Ross ROSS = Recommend OSS · open-source software intelligence for agents

strongdm/attractor resource

nlspec of StrongDM's Attractor, a non-interactive Coding Agent sufficient for use in a Software Factory observed · 2026-08-28

github.com/strongdm/attractor · homepage · Apache-2.0 (permissive) observed · 2026-08-28

Health v2 · maintenance only

47/100

  • Activity 72
  • Release rhythm 35
  • Longevity 14

Flags: no_releases

How is this computed?

round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10) — computed 2026-09-03. Adoption (stars, forks) is never an input.

  • gap_med: n/a
  • age_days: 209
  • days_rel: n/a
  • days_push: 169
  • n_releases_24m: 0

Full methodology

Adoption not part of the score

1277 stars · 195 forks observed · 2026-08-28

What it is AI-extracted, prompt v1, taxonomy v1, 2026-08-30, confidence not recorded

Attractor is a set of Natural Language Specifications (NLSpecs) from StrongDM describing how to build a non-interactive coding agent that composes models, prompts, and tools into a graph-structured pipeline for end-to-end software development. The repository contains human-readable specs (agent loop, unified LLM client, and overall Attractor spec) intended to be directly consumed by coding agents to implement and validate behavior.

Use cases

  • build a non-interactive coding agent from a natural language specification
  • automate the software development lifecycle with an LLM-driven graph pipeline
  • implement a unified LLM client for multiple model providers
  • create a software factory that turns fully specified work into completed code
  • orchestrate coding agent phases like implement, optimize, and validate as graph nodes
  • evaluate community implementations of an open coding agent spec

When to choose

  • you want a vendor-neutral, open specification for building your own autonomous coding agent
  • you need a deterministic, resumable, graph-structured agent pipeline for fully specified tasks
  • you want to feed a spec directly to a coding agent like Claude Code or Codex to generate an implementation

When to avoid

  • you need a ready-to-run coding agent binary rather than specifications to implement
  • your tasks are not fully specified and require interactive human-in-the-loop coding
  • you want a framework with shipped code and APIs instead of natural language documents

Facets

learning-resource · maturity active

agent-framework llm-inference prompt-engineering developer-tools workflow-automation artificial-intelligence large-language-models developer-tools cross-platform cli nl-spec coding-agent software-factory specification agentic-loop non-interactive-agent graph-pipeline sdlc-automation ai-agents automation

2 sources

Member repositories

RepositoryRoleHealth v2
strongdm/attractormain47

For agents

markdown · JSON · MCP: product_card(name="strongdm/attractor")

Data as of 2026-08-30T08:39:29.467469+00:00 · Report a problem