lynkr 0.1.0 → 0.1.1

package/.github/workflows/index.yml

@@ -0,0 +1,56 @@
+name: Notify IndexNow on Docs Update
+
+on:
+  push:
+    branches:
+      - main
+    paths:
+      - 'docs/**'
+
+jobs:
+  notify-indexnow:
+    runs-on: ubuntu-latest
+
+    steps:
+      - name: Checkout repository
+        uses: actions/checkout@v4
+
+      - name: Notify IndexNow
+        run: |
+          echo "Notifying IndexNow about updated docs..."
+
+          # Host and key settings
+          HOST="vishalveerareddy123.github.io"
+          KEY="42642f749da6234f41b6b425c3bb07c9"
+          KEY_LOCATION="https://$HOST/Lynkr/42642f749da6234f41b6b425c3bb07c9.txt"
+
+          # URLs to notify – you can add more here as your site grows
+          URLS_JSON=$(cat <<EOF
+          {
+            "host": "$HOST",
+            "key": "$KEY",
+            "keyLocation": "$KEY_LOCATION",
+            "urlList": [
+              "https://$HOST/Lynkr/",
+              "https://$HOST/Lynkr/sitemap.xml"
+            ]
+          }
+          EOF
+          )
+
+          echo "Payload:"
+          echo "$URLS_JSON"
+
+          HTTP_CODE=$(curl -s -o /tmp/indexnow_response.txt -w "%{http_code}" \
+            -X POST "https://www.bing.com/indexnow" \
+            -H "Content-Type: application/json; charset=utf-8" \
+            -d "$URLS_JSON")
+
+          echo "IndexNow response HTTP code: $HTTP_CODE"
+          echo "IndexNow response body:"
+          cat /tmp/indexnow_response.txt
+
+          if [ "$HTTP_CODE" -ge 400 ]; then
+            echo "IndexNow request failed"
+            exit 1
+          fi

package/README.md

@@ -1,6 +1,14 @@
-# Lynkr
+# Lynkr 
 
-> Drop-in HTTP proxy that lets Claude Code CLI talk to non-Anthropic backends, manage local tools, and compose Model Context Protocol (MCP) servers with prompt caching, repo intelligence, and Git-aware automation.
+[![npm version](https://img.shields.io/npm/v/lynkr.svg)](https://www.npmjs.com/package/lynkr)
+[![Homebrew Tap](https://img.shields.io/badge/homebrew-lynkr-brightgreen.svg)](https://github.com/vishalveerareddy123/homebrew-lynkr)
+[![License: MIT](https://img.shields.io/badge/license-MIT-blue.svg)](LICENSE)
+[![Ask DeepWiki](https://deepwiki.com/badge.svg)](https://deepwiki.com/vishalveerareddy123/Lynkr)
+[![Databricks Supported](https://img.shields.io/badge/Databricks-Supported-orange)](https://www.databricks.com/)
+[![IndexNow Enabled](https://img.shields.io/badge/IndexNow-Enabled-success?style=flat-square)](https://www.indexnow.org/)
+
+
+> It is a Cli tool which acts like a HTTP proxy that lets Claude Code CLI talk to non-Anthropic backends, manage local tools, and compose Model Context Protocol (MCP) servers with prompt caching, repo intelligence, and Git-aware automation.
 
 ## Table of Contents
 
@@ -45,6 +53,8 @@ The result is a self-hosted alternative that stays close to Anthropic’s ergono
 
 > **Compatibility note:** Claude models hosted on Databricks work out of the box. Set `MODEL_PROVIDER=azure-anthropic` (and related credentials) to target the Azure-hosted Anthropic `/anthropic/v1/messages` endpoint. Additional providers will require future adapters.
 
+Further documentation and usage notes are available on [DeepWiki](https://deepwiki.com/vishalveerareddy123/Lynkr).
+
 ---
 
 ## Core Capabilities
@@ -156,6 +166,15 @@ The result is a self-hosted alternative that stays close to Anthropic’s ergono
 ### Installation
 
 ```bash
+# from npm (recommended)
+npm install -g lynkr
+lynkr start
+
+# via Homebrew tap
+brew tap vishalveerareddy123/lynkr
+brew install vishalveerareddy123/lynkr/lynkr
+
+# or clone the repo
 git clone https://github.com/vishalveerareddy123/Lynkr.git
 cd Lynkr
 npm install
@@ -234,14 +253,15 @@ See `src/config/index.js` for the full configuration matrix, including sandbox m
 ### Launching the Proxy
 
 ```bash
-# Development: auto-restarts on file changes (requires nodemon)
-npm run dev
+# global install
+lynkr start
 
