Setups
Repositories and frameworks we point to for context management, agent roles, and AI-native workflows. Not endorsements—useful starting points.
Cursor Agentic Toolkit
A structured operating layer for AI-assisted delivery in Cursor: intent → brief → spec → tasks → QA, curated context, external operational memory, and installer profiles—without turning the toolkit repo into your product workspace.
Agent Skills (open standard)
Vendor-neutral Agent Skills ecosystem: shared conventions so skills work across tools and models, not locked to a single assistant.
RuFlo
Agent orchestration for multi-agent swarms, autonomous workflows, and conversational systems—with hooks into common AI coding tools and RAG-style integration.
BHIL AI-First Development Toolkit
A production-oriented methodology repo: traceable PRD → SPEC → ADR → TASK chains, sprint loops, and AI-native patterns from an external practitioner.
LangGraph
Graph-based orchestration for stateful, long-running agents: nodes, edges, human-in-the-loop, and durable execution—sibling idea to swarm platforms, different shape.
Anthropic Agent Skills
The public skills repo and Agent Skills spec: folders with SKILL.md, scripts, and resources Claude loads for repeatable, specialized tasks.
GitHub Spec Kit
Spec-driven development for the AI coding era: constitution, specify, plan, tasks, implement—persistent specs that steer agents instead of one-off prompts.
Context Management Bootstrap Kit
A reusable framework for multi-agent AI development: four roles, briefs as contracts, and shared documentation—aligned with how Nimbus thinks about handoffs.