Open-source-first LangGraph setup

End-User Setup Demo

Install provider context, export LangGraph runtime manifests, keep workflow state outside the LLM context, and choose tracing without adding mandatory hosted dependencies.

3

Provider-native root files: CLAUDE.md, AGENTS.md, and GEMINI.md.

1

LangGraph runtime export under .langgraph/.

3

Trace modes: otel, langsmith, or none.

The Problem Before

Setup is assistant-specific

Teams often copy one assistant file and lose provider-neutral behavior for the next tool.

Runtime state disappears

Long triage flows need checkpoints and durable context outside the model prompt.

Monitoring choices are unclear

Tracing should be optional, documented, and open-source-first by default.

The Solution

Install provider context at the project root, install LangGraph manifests under .langgraph/, store runtime state in a repo-local checkpoint path, and select otel, langsmith, or none for tracing.

Interactive Setup

Select Provider

Choose the assistant surface for the consuming repository. LangGraph remains the runtime export, not the provider.

./install.sh --provider claude --project --context-only --dry-run
./install.sh --provider codex --project --context-only --dry-run
./install.sh --provider gemini --project --context-only --dry-run
ProviderClaude, Codex, or Gemini
RuntimeLangGraph later
RiskNo files written