Personal AI, On Personal Devices.
Why NOVA AI?
Personal AI agents are exploding in popularity, but nearly all of them still route intelligence through cloud APIs. Your "personal" AI continues to depend on someone else's server. Local language models already handle most single-turn chat and reasoning queries, and their capability per watt keeps improving year over year. What has been missing is the software stack to make local-first personal AI practical.
NOVA AI is that stack. It is a framework for local-first personal AI, built around three core ideas: shared primitives for building on-device agents; evaluations that treat energy, FLOPs, latency, and dollar cost as first-class constraints alongside accuracy; and a learning loop that improves models using local trace data. The goal is simple: make it possible to build personal AI agents that run locally by default, calling the cloud only when truly necessary. NOVA AI aims to be both a research platform and a production foundation for local AI, in the spirit of PyTorch.
Installation & Quick Start
Pick your platform and start in seconds:
| Platform | Quick Launch | Installation One-liner |
|---|---|---|
| Windows (Setup EXE, no Python) | Double-click NOVA-AI-Setup-1.2.5.exe — includes Alt+Space Quick Capture |
Latest Release |
| Windows (1-Click) | Double-click start.bat |
irm https://hamza35779.github.io/NOVA-AI/install.ps1 | iex or run install.bat |
| Linux · macOS | ./start.sh |
curl -fsSL https://hamza35779.github.io/NOVA-AI/install.sh | bash |
| Docker | cp deploy/docker/.env.example .env # fill NOVA_AI_API_KEY then docker compose -f deploy/docker/docker-compose.yml --env-file .env up |
Containerized setup with local Ollama engine |
| Desktop GUI | Download .exe / .dmg / .AppImage |
Latest Release |
Start Working with NOVA AI
# Interactive Chat
nova chat
# Hands-free Voice Conversation
nova voice --push-to-talk
# Smart Model Router (Auto-selects optimal model)
nova router status
nova router test "Analyze quantum algorithms"
# Active Memory Wiki
nova memory-wiki show profile
nova memory-wiki search "preferences"
# Interactive Canvas (Open HTML/SVG/Chart visualizations)
nova canvas list
# Build/Test Diagnostics with Self-Healing Fix Suggestions
nova dev-watch -c "pytest -q"
# Presets & System Diagnostics
nova init --preset morning-digest-minimal
nova doctor
Prefix
nova ...withuv run, orsource .venv/bin/activatefirst.
| Preset | What it does |
|---|---|
morning-digest-mac / morning-digest-linux / morning-digest-minimal |
Spoken daily briefing from email, calendar, health, news |
deep-research |
Multi-hop research across indexed docs with citations |
code-assistant |
Agent with code execution, file I/O, and shell access |
scheduled-monitor |
Stateful agent on a schedule with memory |
chat-simple |
Lightweight conversation, no tools |
Example:
nova init --preset morning-digest-mac
nova connect gdrive # one OAuth covers Gmail / Calendar / Tasks
nova digest --fresh # generate and play your first briefing
Per-preset deep dives: morning digest · deep research · code assistant · scheduled monitor · chat simple · or the full quickstart guide.
Skills
Skills teach agents how to better use tools and improve their reasoning. Every skill is a tool — agents discover them from a catalog and invoke them on demand.
# Install skills from public sources
nova skill install hermes:arxiv
nova skill sync hermes --category research
# Use skills with any agent
nova ask "Use the code-explainer skill to explain this Python code: for i in range(5): print(i*2)"
# Optimize skills from your trace history
nova optimize skills --policy dspy
# Benchmark the impact
nova bench skills --max-samples 5 --seeds 42
Import from Hermes Agent (~150 skills), OpenClaw (~13,700 community skills), or any GitHub repo. Skills follow the agentskills.io open standard.
See the Skills User Guide and Skills Tutorial for details.
