@leanlabsinnov/codegraph 0.1.2 → 0.1.4

package/README.md

@@ -1,13 +1,14 @@
 # @leanlabsinnov/codegraph
 
-Live, queryable knowledge graph for your codebase. Indexes JS/TS into an embedded graph
-DB with vector embeddings, then exposes a local MCP server that Claude Code, Cursor, and
-Windsurf can call to answer questions like "what calls `useAuth`?", "what's the blast
-radius of changing `formatPrice`?", or "find symbols semantically similar to a JWT auth
-helper".
+[![npm version](https://img.shields.io/npm/v/@leanlabsinnov/codegraph)](https://www.npmjs.com/package/@leanlabsinnov/codegraph)
+[![License: MIT](https://img.shields.io/badge/License-MIT-yellow.svg)](../../LICENSE)
+[![Node.js >=20](https://img.shields.io/badge/node-%3E%3D20-brightgreen)](https://nodejs.org)
 
-Zero infrastructure. The graph lives in a folder under `~/.codegraph/`. No Docker, no
-external services.
+**Live, queryable knowledge graph for your codebase.** Indexes JS/TS/Python into an embedded graph database with vector embeddings, then exposes a local MCP server that Claude Code, Cursor, and Windsurf can call to answer structural questions about your code.
+
+Zero infrastructure. The graph lives at `~/.codegraph/`. No Docker, no external services.
+
+---
 
 ## Install
 
@@ -15,36 +16,101 @@ external services.
 npm i -g @leanlabsinnov/codegraph
 ```
 
-Requires Node 20+.
+Requires **Node.js 20+**.
+
+---
 
 ## Quickstart
 
 ```bash
-codegraph config llm set byo-openai
+# 1. Pick an LLM provider
+codegraph config llm set byo-openai        # also: byo-anthropic, byo-google, local-ollama
 export OPENAI_API_KEY=sk-...
+
+# 2. Verify the wire-up (5-token gen + 1 embedding round-trip)
+codegraph config llm test
+
+# 3. Index a repo
 codegraph index ~/my-project
+
+# 4. Boot the MCP server
 codegraph serve
+# → http://127.0.0.1:3748/mcp
 ```
 
-Then point Claude Code / Cursor / Windsurf at `http://127.0.0.1:3748/mcp` with the bearer
-token from `~/.codegraph/config.json`.
+Point Claude Code / Cursor / Windsurf at `http://127.0.0.1:3748/mcp` with the bearer token from `~/.codegraph/config.json`.
 
-See the full [README on GitHub](https://github.com/leanlabsinnov/codegraph) for client setup, all
-10 MCP tools, and troubleshooting.
+See [client setup docs](https://github.com/Cirilcetra/codegraph/blob/main/docs/clients.md) for copy-paste config snippets.
+
+---
 
 ## Commands
 
-| Command | What it does |
+| Command | Description |
 |---|---|
-| `codegraph index <path>` | Walk the repo, parse JS/TS, embed every symbol, write to the graph |
-| `codegraph index <path> --no-embed` | Skip embeddings (faster, semantic search disabled) |
-| `codegraph status <path>` | Node + edge counts and embedding coverage |
-| `codegraph serve` | Boot the MCP server on `:3748` |
-| `codegraph doctor` | Verify Node version, config, LLM credentials, Kuzu writeable |
-| `codegraph config show` | Print the resolved config |
-| `codegraph config llm set [preset]` | Switch LLM preset (interactive when omitted) |
+| `codegraph index <path>` | Walk, parse, embed every symbol, write to graph |
+| `codegraph index <path> --no-embed` | Parse only — faster, semantic search disabled |
+| `codegraph status <path>` | Node/edge counts and embedding coverage |
+| `codegraph wipe [path]` | Delete a repo's graph rows (`--yes` skips prompt) |
+| `codegraph serve [--port N] [--host H]` | Boot the MCP server (default `:3748`) |
+| `codegraph doctor` | Health check: Node, config, API keys, Kuzu, LLM |
+| `codegraph config show` | Print resolved `~/.codegraph/config.json` |
+| `codegraph config llm set [preset]` | Switch LLM preset (interactive picker if no arg) |
 | `codegraph config llm test` | Round-trip the configured provider |
 
+---
+
+## LLM Providers
+
+| Preset | Generation | Embeddings | Required env var |
+|---|---|---|---|
+| `byo-openai` | gpt-4o-mini | text-embedding-3-small | `OPENAI_API_KEY` |
+| `byo-anthropic` | claude-3-5-haiku-latest | text-embedding-3-small | `ANTHROPIC_API_KEY` + `OPENAI_API_KEY` |
+| `byo-google` | gemini-1.5-flash-latest | text-embedding-004 | `GOOGLE_GENERATIVE_AI_API_KEY` |
+| `local-ollama` | qwen2.5-coder:14b | nomic-embed-text | Ollama running locally |
+
+---
+
+## What you can ask
+
+Once connected, ask your AI assistant:
+
+- *"What calls `useAuth`?"*
+- *"Show the component tree rooted at `App`."*
+- *"What's the blast radius of renaming `formatPrice`?"*
+- *"Find symbols semantically similar to 'JWT auth helper'."*
+- *"What are the transitive imports of `src/lib/db.ts`?"*
+
+---
+
+## Configuration
+
+Config is stored at `~/.codegraph/config.json` (auto-generated on first `serve`):
+
+```json
+{
+  "llm": {
+    "mode": "byo",
+    "generation": { "provider": "openai", "model": "gpt-4o-mini" },
+    "embeddings": { "provider": "openai", "model": "text-embedding-3-small", "dimension": 1536 }
+  },
+  "server": {
+    "port": 3748,
+    "bearerToken": "<32-hex-chars>"
+  }
+}
+```
+
+You can also override via environment variables — see `.env.example` in the repo root.
+
+---
+
+## Troubleshooting
+
+Run `codegraph doctor` first. For client-specific config issues, see the [full docs](https://github.com/Cirilcetra/codegraph/blob/main/docs/clients.md#troubleshooting).
+
+---
+
 ## License
 
 MIT

package/dist/bin.js

@@ -2,10 +2,10 @@
 import {
   buildProgram,
   renderError
-} from "./chunk-36AWRLQ6.js";
-import "./chunk-B2TIVKUB.js";
-import "./chunk-2TORJYBO.js";
-import "./chunk-XGPZDCQ4.js";
+} from "./chunk-64OLVRK3.js";
+import "./chunk-WXBYICTK.js";
+import "./chunk-AVQNLB4I.js";
+import "./chunk-POGEFB23.js";
 
 // src/bin.ts
 import { CommanderError } from "commander";