TurboClaude Agent - Agentic Framework for Claude
A comprehensive agent framework built on TurboClaude, enabling sophisticated AI agents with hooks, permissions, message routing, and skill integration.
📚 Documentation
- API Reference - Complete API documentation with examples
- Performance Tuning - Optimization guide and best practices
- Troubleshooting - Common issues and solutions
Features
- Agent Framework: Complete client with routing and message parsing
- Hooks System: Intercept and modify messages at key points
- Permissions: Fine-grained control over agent capabilities
- Skills Integration: Register and execute dynamic skills
- Message Routing: Sophisticated message handling and filtering
- Session Management: Maintain conversation state
Quick Start
use Agent;
use MessageRequest;
async
Components
Agent Client
Main entry point for agent interactions with configurable behavior.
Hooks
Intercept and modify:
message_start: Before sending messagesmessage_stop: After receiving messagestool_call: Before executing toolstool_result: After tool execution
Permissions
Control agent capabilities:
- Tool execution permissions
- Resource access control
- Rate limiting
Skills
Dynamic skill registration and execution:
- Register skills from external systems
- Execute skills based on agent needs
- Manage skill lifecycle
Architecture
turboclaudeagent
├── client (Agent client implementation)
├── config (Configuration builder)
├── hooks (Extensible hook system)
├── permissions (Permission control)
├── routing (Message routing logic)
├── skills (Skills integration)
└── message_parser (Advanced message parsing)
Examples
See examples/ for:
simple_query.rs- Basic agent usagewith_hooks.rs- Hook system demonstrationwith_permissions.rs- Permission configurationwith_skills.rs- Skills integration
Testing
See tests/ for comprehensive test coverage including E2E tests.
Documentation
Full documentation: cargo doc --open
Part of TurboClaude 🤖