Built-in Agents
NOVA AI ships with built-in agents across three execution modes (on-demand, scheduled, continuous):
| Agent | Type | What it does |
|---|---|---|
morning_digest |
Scheduled | Daily briefing from email, calendar, health, news — with TTS audio and a desktop notification when ready |
deep_research |
On-demand | Multi-hop research with citations across web and local docs |
monitor_operative |
Continuous | Long-horizon monitoring with memory, compression, and retrieval |
orchestrator |
On-demand | Multi-turn reasoning with automatic tool selection |
native_react |
On-demand | ReAct (Thought-Action-Observation) loop agent |
self_healing_react |
On-demand | ReAct with a bounded self-repair loop — powers nova dev-watch diagnostics |
operative |
Continuous | Persistent autonomous agent with state management |
native_openhands |
On-demand | CodeAct — generates and executes Python code |
simple |
On-demand | Single-turn chat, no tools |
opencode Integration
Use opencode with NOVA AI in both directions — opencode gets your
local Ollama models (as the nova-ai provider) and NOVA's tool registry via MCP, so
coding-agent sessions run local-first:
nova opencode install # fetch the opencode CLI when missing
nova opencode init # write/merge ./opencode.json (provider + MCP tools)
nova serve # start the backend (another terminal)
nova opencode launch # open opencode wired to NOVA AI
nova opencode status shows per-provider data residency (local vs cloud); --local-only
locks opencode to local models and disables session sharing. Docs: opencode Integration.
Desktop Extras
- ⚡ Quick Capture (Windows:
Alt+Space, macOS:Cmd+Shift+Space) — a Raycast-style chat popup from anywhere; the conversation syncs back to the main app automatically. - 🔔 Morning digest notifications — a desktop notification fires the moment your briefing is stored (covers scheduler, CLI, and server delivery);
nova digestplays audio on Windows viawinsound/the default media player. - 🔨 Dev-Watch — run a build/test command, get failure classification (timeout / exit code / embedded errors) plus self-healing fix suggestions; results feed the Build Diagnostics panel on the Dashboard (
/api/devwatch/runs).
Complete CLI Commands Reference
NOVA AI features a comprehensive CLI suite (nova or python -m nova_ai.cli or standalone nova-ai.exe):
1. 💬 Chat, Voice & Perception
| Command | Description | Example |
|---|---|---|
nova chat |
Launch an interactive multi-turn REPL chat session | nova chat --model llama3 |
nova ask "<query>" |
Send a single query directly to the model/agent | nova ask "Summarize this repo" |
nova voice |
Real-time hands-free voice conversation mode | nova voice --push-to-talk |
nova screen capture |
Capture active window/screen and run OCR text extraction | nova screen capture --output screen.png |
nova screen ask "<query>" |
Ask questions about what's currently on your screen | nova screen ask "Explain this error" |
2. 🚀 Server & Background Daemons
| Command | Description | Example |
|---|---|---|
nova serve |
Start the local OpenAI-compatible REST & WebSocket API server | nova serve --port 8000 |
nova start |
Start the NOVA AI server as a background daemon process | nova start |
nova status |
Check status of the running background daemon | nova status |
nova restart |
Restart the running server daemon | nova restart |
nova stop |
Terminate the server background daemon | nova stop |
nova tunnel |
Expose local API securely to the internet via Cloudflare Tunnel | nova tunnel start |
3. 🧠 Models & Smart Routing
| Command | Description | Example |
|---|---|---|
nova model list |
List all discovered local and cloud AI models | nova model list |
nova model pull <name> |
Download a local GGUF/Ollama model directly | nova model pull llama3 |
nova host <model> |
Serve and host a local model with hardware acceleration | nova host qwen2.5:7b |
nova router status |
View the Smart Router complexity tiers & statistics | nova router status |
nova router test "<query>" |
Test dynamic query complexity classification | nova router test "Design a microservice" |
4. 🛠️ Autonomous Tools & Integrations
| Command | Description | Example |
|---|---|---|
nova tool list |
List all registered built-in and dynamic tools | nova tool list |
nova integrations list |
View software connectors (Packet Tracer, Office, Canvas, Git) | nova integrations list |
nova integrations enable <id> |
Enable a specific software bridge | nova integrations enable cisco_packet_tracer |
nova canvas list |
List interactive Canvas charts, HTML, and SVG artifacts | nova canvas list |
nova scheduler list |
View and manage scheduled tasks and cron jobs | nova scheduler list |
nova add <mcp-server> |
Connect external Model Context Protocol (MCP) servers | nova add filesystem |
5. 📚 Long-Term Memory & Deep Research
| Command | Description | Example |
|---|---|---|
nova memory status |
Inspect SQLite vector store and indexed chunk counts | nova memory status |
nova memory search "<q>" |
Semantic search over indexed personal knowledge base | nova memory search "project plan" |
nova memory-wiki show <topic> |
Display structured markdown knowledge-base articles | nova memory-wiki show profile |
nova research "<topic>" |
Multi-hop autonomous deep research with cited sources | nova research "Latest advancements in LLM reasoning" |
6. ⚙️ Diagnostics, Config & Benchmarking
| Command | Description | Example |
|---|---|---|
nova doctor |
Run full hardware, GPU, and engine health diagnostics | nova doctor |
nova dev-watch -c "<cmd>" |
Run a build/test command and self-diagnose failures with fix suggestions | nova dev-watch -c "pytest -q" --watch |
nova init |
Auto-detect GPU hardware and create ~/.nova_ai/config.toml |
nova init --preset deep-research |
nova config show |
Print loaded configuration hierarchy and settings | nova config show |
nova config set <k> <v> |
Modify a configuration property in TOML | nova config set engine.default ollama |
nova bench |
Measure inference latency, tokens/sec, and energy consumption | nova bench --models llama3 |
nova self-update |
Upgrade NOVA AI to the latest release | nova self-update |
See the User Guide and Tutorials for detailed setup instructions.
