taracode

DevOps & Cloud AI Assistant
Expert guidance for Kubernetes, Terraform, Docker, and multi-cloud deployments.
Runs locally with Ollama for complete privacy.

---

Why taracode?

• DevOps Expertise - Specialized in Kubernetes, Terraform, Docker, CI/CD, and cloud platforms
• 58 Built-in Tools - DevOps, security scanning, file operations, git, web search
• Multi-Agent System - 7 specialized agents for complex tasks
• Privacy-first - Runs fully local with Ollama, your data never leaves your machine
• No Account Required - Open source, just install and use

Quick Start

1. Install Ollama

# macOS / Linux
brew install ollama

# Or download from https://ollama.ai

2. Pull a Model

ollama pull gemma3:27b    # Recommended (16GB+ RAM)
ollama pull gemma3:12b    # For limited hardware

3. Install taracode

Quick install (recommended):

curl -fsSL https://code.tara.vision/install.sh | bash

Homebrew (macOS / Linux):

brew install tara-vision/tap/taracode

Go install:

go install github.com/tara-vision/taracode@latest

Manual download:

Download binaries from GitHub Releases

4. Run

cd your-project
taracode
> /init    # Initialize project features

That's it! Start asking questions about your infrastructure.

Features

Screen Monitoring (/watch)

Let the AI watch your screen and catch errors before you do:

> /watch this          # Capture and analyze all screens now
> /watch start         # Start continuous monitoring
> /watch stop          # Stop monitoring

Multi-Agent System

7 specialized agents work together on complex tasks:

Agent	Specialty
Planner	Task decomposition and dependency analysis
Coder	Code generation and editing
Tester	Test execution and output analysis
Reviewer	Code review and quality checks
DevOps	Infrastructure and deployment operations
Security	Security scanning and vulnerability analysis
Diagnostics	Failure analysis and root cause detection

> /agent list          # List all agents
> /agent use security  # Route next prompt to specific agent

Autonomous Task Execution (/task)

Plan and execute multi-step tasks with checkpoints:

> /task "Add authentication to the API"
> /task "Deploy to production with blue-green strategy"
> /task templates      # List built-in templates

Project Memory

Remember project-specific knowledge across sessions:

> /remember We use PostgreSQL for production databases
> /remember Always run tests before pushing #workflow
> /memory search database

DevOps Tools

Category	Tools
Kubernetes	kubectl get/apply/delete/describe/logs/exec, helm list/install
Terraform	init, plan, apply, destroy, output, state
Docker	build, ps, logs, compose, exec
AWS	aws cli, ecs, eks operations
Azure	az cli, aks operations
GCP	gcloud cli, gke operations
Security	trivy, gitleaks, SAST, tfsec, kubesec, dependency audit

Security Mode

Full DevSecOps capabilities with audit logging:

> /mode security       # Switch to security mode

# Security scanning
> Scan this image for vulnerabilities: nginx:latest
> Check for secrets in the current directory
> Run a SAST scan on the codebase

Commands

Command	Description
/init	Initialize project
/mode	Switch mode (devops, security)
/model	Switch between models
/task	Execute multi-step tasks
/agent	Manage specialized agents
/watch	Screen monitoring
/memory	Project memory management
/permissions	Tool permission controls
/audit	Security audit log
/history	File operation history
/undo	Undo file modifications
/diff	Show session changes
/tools	List available tools
/upgrade	Check for and install updates
/context	Context window budget breakdown
/compact	Force conversation compaction
/stats	Session statistics
/hosts	Multi-host status (v2.0)
/help	Show help

Configuration

Create ~/.taracode/config.yaml:

# Single Host (simple setup)
host: http://localhost:11434

# Multi-Host Setup (v2.0) - for multiple Ollama servers
hosts:
  primary:
    url: http://gpu-server:11434
    models: [ gemma3:27b, qwen2.5-coder:32b ]
    priority: 1
  local:
    url: http://localhost:11434
    fallback: primary      # Use primary if local is down
    priority: 2
default_host: primary

# Model generation options (v2.0.4)
model:
  temperature: 0.7     # Sampling randomness (0.0-2.0)
  top_p: 0.9           # Nucleus sampling threshold (0.0-1.0)
  num_predict: 0       # Max tokens per response (0 = model default)

# Search
search:
  primary: duckduckgo
  fallback: searxng
  brave_api_key: ""    # Optional: Brave Search API

# Memory
memory:
  enabled: true
  auto_capture: true

# Per-agent host assignment
agents:
  coder:
    host: primary
    model: qwen2.5-coder:32b
  reviewer:
    host: local
    model: llama3.2:3b

See config.example.yaml for all options.

Supported LLM Backends

Backend	Setup	Notes
Ollama	brew install ollama	Recommended, easiest setup
vLLM	Self-hosted	For production deployments
llama.cpp	Self-hosted	Lightweight option

Development

make deps      # Install dependencies
make build     # Build binary
make test      # Run tests
make install   # Install to /usr/local/bin

See CONTRIBUTING.md for development guidelines.

Contributing

Contributions are welcome! Please read our Contributing Guide and Code of Conduct.

Security

For security issues, please see our Security Policy.

License

MIT License - see LICENSE for details.

---

Built with ❤️ by Tara Vision · Created by Dejan Stefanoski