Open Source · MIT License

Your Terminal.
17+ Providers. 14+ Agents.
Infinite Possibilities.

The open-source, multi-agent AI coding assistant that orchestrates specialized agents to plan, write, review, test, and publish code — all from a single terminal command. No subscriptions. No telemetry. Your models, your way.

Get Started Free View on GitHub
14+ Agent Roles
17+ AI Providers
2,362 Tests Passing
100% Open Source
Agent-Nuvira AI Coding Assistant
agent-nuvira execute
$ agent-nuvira execute "add JWT authentication" --verbose
🔍 Planner analyzing goal... 📁 Context Gatherer scanning codebase... ✅ Writer implemented auth middleware 👀 Reviewer validating changes... ✅ All 2,362 tests passed 🔒 VerifyModule running security scan... ✅ No security issues found 🚀 Changes committed to feature/auth
▊
Live Demo

See Agent-Nuvira in Action

Watch how the multi-agent pipeline orchestrates specialized AI agents to complete complex coding tasks — all from a single terminal command.

Agent-Nuvira AI Coding Assistant Live Demo
Live Preview

Multi-Agent Orchestration

Planner → Gatherer → Writer → Reviewer → Tester — all working together autonomously.

Provider Flexibility

Switch between Groq, Gemini, OpenRouter, NVIDIA NIM, or local models mid-session.

Real-Time Progress

Watch each agent execute in real-time with streaming output and live status updates.

Context-Aware Edits

Agents understand your full codebase context before making any changes.

Features

More Than a Chat Bot.
A Full Development Team in Your Terminal.

Agent-Nuvira isn't just another AI assistant — it's an autonomous pipeline of specialized AI agents that work together to ship code.

Multi-Agent Pipeline

10+ specialized agents — Planner, Writer, Reviewer, Tester, Debugger, and more — orchestrated to complete complex goals autonomously.

17+ AI Providers

Connect to Groq, NVIDIA NIM, Google Gemini, OpenRouter (200+ models), AWS Bedrock, Azure OpenAI, DeepSeek, or run locally with Ollama — all through one unified CLI. 5 built-in, 12+ configurable.

Fully Offline-Capable

Run entirely offline with local models via Ollama, HuggingFace, or GGML. No internet connection required.

Privacy-First

Your code connects directly to your chosen AI provider. No intermediary server, no telemetry, no data leaving your machine without your control.

Plugin System

Extend the CLI with custom AI providers and agent types. A programmatic SDK lets you build and register new capabilities.

Self-Learning System

Adaptive model routing, trajectory scoring, and pattern extraction that improve over time. The system learns which models perform best for which tasks.

How It Works

The Multi-Agent Pipeline

A goal goes in. Code comes out. Here's what happens in between — including the new Verify step from v1.21.0.

$ agent-nuvira execute <goal>
🧠 Planner
Analyzes goal, creates task plan
📁 Gatherer
Scans codebase for context
✍️ Writer
Implements code changes
👀 Reviewer
Validates for bugs & style
🧪 Tester
Runs tests in sandbox
✅ Verify
Security scan + quality checks
🚀 Ship
Commits & publishes
Agent-Nuvira Multi-Agent Pipeline Flow
Parallel execution where possible
Per-agent model configuration
Automatic error recovery
Dry-run preview mode
Providers

Choose Your AI Engine

Connect to any provider — or run locally. Switch between them per command or mid-session.

Agent-Nuvira AI Provider Options

Groq

Blazing-fast LPU inference for open-source models. Free tier available with generous rate limits.

Llama 3.3 Mixtral Gemma 2 DeepSeek
Get API Key →

NVIDIA NIM

Hosted API access to 121+ models. Free tier with rate limits. Also supports self-hosted NIM deployments.

Llama 3.1 DeepSeek Mistral 120+ more
Get API Key →

Google Gemini

Google's latest models with a generous free tier — 60 requests/minute at no cost.

Gemini 2.0 Flash Gemini Pro
Get API Key →

OpenRouter

Access 200+ models from OpenAI, Anthropic, Google, Meta, and more — all through one API.

GPT-4o Claude 3 Gemini 200+ total
Get API Key →

Local (Ollama)

Run models entirely on your machine. Ollama, HuggingFace Transformers, or GGML — completely free and offline.

Llama 2 Mistral Phi-2 Any GGUF
Get Ollama →
Get Started

Install & Go in Under a Minute

One command to install. One API key to get started. Zero configuration required.

1

Install

Install globally via npm — works on macOS, Linux, and Windows.

$ npm install -g agent-nuvira
2

Set Your API Key

Pick a provider and set your key as an environment variable.

$ export GROQ_API_KEY='gsk_your_key_here'
3

Start Coding

Chat, edit files, or run the full multi-agent pipeline.

$ agent-nuvira execute 'add input validation to API routes' --verbose
4

More Commands

Explore everything Agent-Nuvira can do.

$ agent-nuvira --help

Want to dig deeper? Read the full documentation.

Read the Docs
Extensions

Your Editor, Amplified

Agent-Nuvira's multi-agent pipeline is available wherever you code.

Agent-Nuvira Web Dashboard

VS Code Extension

Inline code suggestions, agent chat panel, diff viewer, and full multi-agent capabilities — right in your editor.

Install from Marketplace →

Agent SDK

Build custom agents with the @agent-nuvira/sdk package. Extend the pipeline with your own specialized agent roles.

$ npm install @agent-nuvira/sdk

Web Dashboard

Monitor provider health, visualize agent execution DAGs, browse conversation history, and track cost — all from a local web UI.

$ agent-nuvira dashboard
Architecture

Phase 1 → 11 Migration Complete

From monolithic agent switches to 11 completed phases — the complete evolution of Agent-Nuvira's execution engine. Phase 11 adds TS Compiler API-aware structural editing with parser-level accuracy.

Agent-Nuvira Architecture Migration Roadmap
🔧 11/11 Phases Complete
🧩 9/9 Modules Extracted
📡 4 Output Formats
🧪 2,362 Unit Tests
Why Agent-Nuvira?

Built Different. Truly Open.

See how we stack up against the competition.

Feature Agent-Nuvira GitHub Copilot Cursor Claude Code
Multi-Agent Pipeline ✓ 14+ agent roles ✗ Single agent ✗ Single agent ✗ Single agent
AI Provider Choice ✓ 17+ providers + plugins ✗ OpenAI only ✗ Vendor-locked ✗ Anthropic only
Offline Capable ✓ Full offline ✗ Cloud-only ✗ Cloud-only ✗ Cloud-only
Privacy / No Telemetry ✓ Direct-to-provider ✗ Routes via MS ~ Limited ~ Limited
Pricing ✓ Free (MIT) + API keys ✗ $10-39/mo ✗ $20/mo ✗ $20/mo
Plugin System ✓ Full SDK ✗ None ✗ Limited ✗ None
Self-Learning ✓ Adaptive routing ✗ None ✗ None ✗ None
Terminal-Native ✓ No IDE lock-in ~ VS Code only ~ Cursor only ~ Terminal-only

Ready to Supercharge Your Development?

Join developers who are already using Agent-Nuvira to ship code faster, with more control and zero vendor lock-in.

Get Started Free Star on GitHub