Mambo Agents

AI Agent framework built on LangChain/LangGraph — multi-backend filesystem, sub-agent parallel scheduling, conversation summarization, security review, skills system, and more, out of the box.
基于 LangChain/LangGraph 的 AI Agent 框架 — 提供多后端文件系统、子代理并行调度、对话摘要、安全审查、技能系统等开箱即用的能力。

📖 English | 中文

This project draws architectural inspiration from deepagents, with independent refactoring and extensions. See comparison with deepagents.

Key Features

• Let Your Agent Control the Environment — multi-backend filesystem (virtual/local/SSH/hybrid), with shell command execution
• Long Conversation Management — automatic conversation history compaction with chained summaries
• Task Planning & Tracking — structured TODO lists with automatic progress tracking
• Installing Skill Packs — progressive disclosure, on-demand loading, multi-source overlay
• Let Your Agent Remember Your Preferences — AGENTS.md persistent context, AI self-learning write-back
• Security & Human Approval — cheap model pre-review + human approval for high-risk operations
• File Change History & Rollback — checkpoint-level incremental snapshots, manual rollback
• Integrating External MCP Tools — disclosure-based design, on-demand lookup
• Multi-Agent Collaboration — sync/async sub-agents, parallel scheduling, isolated context windows
• Goal-Driven Loop Control — preset goals with completion conditions, or LLM-autonomous long-running tasks with auto-continuation

Quick Start

pip install mambo-agents

from mambo_agents import create_mambo_agent, StoreBackend
from langchain_core.messages import HumanMessage

agent = create_mambo_agent(
    "gpt-4o",
    backend=StoreBackend(),
    include_general_purpose=True,
)
result = agent.invoke({"messages": [HumanMessage("Create a hello.py file")]}, config={"configurable": {"thread_id": "session-1"}})

Architecture

┌──────────────────────────────────────────────────────────┐
│                    create_mambo_agent()                   │
│                                                          │
│  ┌─────────────┐  ┌──────────┐  ┌────────────────────┐  │
│  │   Backend   │  │  Model   │  │    Middleware Stack │  │
│  │  Protocol   │  │ (LLM)    │  │                    │  │
│  │  Store      │  │          │  │ BackendTools       │  │
│  │  Local      │  │          │  │ Skills             │  │
│  │  SSH        │  │          │  │ Memory             │  │
│  │  Hybrid     │  │          │  │ VersionControl     │  │
│  │  ReadOnly   │  │          │  │ Summarization      │  │
│  │             │  │          │  │ Planning           │  │
│  └─────────────┘  └──────────┘  │ SubAgents          │  │
│                                 │ AsyncSubAgents     │  │
│                                 │ SecurityReview     │  │
│                                 │ Patch + Reorder    │  │
│                                 └────────────────────┘  │
│                                                          │
│  ┌─────────────────────────────────────────────────────┐ │
│  │              LangGraph CompiledGraph                │ │
│  │  invoke() · astream() · astream_events()            │ │
│  └─────────────────────────────────────────────────────┘ │
└──────────────────────────────────────────────────────────┘

Docs

• Detailed Usage Guide — API reference, configuration, advanced usage
• Comparison with deepagents — architectural differences, feature mapping, design trade-offs

Related Projects

• MamboChat — Full-featured Web UI built on Mambo Agents

License

MIT License