# OpenNSWM-Lab/FAROS

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

Repository: https://github.com/OpenNSWM-Lab/FAROS
Canonical: https://ross.abutalabs.com/products/faros
Language: Python
License Family: other
Topics: agentic-workflow, ai-scientist, automated-research, autoresearch, llm-agents, multi-agent, paper-generation, research-agent, research-automation, scientific-discovery, workflow-orchestration, academic-research, academic-writing, ai-for-science, ai4science, autonomous-research, paper-writing, research-orchestration, research-workflow, scientific-workflow
Last push: 2026-08-25T00:44:49+00:00

## Health v2 (maintenance only)
Score: 58/100 (v2, computed 2026-09-03T02:20:16.233290+00:00)
- activity 99, release rhythm 35, longevity 8
- inputs: {"age_days": 112, "days_push": 9, "days_rel": null, "gap_med": null, "n_releases_24m": 0}
- flags: no_releases, young, no_license
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 3001, forks 350 (observed 2026-08-28T04:07:37.448460+00:00)

## What it is
FAROS is a blueprint-driven AutoResearch runtime that orchestrates end-to-end AI research workflows, from idea generation through experiments, paper writing, and peer review. It is built around composable Blueprints, Capabilities, Profiles, and Providers, currently shipping an LLM-domain baseline (FAROS-LLM) with file-backed persistence and venue-aware LaTeX paper generation.

## Use cases
- automate the full research pipeline from idea to paper and review
- generate academic papers with LaTeX tailored to a venue
- orchestrate multi-agent LLM research workflows from blueprints
- run an AI scientist system that proposes and evaluates research ideas
- automate peer review of generated papers
- build custom research workflow runtimes with pluggable providers

## When to choose
- you want a configurable, blueprint-based alternative to hardcoded AI-scientist agents
- you need an end-to-end LLM research pipeline including paper writing and review
- you want file-backed run, event, and artifact persistence for research runs
- you are experimenting with automated scientific discovery in the LLM domain

## When to avoid
- you need full DAG scheduling and parallel orchestration, which is not yet included
- you need a mature cross-domain or non-LLM provider ecosystem
- you require a polished frontend console or DB-backed runtime metadata
- you need a permissively licensed project - no license is currently specified

## Facets
- artifact type: framework
- maturity: experimental
- function: agent-framework, workflow-automation, llm-inference, prompt-engineering, rag
- domain: artificial-intelligence, large-language-models, developer-tools
- platform: python, cross-platform
- tags: ai-scientist, autoresearch, research-automation, paper-generation, multi-agent, blueprint-driven, scientific-workflow, peer-review-automation, ai-agents, automation, nodejs, docker

## Member repositories
- OpenNSWM-Lab/FAROS (main) score 58

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:07:37.448460+00:00.
- Health v2: computed from the inputs above; adoption is never an input.
- Inferred fields (summary, facets, guidance): AI-extracted, prompt v1, taxonomy v1, on 2026-08-30T07:30:34.823094+00:00, confidence not recorded.
  - readme: https://github.com/OpenNSWM-Lab/FAROS (fetched 2026-08-28T04:07:37.448460+00:00, sha 0b0c917ad28b)
- Data as of 2026-08-30T08:39:29.467469+00:00.