-# Production
-npm start
+# local checkout
+npm run dev    # development: auto-restarts on file changes
+npm start      # production
 ```
 
-Logs stream to stdout. The server listens on `PORT` and exposes `/v1/messages` in the Anthropic-compatible shape.
+Logs stream to stdout. The server listens on `PORT` and exposes `/v1/messages` in the Anthropic-compatible shape. If you installed via npm globally, `lynkr start` reads the same environment variables described above.
 
 ### Connecting Claude Code CLI
 
@@ -313,7 +333,7 @@ The compose file exposes:
 - Proxy HTTP API on `8080`
 - Optional SearxNG instance on `8888` (started automatically when `WEB_SEARCH_ENDPOINT` is the default)
 
-Workspace files are mounted into the container (`./:/workspace`), and `./data` is persisted for SQLite state.
+Workspace files are mounted into the container (`./:/workspace`), and `./data` is persisted for SQLite state. If you launch the proxy outside of this compose setup you must provide your own search backend and point `WEB_SEARCH_ENDPOINT` at it (for example, a self-hosted SearxNG instance). Without a reachable search service the `web_search` and `web_fetch` tools will return placeholder responses or fail.
 
 #### Manual Docker build
 
@@ -328,6 +348,24 @@ docker run --rm -p 8080:8080 -p 8888:8888 \
 
 Adjust port and volume mappings to suit your environment. Ensure the container has access to the target workspace and required credentials.
 
+#### Direct `docker run` with inline environment variables
+
+```bash
+docker run --rm -p 8080:8080 \
+  -v "$(pwd)":/workspace \
+  -v "$(pwd)/data":/app/data \
+  -e MODEL_PROVIDER=databricks \
+  -e DATABRICKS_API_BASE=https://<workspace>.cloud.databricks.com \
+  -e DATABRICKS_ENDPOINT_PATH=/serving-endpoints/<endpoint-name>/invocations \
+  -e DATABRICKS_API_KEY=<personal-access-token> \
+  -e WORKSPACE_ROOT=/workspace \
+  -e PORT=8080 \
+  claude-code-proxy
+```
+
+Use additional `-e` flags (or `--env-file`) to pass Azure Anthropic credentials or other configuration values as needed.
+Replace `<workspace>` and `<endpoint-name>` with your Databricks workspace host and the Serving Endpoint you want to target (e.g. `/serving-endpoints/databricks-gpt-4o-mini/invocations`) so you can choose any available model.
+
 ### Provider-specific behaviour
 
 - **Databricks** – Mirrors Anthropic’s hosted behaviour. Automatic policy web fallbacks (`needsWebFallback`) can trigger an extra `web_fetch`, and the upstream service executes dynamic pages on your behalf.
@@ -415,3 +453,7 @@ A: In SQLite at `data/sessions.db` (configurable via `SESSION_DB_PATH`).
 ## License
 
 MIT License. See [LICENSE](LICENSE) for details.
+
+---
+
+If you find Lynkr useful, please ⭐ the repo — it helps more people discover it.

package/docs/42642f749da6234f41b6b425c3bb07c9.txt

@@ -0,0 +1 @@
+42642f749da6234f41b6b425c3bb07c9

package/docs/BingSiteAuth.xml

@@ -0,0 +1,4 @@
+<?xml version="1.0"?>
+<users>
+	<user>124252D20CDCDAB4459245ACF3CFE165</user>
+</users>

package/docs/google5be250e608e6da39.html

@@ -0,0 +1 @@
+google-site-verification: google5be250e608e6da39.html

package/docs/index.md

@@ -0,0 +1,362 @@
+
+<link rel="stylesheet" href="style.css">
+
+
+# Lynkr – Claude Code-Compatible Proxy for Databricks 
+#### Lynkr is an open-source Claude Code-compatible proxy that allows the Claude Code CLI to run directly on Databricks. It supports MCP servers, Git workflows, repo intelligence, workspace tools, and prompt caching for LLM-powered development.
+<!--
+SEO Keywords:
+Databricks, Claude Code, Anthropic, Azure Anthropic,
+LLM tools, LLM agents, Model Context Protocol, MCP,
+developer tools, proxy, git automation, AI developer tools,
+prompt caching, Node.js
+-->
+
+
+---
+
+#  Lynkr  
+### Claude Code-Compatible Proxy for Databricks & Azure Anthropic  
+**MCP • Git Tools • Repo Intelligence • Prompt Caching • Workspace Automation**
