
How does it compare?
MagesticAI sits next to two open-source projects with overlapping goals but very different shapes:
| Spec Kit (https://github.com/github/spec-kit) | Compozy (https://github.com/compozy/compozy) | MagesticAI | |
|---|---|---|---|
| Primary interface | CLI (specify) | CLI / single Go binary | Browser UI |
| Generates specs | Yes — its core purpose | Partial — workflow artifacts | Yes — multi-agent spec authoring (3–8 stages, auto-scaled by complexity) |
| Executes the spec | No — hands off to your external agent (Copilot / Claude Code / Cursor) | Orchestrates external agents via the ACP protocol | Yes — built-in Planner / Coder / QA Reviewer / QA Fixer |
| Task isolation | None | Workflow state in a daemon | Git worktree per task |
| LLM provider model | Inherited from whatever agent you hand off to | Inherited from the agent it orchestrates | Direct multi-provider: Claude, Codex CLI, Gemini, any OpenAI-compatible endpoint (Ollama, LM Studio, vLLM, OpenRouter, Together, Groq, LocalAI…) |
| License | MIT | MIT | AGPL-3.0 |
The short version: Spec Kit is great for authoring specs you’ll execute with an existing agent. Compozy is great if you want a terminal-first multi-agent runner driving external agents. MagesticAI is the one to pick if you want the full spec → plan → code → QA loop in one self-hosted browser app, with first-class support for local and OpenAI-compatible LLMs.
Architecture
┌─────────────────────────────────────────────────────────────────┐
│ MagesticAI │
├─────────────────────────────────────────────────────────────────┤
│ │
│ Browser (React 19 + Vite) Port 3100 │
│ ├── Kanban Board │
│ ├── Terminal Grid (xterm.js) │
│ ├── Code Editor (Monaco) │
│ ├── Task Detail Modal │
│ └── Real-time WebSocket Updates │
│ │
├─────────────────────────────────────────────────────────────────┤
│ │
│ Web Server (FastAPI) Port 3101 │
│ ├── REST API (/api/*) │
│ ├── WebSocket Endpoints (/ws/*) │
│ ├── PTY Session Management │
│ ├── Agent Execution Service │
│ └── File Operations │
│ │
├─────────────────────────────────────────────────────────────────┤
│ │
│ Backend Agents (Python) │
│ ├── Claude Agent SDK Integration │
│ ├── Multi-Provider Engine (Claude/Codex/Gemini/OpenAI-compat) │
│ ├── Local LLM Tool Calling (Read/Write/Edit/Bash/Glob/Grep) │
│ ├── Planner Agent (creates implementation plans) │
│ ├── Coder Agent (implements subtasks) │
│ ├── QA Reviewer (validates code) │
│ ├── QA Fixer (resolves issues) │
│ └── Graphiti Memory (LadybugDB) │
│ │
└─────────────────────────────────────────────────────────────────┘
Project Structure
MagesticAI/
├── apps/
│ ├── frontend-web/ # React web frontend (Vite)
│ │ ├── src/
│ │ │ ├── components/ # 57+ React components
│ │ │ ├── stores/ # 14 Zustand stores
│ │ │ ├── hooks/ # Custom React hooks
│ │ │ ├── lib/ # API client, WebSocket
│ │ │ └── shared/ # Types, i18n, constants
│ │ └── package.json
│ │
│ ├── web-server/ # FastAPI backend
│ │ └── server/
│ │ ├── routes/ # REST API endpoints
│ │ ├── websockets/ # WebSocket handlers
│ │ ├── services/ # Agent execution service
│ │ └── pty/ # Terminal management
│ │
│ ├── backend/ # Python agent system
│ │ ├── agents/ # Planner, Coder agents
│ │ ├── providers/ # Multi-LLM adapters (Claude, Codex, Gemini, OpenAI-compatible inc. Ollama)
│ │ ├── tools/ # Reusable tool executor (Read, Write, Edit, Bash, Glob, Grep)
│ │ ├── qa/ # QA Reviewer, Fixer
│ │ ├── spec/ # Spec creation pipeline
│ │ ├── security/ # Command validation & path boundary
│ │ ├── integrations/ # Graphiti, Linear, GitHub
│ │ └── prompts/ # Agent system prompts
│ │
│ ├── guides/ # Extended documentation
├── tests/ # Test suite
├── scripts/ # Build scripts
├── Dockerfile # Container image definition
├── docker-compose.yml # Container orchestration
├── CHANGELOG.md # Version history
├── RELEASE.md # Release process guide
├── AGENTS.md # AI agent instructions
├── GEMINI.md # Gemini AI instructions
├── ContainerAPP.md # Docker deployment guide
└── package.json # Root package
Task Lifecycle
1. CREATE → TaskCreationWizard generates spec
2. PLAN → Planner Agent creates subtask plan
3. CODE → Coder Agent implements in isolated worktree
4. QA REVIEW → QA Agent validates against acceptance criteria
5. FIX → QA Fixer resolves any issues (loops back to QA)
