Deep Research

with MangoAgent

芒果智能体平台
集成 tools、skills、sandboxes and subagents 等核心能力
轻松完成不同难度的任务

Case Studies
See how MangoAgent is used in the wild
Agent Skills
Agent Skills are loaded progressively — only what's needed, when it's needed.
Extend MangoAgent with your own skill files, or use our built-in library.
Click to play
/mnt/skills/
deep-search
SKILL.md
biotech.md
computer-science.md
physics.md
frontend-design
SKILL.md
deploy
SKILL.md
scripts
deploy.sh
MangoAgent
Ask MangoAgent anything...
Agent Runtime Environment

We give MangoAgent a "computer", which can execute commands, manage files, and run long tasks — all in a secure Docker-based sandbox

pygame==2.5.0
✔ Installed pygame
✔ Written 156 lines
✔ All sprites loaded
✔ Physics engine OK
✔ 60 FPS stable
Downloaded 12.4 MB

Open-source

AIO Sandbox

We recommend using All-in-One Sandbox that combines Browser, Shell, File, MCP and VSCode Server in a single Docker container.

IsolatedSafePersistentMountable FSLong-running
Whats New in MangoAgent 2.0
MangoAgent is now evolving from a Deep Research agent into a full-stack Super Agent
Context Engineering

Long/Short-term Memory

Now the agent can better understand you
Long Task Running

Planning and Sub-tasking

Plans ahead, reasons through complexity, then executes sequentially or in parallel
Extensible

Skills and Tools

Plug, play, or even swap built-in tools. Build the agent you want.
Persistent

Sandbox with File System

Read, write, run — like a real computer
Flexible

Multi-Model Support

Doubao, DeepSeek, OpenAI, Gemini, etc.
Free

Open Source

MIT License, self-hosted, full control
Join the Community
Contribute brilliant ideas to shape the future of MangoAgent. Collaborate, innovate, and make impacts.