---
> **[Documentation](https://hazyresearch.stanford.edu/OpenJarvis/)**
>
> **[Project Site](https://www.intelligence-per-watt.ai/)**
OpenJarvis is a framework for building AI systems that run *entirely on local hardware*. Rather than treating intelligence as a cloud service, OpenJarvis provides composable abstractions for local model selection, inference, agentic reasoning, tool use, and learning — all aware of the hardware they run on.
```python
from openjarvis import Jarvis
j = Jarvis() # auto-detect hardware + engine
response = j.ask("Explain backpropagation") # route to best local model
j.ask("Solve x^2 - 5x + 6 = 0", # multi-turn agent with tools
agent="orchestrator",
tools=["calculator", "think"])
j.memory.index("./papers/") # index documents into local storage
results = j.memory.search("attention mechanism") # semantic retrieval
j.close()
```
## Installation
```bash
pip install openjarvis # core framework
pip install openjarvis[server] # + FastAPI server
```
You also need a local inference backend: [Ollama](https://ollama.com), [vLLM](https://github.com/vllm-project/vllm), [SGLang](https://github.com/sgl-project/sglang), or [llama.cpp](https://github.com/ggerganov/llama.cpp).
## Quick Start
The fastest path is Ollama on any machine with Python 3.10+:
```bash
# 1. Install OpenJarvis
pip install openjarvis
# 2. Detect hardware and generate config
jarvis init
# 3. Install and start Ollama (https://ollama.com)
curl -fsSL https://ollama.com/install.sh | sh
ollama serve # start the Ollama server
# 4. Pull a model
ollama pull qwen3:8b
# 5. Ask a question
jarvis ask "What is the capital of France?"
# 6. Verify your setup
jarvis doctor
```
`jarvis init` auto-detects your hardware and recommends the best engine. After init, it prints engine-specific next steps. Run `jarvis doctor` at any time to diagnose configuration or connectivity issues.
## The Five Pillars
| Pillar | What it does | Key abstractions |
|--------|-------------|-----------------|
| **Intelligence** | Model management and routing | `RouterPolicy`, `QueryAnalyzer`, `ModelCatalog` |
| **Engine** | Inference runtime abstraction | `InferenceEngine` ABC — Ollama, vLLM, SGLang, llama.cpp, MLX |
| **Agents** | Pluggable reasoning strategies | `BaseAgent` ABC — Simple, Orchestrator, ReAct, OpenHands, OpenClaw |
| **Tools** | Capabilities via MCP | `BaseTool` ABC — calculator, code interpreter, web search, memory; external MCP servers auto-discovered |
| **Learning** | Trace-driven adaptation | `LearningPolicy` ABC — SFT (model routing), AgentAdvisor (restructuring), ICL (tool usage) |
Every interaction produces a **Trace** — a structured record of the full reasoning chain. Learning policies consume traces to improve model selection, agent behavior, and tool usage over time.
## About
OpenJarvis is part of [Intelligence Per Watt](https://www.intelligence-per-watt.ai/), a research initiative studying the efficiency of on-device AI systems. The project is developed at [Hazy Research](https://hazyresearch.stanford.edu/) and the [Scaling Intelligence Lab](https://scalingintelligence.stanford.edu/) at [Stanford SAIL](https://ai.stanford.edu/).
## Sponsors
Laude Institute •
Stanford Marlowe •
Google Cloud Platform •
Lambda Labs
## License
[Apache 2.0](LICENSE)