6. MERGE → Human reviews and merges to main branch
API Endpoints
REST API (/api/)
| Endpoint | Method | Description |
|---|---|---|
/api/projects | GET/POST | List/create projects |
/api/projects/{id} | GET/PUT/DELETE | Project CRUD |
/api/tasks | GET/POST | List/create tasks |
/api/tasks/{id}/start | POST | Start task execution |
/api/terminals | GET/POST | Terminal management |
/api/files/list | GET | Directory listing |
/api/files/read | GET | Read file content |
/api/settings | GET/PUT | App settings |
WebSocket Endpoints (/ws/)
| Endpoint | Purpose |
|---|---|
/ws/events | Global event broadcasting |
/ws/terminal/{id} | Terminal I/O |
/ws/tasks/{id}/progress | Task progress streaming |
/ws/tasks/{id}/logs | Task log streaming |
Scripts
# Development
npm run dev # Start web frontend (dev mode)
# Installation
npm run install:all # Install all dependencies
npm run install:backend # Backend only
npm run install:frontend # Frontend only
# Testing
npm run test # Run frontend tests
npm run test:backend # Run backend tests
# Production
npm run build # Build frontend for production
Troubleshooting
| Issue | Solution |
|---|---|
| Cannot connect to backend | Ensure web-server running on port 3101 |
| Invalid token | Get token from ~/.magestic-ai/.token |
| WebSocket failed | Check token in URL, verify ports accessible |
| Task stuck | Check agent logs |
Similar Articles
I Built MagesticAI. A Cloud Web-Based Agentic DevOps Orchestrator that actually helped me develop Itself.
MagesticAI is an open-source, browser-based multi-agent AI coding platform that uses Planner, Coder, and QA Reviewer agents in coordinated sessions with isolated git worktrees and supports multiple LLMs including OpenAI-compatible endpoints.
@justloveabit: With This Open-Source Tool, I Got a Team of AIs to Work for Me. Here's the deal: I've been tinkering with various AI agents lately. Multiple Claude Code windows open, Codex running, occasionally using Cursor. The result? Total chaos—I had no idea what each agent was doing or how much it was costing. Restar…
This article introduces Paperclip, an open-source tool designed to centrally manage and orchestrate multiple AI agents. By simulating a corporate organizational structure, task assignment, and budget control, it addresses key pain points in multi-agent collaboration, such as lost context, unpredictable costs, and chaotic scheduling.
@AxtonLiu: https://x.com/AxtonLiu/status/2073791557547794579
This article discusses the concept of Agent OS, emphasizing the division of tasks into multiple workstations (fetch, refine, verify, confirm) through specialization, each managed by an independent Agent to achieve controllable automation. The author uses the example of digesting browser tabs to demonstrate how specialization isolates context, responsibility, and risks, ensuring the accuracy and reliability of AI output.
@GitHub_Daily: AI agents automating browser operations or scraping data often get blocked by anti-scraping mechanisms, and get stuck when encountering captchas or human verification. Recently, the BrowserAct team open-sourced a Skill, a browser automation command-line tool designed specifically for AI agents. It provides three layers of anti-blocking mechanisms, from…
The BrowserAct team open-sourced a browser automation command-line tool designed specifically for AI agents, providing three layers of anti-blocking mechanisms (fingerprint spoofing, captcha cracking, human takeover), supports multi-browser parallelism and account isolation, and optimizes output format to save tokens.
@QingQ77: Describe requirements in natural language, and the AI Agent automatically breaks down steps, calls tools to complete development, file operations, browser control, and other tasks, while also providing a full-fledged editor and terminal. https://github.com/Liuchun-oss/codelf-agent… Codelf is…
Codelf is an open-source desktop AI assistant that lets you describe requirements in natural language. It automatically breaks down steps and calls tools to handle development, file operations, browser control, and more, all while providing a complete editor and terminal. It supports models like DeepSeek, Claude, and ChatGPT, works well on domestic networks, and includes local RAG knowledge base capabilities.