From 5d6bc57483faaa99563056ef8f81d7eaf2e78290 Mon Sep 17 00:00:00 2001 From: Jon Saad-Falcon Date: Sun, 8 Mar 2026 00:34:47 +0000 Subject: [PATCH] docs: remove Five Pillars section from README The architecture details are now in .claude/rules/python-dev.md. Keep the README focused on installation, quickstart, and project info. Co-Authored-By: Claude Opus 4.6 --- README.md | 12 ------------ 1 file changed, 12 deletions(-) diff --git a/README.md b/README.md index 00d2c502..dfc356d4 100644 --- a/README.md +++ b/README.md @@ -89,18 +89,6 @@ uv run pytest tests/ -v See [Contributing](docs/development/contributing.md) for more. -## 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/).