Full documentation — including Docker deployment, cloud engines, development setup, and tutorials — at hamza35779.github.io/NOVA-AI.
Community
- GitHub: github.com/Hamza35779/NOVA-AI
- Issues: github.com/Hamza35779/NOVA-AI/issues
Contributing
We welcome contributions! See the Contributing Guide for incentives, contribution types, and the PR process.
Quick start for contributors:
git clone https://github.com/Hamza35779/NOVA-AI.git
cd NOVA-AI
uv sync --extra dev
uv run pre-commit install
uv run pytest tests/ -v
Browse the Roadmap for areas where help is needed. Comment "take" on any issue to get auto-assigned.
License
1 maintainer
Release files for nova-ai-pro 1.2.5
For a detailed explanation of source distributions (sdists) and built distributions (wheels), please see the package formats documentation.
Source distribution (sdist)
| File | Size | Uploaded | |
|---|---|---|---|
| nova_ai_pro-1.2.5.tar.gz | 13.8 MB | Details |
Built distribution (wheel)
| File | Interpreter | ABI | Platform | Reset |
|---|---|---|---|---|
| nova_ai_pro-1.2.5-py3-none-any.whl | Python 3 | none | any | Details |
Total release size: 16.1 MB
Release files / nova_ai_pro-1.2.5.tar.gz
| Download URL | nova_ai_pro-1.2.5.tar.gz |
|---|---|
| Size | 13.8 MB |
| Tags | Source |
|
SHA-256 checksum How to use checksums |
93df0a48c60e5366f9935a66ae249668619e110752b5aaa4b14924aacd6f898b
|
|
BLAKE2b-256 checksum How to use checksums |
4437671ce72ac7a3b44e16cc8d0331bba761f424e7d69b16ae14683d05baf1e2
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
No |
| Uploaded via |
uv/0.12.17 {"installer":{"name":"uv","version":"0.12.17","subcommand":["publish"]},"python":null,"implementation":{"name":null,"version":null},"distro":{"name":"Ubuntu","version":"24.04","id":"noble","libc":null},"system":{"name":null,"release":null},"cpu":null,"openssl_version":null,"setuptools_version":null,"rustc_version":null,"ci":true}
|
Release files / nova_ai_pro-1.2.5-py3-none-any.whl
| Download URL | nova_ai_pro-1.2.5-py3-none-any.whl |
|---|---|
| Size | 2.3 MB |
| Tags | Python 3 |
|
SHA-256 checksum How to use checksums |
f4bb527f9b65ebe820f2124953d984cf8de7d8dd9ef23d8956c8baaceb4e1b38
|
|
BLAKE2b-256 checksum How to use checksums |
9837dd689dc52e84fb11f88e7102af6c2aced0f6917493d0c2a1d354d505ee06
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
No |
| Uploaded via |
uv/0.12.17 {"installer":{"name":"uv","version":"0.12.17","subcommand":["publish"]},"python":null,"implementation":{"name":null,"version":null},"distro":{"name":"Ubuntu","version":"24.04","id":"noble","libc":null},"system":{"name":null,"release":null},"cpu":null,"openssl_version":null,"setuptools_version":null,"rustc_version":null,"ci":true}
|