+
+[⭐ Star on GitHub](https://github.com/vishalveerareddy123/Lynkr) ·  
+[📘 Documentation](https://deepwiki.com/vishalveerareddy123/Lynkr) ·  
+[🐙 Source Code](https://github.com/vishalveerareddy123/Lynkr)
+
+---
+
+# 🚀 What is Lynkr?
+
+**Lynkr** is an open-source **Claude Code-compatible backend proxy** that lets you run the **Claude Code CLI** and Claude-style tools **directly against Databricks** or **Azure-hosted Anthropic models** instead of the default Anthropic cloud.
+
+It enables full repo-aware LLM workflows:
+
+- code navigation  
+- diff review  
+- Git operations  
+- test execution  
+- workspace tools  
+- Model Context Protocol (MCP) servers  
+- repo indexing and project intelligence  
+- prompt caching  
+- conversational sessions  
+
+This makes Databricks a first-class environment for **AI-assisted software development**, **LLM agents**, **automated refactoring**, **debugging**, and **ML/ETL workflow exploration**.
+
+---
+
+# 🌟 Key Features (SEO Summary)
+
+### ✔ Claude Code-compatible API (`/v1/messages`)  
+Emulates Anthropic’s backend so the **Claude Code CLI works without modification**.
+
+### ✔ Works with Databricks LLM Serving  
+Supports **Databricks-hosted Claude Sonnet / Haiku models**, or any LLM served from Databricks.
+
+### ✔ Supports Azure Anthropic models  
+Route Claude Code requests into Azure’s `/anthropic/v1/messages` endpoint.
+
+### ✔ Full Model Context Protocol (MCP) integration  
+Auto-discovers MCP manifests and exposes them as tools for smart workflows.
+
+### ✔ Repo Intelligence: `CLAUDE.md`, Symbol Index, Cross-file analysis  
+Lynkr builds a repo index using SQLite + Tree-sitter for rich context.
+
+### ✔ Git Tools and Workflow Automation  
+Commit, push, diff, stage, generate release notes, etc.
+
+### ✔ Prompt Caching (LRU + TTL)  
+Reuses identical prompts to reduce cost + latency.
+
+### ✔ Workspace Tools  
+Task tracker, file I/O, test runner, index rebuild, etc.
+
+### ✔ Fully extensible Node.js architecture  
+Add custom tools, policies, or backend adapters.
+
+---
+
+# 📚 Table of Contents
+
+- [What Lynkr Solves](#-what-lynkr-solves)
+- [Architecture Overview](#-architecture-overview)
+- [Installation](#-installation)
+- [Configuring Providers (Databricks & Azure Anthropic)](#-configuring-providers)
+- [Using Lynkr With Claude Code CLI](#-using-lynkr-with-claude-code-cli)
+- [Repo Intelligence & Indexing](#-repo-intelligence--indexing)
+- [Prompt Caching](#-prompt-caching)
+- [MCP (Model Context Protocol) Integration](#-model-context-protocol-mcp)
+- [Git Tools](#-git-tools)
+- [API Examples](#-api-examples)
+- [Roadmap](#-roadmap)
+- [Links](#-links)
+
+---
+
+# 🧩 What Lynkr Solves
+
+### **The Problem**
+Claude Code is exceptionally useful—but it only communicates with Anthropic’s hosted backend.
+
+This means:
+
+❌ You can’t point Claude Code at **Databricks LLMs**  
+❌ You can’t run Claude workflows **locally**, offline, or in secure contexts  
+❌ MCP tools must be managed manually  
+❌ You don’t control caching, policies, logs, or backend behavior
+
+### **The Solution: Lynkr**
+Lynkr is a **Claude Code-compatible backend** that sits between the CLI and your actual model provider.
+
+```
+
+Claude Code CLI
+↓
+Lynkr Proxy
+↓
+Databricks / Azure Anthropic / MCP / Tools
+
+```
+
+This enables:
+
+- **Databricks-native LLM development**
+- **Enterprise-private model usage**
+- **LLM agents with Git + file system access**
+- **Smart workflows via MCP**
+- **Transparent caching + logging**
+
+---
+
+# 🏗 Architecture Overview
+
+```
+
+Claude Code CLI
+↓  (HTTP POST /v1/messages)
+Lynkr Proxy (Node.js + Express)
+↓
+────────────────────────────────────────
+│  Orchestrator (Agent Loop)          │
+│  ├─ Tool Execution Pipeline         │
+│  ├─ MCP Registry + Sandbox          │
+│  ├─ Prompt Cache (LRU + TTL)        │
+│  ├─ Session Store (SQLite)          │
