Vibez
A multi-agent CLI coding assistant built in Rust that uses parallel workers for faster code generation.
Features
- 🚀 Parallel Tool Execution - Independent operations run concurrently for maximum speed
- 🤖 Multi-Agent Architecture - Manager coordinates multiple worker agents
- 🔒 Smart Conflict Detection - Automatic file locking prevents race conditions
- 📝 Contract-Based Coordination - Workers share interfaces through contracts
- ⚡ Streaming Responses - Real-time output as the AI generates code
- 🎯 Topological Task Scheduling - Dependency-aware task execution
Installation
From crates.io (recommended)
From source
Setup
On first run, Vibez will prompt you for your OpenAI API key:
Your API key is securely stored in ~/.vibez/config.toml and will be used for all future runs.
Usage
Interactive mode (REPL)
Single prompt mode
Commands
/help- Show available commands/config- Show current configuration/clear- Clear screen/quit- Exit
Options
Configuration
Configuration Priority
Settings are loaded in this order (highest priority last):
- Default values
- User config file (
~/.vibez/config.toml) - Project config file (
./.vibez/config.toml) - Environment variables (
VIBEZ_MODEL,VIBEZ_VERBOSE,VIBEZ_API_TIMEOUT) - CLI arguments (
--model,--verbose)
Note: OpenAI API key is NOT loaded from environment variables for security. It must be in a config file.
Example Config File
~/.vibez/config.toml:
= "gpt-5.1"
= false
[]
= "sk-..."
= 60
Architecture
Vibez uses a sophisticated multi-agent architecture:
- Manager Agent - Plans tasks, creates contracts, and coordinates workers
- Worker Agents - Execute tasks in parallel with contract adherence
- Tool Registry - Provides file operations, bash commands, and more
- File Locking - Prevents conflicts when multiple workers access the same files
- Smart Grouping - Automatically parallelizes independent tool calls
Performance
Vibez is designed for speed:
- Parallel Tool Execution: Independent file reads/writes run concurrently
- Conflict Detection: Graph-based algorithm groups non-conflicting operations
- Topological Scheduling: Tasks execute as soon as dependencies are met
- Rate Limiting: Semaphore-based API request management
License
MIT - see LICENSE file for details