Jon Saad-FalconandClaude Opus 4.6
bd49383201
Evaluation framework (evals/): benchmarking system for measuring accuracy
across four categories — Chat (WildChat), Reasoning (SuperGPQA), RAG (FRAMES),
and Agentic (GAIA). Two backends: jarvis-direct (engine-level) and jarvis-agent
(agent-level with tool calling), both supporting local and cloud models.
Datasets adapted from IPW, scorers include exact match, LLM letter extraction,
and LLM-as-judge. Parallel execution via ThreadPoolExecutor with incremental
JSONL output. CLI: python -m evals {run,run-all,summarize,list}. 57 tests pass.
SVG fix: center logo content within viewBox by wrapping icon+text in a
translate(90,0) group, eliminating the left-shift visible in the README.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
Programming abstractions for on-device 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.
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
pip install openjarvis # core framework
pip install openjarvis[server] # + FastAPI server
You also need a local inference backend: Ollama, vLLM, SGLang, or llama.cpp.
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, a research initiative studying the efficiency of on-device AI systems. The project is developed at Hazy Research and the Scaling Intelligence Lab at Stanford SAIL.
Sponsors
Laude Institute • Stanford Marlowe • Google Cloud Platform • Lambda Labs