box-agent 0.6.4

AI agent framework with Jupyter sandbox, data analysis, MCP tools, ACP protocol, multi-provider LLM, and standalone runtime packaging

Box Agent

A general-purpose AI agent with sandboxed code execution, sub-agent parallelism, and multi-provider LLM support.

English | 中文

---

Get started in 30 seconds:

pip install box-agent
box-agent setup        # interactive config wizard
box-agent              # start chatting

Or run a one-shot task:

box-agent --task "Analyze sales.csv — show top 10 products by revenue with a bar chart"

---

Why Box Agent?

Most agent frameworks are either too simple (no sandbox, no tools) or too complex (massive dependencies, rigid architecture). Box Agent hits the sweet spot:

Feature	Box Agent	Open Interpreter	Aider
Sandboxed code execution	Jupyter kernel in isolated venv	Runs in host Python	N/A
Sub-agent parallelism	Multiple sub-agents run concurrently	No	No
Multi-provider LLM	Anthropic, OpenAI, DeepSeek, SiliconFlow, any API	OpenAI + a few others	OpenAI + Anthropic
MCP tool integration	Native	No	No
ACP protocol (embed in apps)	Full support	No	No
Standalone binary	PyInstaller runtime, no Python needed	No	No
Context compression	2-layer automatic (micro-compact + LLM summary)	Manual	Git-based

Key Features

Sub-Agent Parallelism

Delegate tasks to isolated sub-agents that run concurrently. Each sub-agent has its own context — only the summary comes back. Perfect for multi-file analysis.

You: "Analyze data1.csv, data2.csv, and data3.csv separately, then give me a combined summary"

┌─ Sub-Agent 1 ──────┐  ┌─ Sub-Agent 2 ──────┐  ┌─ Sub-Agent 3 ──────┐
│ Read data1.csv      │  │ Read data2.csv      │  │ Read data3.csv      │
│ Run statistics      │  │ Run statistics      │  │ Run statistics      │
│ Generate charts     │  │ Generate charts     │  │ Generate charts     │
│ → Summary: ...      │  │ → Summary: ...      │  │ → Summary: ...      │
└─────────────────────┘  └─────────────────────┘  └─────────────────────┘
                              ↓ parallel ↓
                    ┌─ Parent Agent ──────────┐
                    │ Combines 3 summaries    │
                    │ Produces final report   │
                    └─────────────────────────┘

Sandboxed Code Execution

Python runs in an isolated Jupyter kernel with pre-installed data science packages (pandas, numpy, matplotlib, scikit-learn, openpyxl). Generated files (charts, CSVs, PDFs) are automatically detected and surfaced as structured artifacts.

Multi-Provider LLM

One config, any provider:

# Anthropic
api_base: "https://api.anthropic.com"
provider: "anthropic"
model: "claude-sonnet-4-20250514"

# DeepSeek
api_base: "https://api.deepseek.com"
provider: "openai"
model: "deepseek-chat"

# Any OpenAI-compatible endpoint
api_base: "https://your-api.example.com/v1"
provider: "openai"
model: "your-model"

2-Layer Context Compression

• Layer 1 — Micro-compact: Every step, old tool results (3+ turns back) are replaced with short placeholders. Zero cost, no LLM call.
• Layer 2 — Auto-summary: When tokens exceed the threshold (default 80k), an LLM call summarizes the conversation. Original data is preserved in logs.

More

• MCP Tools: Connect to any MCP server — web search, knowledge graphs, databases
• Claude Skills: 11 built-in skills for documents (DOCX, PDF, PPTX, XLSX), canvas design, web app testing, and more
• ACP Protocol: Embed Box Agent in Electron apps, Zed Editor, or any ACP-compatible host via JSON-RPC over stdio
• Standalone Runtime: PyInstaller binary bundles Python + all dependencies. No external Python needed — download and run
• Safety Layer: Dangerous command detection, workspace scope control, auto-backup before file modifications
• Task Tracking: Built-in todo tool for multi-step task decomposition and progress tracking

Demos

Task Execution

The agent creates a webpage and opens it in the browser.

Claude Skill — PDF Generation

The agent uses a skill to create a professional document.

Web Search via MCP

The agent searches the web and summarizes results.

Installation

Quick Start (pip)

pip install box-agent
box-agent setup    # interactive config wizard
box-agent          # start chatting

From Source

git clone https://github.com/Raccoon-Office/Box-Agent.git
cd Box-Agent
uv sync
git submodule update --init --recursive   # optional: load skills
uv run python -m box_agent.cli

Configuration

After running box-agent setup, your config lives at ~/.box-agent/config/config.yaml:

api_key: "your-api-key"
api_base: "https://api.anthropic.com"
model: "claude-sonnet-4-20250514"
provider: "anthropic"           # "anthropic" or "openai"
max_steps: 50

box-agent config           # show current config
box-agent config --edit    # open in editor
box-agent doctor           # check environment & API connectivity

CLI Usage

# Interactive mode
box-agent
box-agent --workspace /path/to/project
box-agent --sandbox              # enable Jupyter sandbox

# Non-interactive (CI/CD, scripts)
box-agent --task "analyze data.csv and create a report"

# Subcommands
box-agent setup     # config wizard
box-agent config    # show/edit config
box-agent doctor    # health check
box-agent log       # open log directory

In-session commands: /help, /clear, /history, /stats, /log, /exit

ACP & Editor Integration

Box Agent supports the Agent Communication Protocol for embedding in editors and apps.

Zed Editor — add to settings.json:

{
  "agent_servers": {
    "box-agent": {
      "command": "/path/to/box-agent-acp"
    }
  }
}

Standalone Runtime — for Electron apps and other hosts:

# Download pre-built binary
gh release download v0.6.2 --repo Raccoon-Office/Box-Agent --pattern "box-agent-runtime-*.tar.gz"

# Or build from source
uv run python scripts/build_runtime.py

The runtime communicates via JSON-RPC over stdio. stdout = protocol only, stderr = diagnostics.

Testing

pytest tests/ -v          # all tests
pytest tests/test_core.py -v   # core + context compression
pytest --cov              # with coverage

Troubleshooting

SSL Certificate Error: pip install --upgrade certifi or set verify=False for testing.

Module Not Found: Make sure you're in the project directory: cd Box-Agent && uv run python -m box_agent.cli

Contributing

Issues and PRs welcome! See Contributing Guide.

License

MIT

Links

• PyPI · GitHub · Releases
• Anthropic API · MCP Servers · ACP Protocol

---

If this project helps you, give it a ⭐!