# FAROS

> A blueprint-driven AutoResearch runtime that orchestrates AI research workflows from idea generation and experiments to paper writing and peer review.

FAROS (Foundation AutoResearch Operating System) is an open-source multi-agent system from OpenNSWM-Lab that covers research topic selection, literature retrieval, planning, code generation, experiment tracking, paper writing and peer review. It keeps provenance, decisions, artifacts and human feedback at each stage.

## What It Is

FAROS is a research-workflow runtime and web workbench for running an AI-assisted research loop. A user starts from a research interest, and the system moves through Idea, PlanPackage, Code, Experiment, Paper and ReviewX stages, ending in human approval or an evidence-driven revision. Its runtime uses a Blueprint + Capability + Profile + Provider design so new workflows and tools can be added.

## How the research loop works

- **Idea:** topic coaching turns a rough interest into a task, method, dataset and evaluation target; literature retrieval, semantic filtering and deep reading run before ideation.
- **PlanPackage:** a structured contract carrying hypotheses, variables, steps, acceptance criteria and evidence references, with reviewer checks and human approval.
- **Code and Experiment:** project generation, sandboxed execution, static and dynamic evaluation, metric ingestion, dataset upload and publication-style figures.
- **Paper:** brief, outline, section drafting, citation management and LaTeX/PDF generation linked to plans and experiments.
- **ReviewX:** extracts claims, aligns them with evidence, checks consistency and reliability, and produces revision actions.

## Setup path

The backend is a FastAPI app (Python 3.11+) and the frontend is a React/TypeScript app (Node.js 18+). Models are configurable per user through provider settings or environment variables; the README lists OpenAI, Anthropic, DeepSeek, Moonshot, Zhipu and MiniMax adapters and compatible endpoints. Docker Engine is required for the formal Code/Experiment sandbox, and formal PDF output needs latexmk, XeLaTeX, ctex and a CJK font. The README also describes user-scoped provider settings with encrypted API key storage, a bilingual UI and recoverable background jobs.

## License and deployment

The current repository licenses original source and documentation under MIT. Setup instructions target Linux or WSL Bash, with Python 3.11+ and Node.js 18+. Model/API and compute costs are separate. Important scientific conclusions still require human verification against their evidence.

## Features
- Configurable model-based research topic coaching
- Literature retrieval with semantic and evidence quality gates
- PlanPackage structured cross-module contract
- Code generation with sandboxed execution and automated repair
- Experiment metric ingestion, dataset upload and figure generation
- Paper drafting with citations and LaTeX/PDF output
- ReviewX claim-evidence-experiment consistency review
- Human approval gates
- Recoverable long-running background jobs
- Bilingual UI with per-user provider configuration and encrypted API keys

## Integrations
OpenAI, Anthropic, DeepSeek, Moonshot, Zhipu, MiniMax, OpenAI-compatible APIs, Docker, LaTeX

## Platforms
LINUX, WEB, API

## Pricing
Open Source

## Links
- Website: https://github.com/OpenNSWM-Lab/FAROS
- Documentation: https://github.com/OpenNSWM-Lab/FAROS/blob/main/docs/DEVELOPER_GUIDE.md
- Repository: https://github.com/OpenNSWM-Lab/FAROS
- EveryDev.ai: https://www.everydev.ai/tools/faros