Bamboo Agent 🎋

A fully self-contained AI agent backend framework with built-in web services.

Bamboo provides everything you need to build, deploy, and scale AI-powered applications with support for multiple LLM providers, comprehensive tool execution, and production-ready infrastructure.

📖 Full Documentation | 🚀 Getting Started | 📚 API Docs

✨ Features

• 🤖 Complete Agent System: Agent loop, tool execution, skill management
• 🌐 Built-in HTTP Server: Actix-web based API server with REST and streaming endpoints
• 🧠 Multi-LLM Support: OpenAI, Anthropic, Google Gemini, GitHub Copilot
• 📁 XDG-Compliant: Follows XDG Base Directory specification
• 🔧 Dual Mode: Binary (standalone server) or library (embedded)
• 🔐 Production-Ready: CORS, rate limiting, security headers built-in
• 🔄 Session Management: Persistent conversation history
• ⚡ Workflow System: Automate complex tasks with YAML workflows
• 🤝 Claude Integration: Seamless Claude Code binary discovery and management
• 🧪 Well Tested: 806 tests with 100% pass rate

Installation

From crates.io

cargo install bamboo-agent

From source

git clone https://github.com/bigduu/Bamboo-agent
cd bamboo
cargo install --path .

Quick Start

Binary Mode

# Start server with default settings
bamboo serve

# Custom configuration
bamboo serve --port 9000 --bind 0.0.0.0 --data-dir /var/lib/bamboo

Library Mode

use bamboo_agent::{BambooBuilder, BambooConfig};

#[tokio::main]
async fn main() {
    let server = BambooBuilder::new()
        .port(3000)
        .bind("0.0.0.0")
        .data_dir(std::path::PathBuf::from("/var/lib/myapp"))
        .build()
        .unwrap();

    server.start().await.unwrap();
}

Configuration

Bamboo follows the XDG Base Directory specification.

Default Paths

• Config: $XDG_CONFIG_HOME/bamboo/config.json (default: ~/.config/bamboo/)
• Data: $XDG_DATA_HOME/bamboo/ (default: ~/.local/share/bamboo/)
• Cache: $XDG_CACHE_HOME/bamboo/ (default: ~/.cache/bamboo/)

Configuration File

Edit ~/.config/bamboo/config.json:

{
  "server": {
    "port": 8080,
    "bind": "127.0.0.1",
    "workers": 10
  },
  "data_dir": "~/.local/share/bamboo"
}

Environment Variables

Override configuration with environment variables:

• BAMBOO_PORT: Server port
• BAMBOO_BIND: Bind address
• BAMBOO_DATA_DIR: Data directory

API Endpoints

Once running, Bamboo exposes the following endpoints:

Health Check

GET /api/v1/health

Chat Completions

POST /api/v1/chat/completions

Agent Execution

POST /api/v1/agent/run

Workflows

GET    /v1/workflows
POST   /v1/workflows
DELETE /v1/workflows/{name}

Sessions

GET  /api/v1/sessions
POST /api/v1/sessions

Development

Build

cargo build

Test

cargo test

Run

cargo run -- serve

Architecture

Bamboo is organized into the following modules:

• config: Configuration management with XDG support
• core: Core types and utilities
• agent: Agent system (loop, tools, skills, LLM providers)
• server: HTTP server and controllers
• process: Process management
• claude: Claude Code integration
• commands: Workflow, slash commands, keyword masking

Documentation

• Full Documentation - Comprehensive guides and references
• API Documentation - Auto-generated API docs
• Migration Guide - Migrating from monorepo structure
• Contributing - How to contribute to Bamboo
• Changelog - Version history and release notes
• Security Policy - Security information and reporting

License

MIT License - see LICENSE for details.

Contributing

Contributions are welcome! Please read our Contributing Guidelines before submitting PRs.

Support

• Issues: https://github.com/bigduu/Bamboo-agent/issues
• Discussions: https://github.com/bigduu/Bamboo-agent/discussions
• Security: See SECURITY.md for reporting security issues

Roadmap

• Complete agent system migration
• Full OpenAI/Anthropic API compatibility
• Webhook support
• Plugin system
• gRPC API
• Kubernetes deployment guides

Made with ❤️ by the Bamboo Contributors