Turbocharge Claude Code, Cursor, Codex, Gemini & every coding agent: faster, cheaper, with contextual understanding specific to your codebase.
TypeScript ai-agentsanthropicclaude-codeclicode-graphcodexcontext-engineeringcursordeveloper-toolsgeminiknowledge-graphllmmcpmcp-serveropen-sourceopenaitree-sitter
docs: graft init now integrates all detected coding agents
Shrish Dwivedi299f08e39dbb
diff --git a/README.md b/README.mdindex 9f6edd8e..b733e8ed 100644--- a/README.md+++ b/README.md@@ -54,16 +54,28 @@ Prefer not to install globally? `npx @nanonets/graft init` works the same way.----## Claude Code integration+## Agent integration-If you use [Claude Code](https://claude.com/claude-code), one command wires Graft into every session in the repo:+One command wires Graft into the coding agents you use:```bashnpx @nanonets/graft init-# writes .claude/ (statusline + hooks) and builds the graph if it's missing+# detects your agents and writes each one's native instruction file;+# Claude Code additionally gets the live statusline + hooks below```-From then on, any Claude Code session opened in the repo gets:+`init` auto-detects which agents are present (via their config directories) and writes a marker-fenced Graft section into each one's shared instruction file — `AGENTS.md`, `GEMINI.md`, `.github/copilot-instructions.md` — or a wholly-owned rule file for the agents that use one — `.cursor/rules/graft.mdc`, `.kiro/steering/graft.md`, `.windsurf/rules/graft.md`. Re-running only updates Graft's own section (or replaces the owned file) and never touches the rest of your content.++| Flag | Effect |+|---|---|+| `--agents <ids...>` | wire only these — ids: `agents`, `cursor`, `gemini`, `copilot`, `kiro`, `windsurf`, `claude` |+| `--all-agents` | write instruction files for every known agent, detected or not |+| `--no-agents` | Claude Code wiring only; skip other agents |+| `--list-agents` | print the known agent ids and exit |++### Claude Code (deep integration)++`graft init` always wires up Claude Code, and Claude Code gets more than an instruction file. From then on, any Claude Code session opened in the repo gets:- **a live statusline** — graph size, % enriched, and a `⚠ N stale` warning when the code has moved ahead of the graph- **auto-sync** — after you edit code, Graft rebuilds the graph in the background at the end of the turn (structural, `$0` — it never calls the LLM on its own)@@ -174,8 +186,11 @@ graft check --json # print the drift report as JSONgraft viz [dir] # see the graph: serves an interactive viewer on localhostgraft viz --port 5000 --no-open # pick a port; don't auto-open the browser-graft init [dir] # set up the Claude Code integration (.claude/ statusline + hooks) in this repo+graft init [dir] # wire Graft into the coding agents detected in this repo (Claude Code always gets full hooks + statusline)graft init --no-build # wire the files only; don't build the graph+graft init --agents cursor kiro # wire only these agents (ids: agents, cursor, gemini, copilot, kiro, windsurf, claude)+graft init --all-agents # wire every known agent, detected or not+graft init --list-agents # list known agent ids and exit# globalgraft --dir <path> # use a context dir other than <repo>/graft