Define a goal. Nova breaks it into subtasks, executes them through a coordinated agent pipeline, evaluates progress, re-plans, and completes — on your hardware, under your control.
Define a goal. Nova breaks it into subtasks, executes autonomously, re-plans as needed.
Learns your preferences, customizes itself, updates its own configuration over time.
Runs entirely on your hardware. Your data never leaves. Sandbox tiers control what agents can access.
Continuous batching, concurrent pipelines, 4 inference backends. No bottleneck.
Agent Pipeline
Every task runs through specialized agents with built-in safety rails. No shortcuts.
Curates relevant code, docs, and task history
Produces the actual output — code, config, or answer
Checks for prompt injection, PII, credential leaks, spec drift
Pass, needs refactor, or reject — loops back up to 3 times
Creates decision record and escalates to human on rejection
Post-Pipeline
parallel, non-blockingCapabilities
From local inference to cloud routing, from IDE integration to self-configuration.
Ollama, vLLM, llama.cpp, SGLang. Pick the right engine for your workload. Run multiple simultaneously.
SGLang caches shared agent system prompts across parallel tasks for significant inference speedup.
Extensible prompt templates and declarative behavior constraints without code changes.
Isolated, nova, workspace, host — execution environments with security-first defaults.
Plug in any MCP server: GitHub, Slack, Sentry, Playwright, Docker, and more.
Anthropic, OpenAI, Ollama, Groq, Gemini, Cerebras, OpenRouter, plus subscription-based Claude/ChatGPT.
Auto-detects hardware, recommends backends, supports remote GPU over LAN with Wake-on-LAN.
Backup/restore, factory reset, service health monitoring via dedicated sidecar service.
OpenAI-compatible endpoint works with Cursor, Continue.dev, Aider, and any OpenAI-API client.
Nova can modify its own settings, prompts, and pod definitions via the nova sandbox tier.
Get Started
The setup wizard detects your hardware, configures providers, and starts everything.
Remote GPU
Got a separate machine with a GPU? Run the remote setup script on it, then re-run
./setup
and choose "Remote GPU".