# Webber - Multi-Agent AI Development System

A Claude Code-inspired development assistant powered by local LLMs via Ollama.

## Structure

This is a monorepo containing three subprojects:

| Directory | Description |
|-----------|-------------|
| `webber-api/` | FastAPI backend server with agent orchestration |
| `webber-cli/` | Command-line client for interacting with the API |
| `webber-sandbox/` | Test project for functional testing |

### Additional Directories

| Directory | Description |
|-----------|-------------|
| `sandbox-templates/` | Reusable project templates for the sandbox |
| `.gitea/workflows/` | CI/CD workflows for releases |

## Quick Start

### 1. Start the API Server

```bash
cd webber-api
python3.12 -m venv .venv
source .venv/bin/activate
pip install -r requirements.txt -r requirements-dev.txt
./wakeup.sh
```

### 2. Set Up the CLI

```bash
cd webber-cli
python3.12 -m venv .venv
source .venv/bin/activate
pip install -r requirements.txt
pip install -e .

# Test connection
webber-cli status
```

### 3. Load a Sandbox Project

```bash
# From repo root
./sandbox.sh list
./sandbox.sh load calculator-cli

cd webber-sandbox
python3.12 -m venv .venv
source .venv/bin/activate
pip install -r requirements.txt
```

### 4. Explore with Webber

```bash
cd webber-cli
webber-cli explore "find all bugs in the code" -d ../webber-sandbox
```

## Versioning

This project uses prefixed tags for independent release cycles:

- `api/v0.3.0` - Triggers API Docker build and deployment
- `cli/v0.1.0` - Triggers CLI installer build (future)

## Requirements

- Python 3.12+
- Ollama running with `mistral-nemo:latest` model
- Docker (for production deployment)

## Documentation

- `webber-api/AGENTS.md` - API development guidelines
- `webber-api/docs/` - Architecture and coverage docs
- `webber-cli/README.md` - CLI usage guide

## License

MIT