+│  ├─ Repo Indexer (Tree-sitter)      │
+│  ├─ Policy Engine                   │
+────────────────────────────────────────
+↓
+Databricks / Azure Anthropic / Other Providers
+
+````
+
+Key directories:
+
+- `src/api` → Claude-compatible API proxy  
+- `src/orchestrator` → LLM agent runtime loop  
+- `src/mcp` → Model Context Protocol tooling  
+- `src/tools` → Git, diff, test, tasks, fs tools  
+- `src/cache` → prompt caching backend  
+- `src/indexer` → repo intelligence
+
+---
+
+# ⚙ Installation
+
+## Global install (recommended)
+```bash
+npm install -g lynkr
+lynkr start
+````
+
+## Homebrew
+
+```bash
+brew tap vishalveerareddy123/lynkr
+brew install vishalveerareddy123/lynkr/lynkr
+```
+
+## From source
+
+```bash
+git clone https://github.com/vishalveerareddy123/Lynkr.git
+cd Lynkr
+npm install
+npm start
+```
+
+---
+
+# 🔧 Configuring Providers
+
+## Databricks Setup
+
+```env
+MODEL_PROVIDER=databricks
+DATABRICKS_API_BASE=https://<workspace>.cloud.databricks.com
+DATABRICKS_API_KEY=<personal-access-token>
+DATABRICKS_ENDPOINT_PATH=/serving-endpoints/databricks-claude-sonnet-4-5/invocations
+WORKSPACE_ROOT=/path/to/your/repo
+PORT=8080
+```
+
+## Azure Anthropic Setup
+
+```env
+MODEL_PROVIDER=azure-anthropic
+AZURE_ANTHROPIC_ENDPOINT=https://<resource>.services.ai.azure.com/anthropic/v1/messages
+AZURE_ANTHROPIC_API_KEY=<api-key>
+AZURE_ANTHROPIC_VERSION=2023-06-01
+WORKSPACE_ROOT=/path/to/repo
+PORT=8080
+```
+
+---
+
+# 💬 Using Lynkr With Claude Code CLI
+
+```bash
+export ANTHROPIC_BASE_URL=http://localhost:8080
+export ANTHROPIC_API_KEY=dummy
+```
+
+Then:
+
+```bash
+claude chat
+claude diff
+claude review
+claude apply
+```
+
+Everything routes through your Databricks or Azure model.
+
+---
+
+# 🧠 Repo Intelligence & Indexing
+
+Lynkr uses Tree-sitter and SQLite to analyze your workspace:
+
+* **Symbol definitions**
+* **Cross-file references**
+* **Language mix**
+* **Framework hints**
+* **Dependency patterns**
+* **Testing metadata**
+
+It generates a structured `CLAUDE.md` so the model always has context.
+
+---
+
+# ⚡ Prompt Caching
+
+Lynkr includes an LRU+TTL prompt cache.
+
+### Benefits:
+
+* Reduced Databricks compute consumption
+* Faster response times
+* Deterministic repeated responses
+
+Configure:
+
+```env
+PROMPT_CACHE_ENABLED=true
+PROMPT_CACHE_TTL_MS=300000
+PROMPT_CACHE_MAX_ENTRIES=64
+```
+
+---
+
+# 🧩 Model Context Protocol (MCP)
+
+Lynkr automatically discovers MCP manifests from:
+
+```
+~/.claude/mcp
+```
+
+or directories defined via:
+
+```
+MCP_MANIFEST_DIRS
+```
+
+MCP tools become available inside the Claude Code environment, including:
+
+* GitHub integrations
+* Jira automations
+* custom internal tools
+* filesystem operations
+* build systems
+* CI/CD triggers
+
+Optional sandboxing uses Docker or OCI runtimes.
+
+---
+
+# 🔧 Git Tools
+
+Lynkr includes a full suite of Git operations:
+
+* `workspace_git_status`
+* `workspace_git_diff`
+* `workspace_git_stage`
+* `workspace_git_commit`
+* `workspace_git_push`
+* `workspace_git_pull`
+* Release-note generation
+* Diff summarization & analysis
+
+Policies:
+
+* `POLICY_GIT_ALLOW_PUSH`
+* `POLICY_GIT_REQUIRE_TESTS`
+* `POLICY_GIT_TEST_COMMAND`
+
+Example:
+
+> Disallow push unless tests pass?
+> Set `POLICY_GIT_REQUIRE_TESTS=true`.
+
+---
+
+# 🧪 API Example (Index Rebuild)
+
+```bash
+curl http://localhost:8080/v1/messages \
+  -H 'Content-Type: application/json' \
+  -d '{
+    "model": "claude-proxy",
+    "messages": [{ "role": "user", "content": "Rebuild the index." }],
+    "tool_choice": {
+      "type": "function",
+      "function": { "name": "workspace_index_rebuild" }
+    }
+  }'
+```
+
+---
+
+# 🛣 Roadmap
+
+* LSP integration (TypeScript, Python, more languages)
+* Per-file diff comments
+* Risk scoring for Git diffs
+* Expand MCP support
+* Skill-like declarative automation layer
+* Historical test dashboards
+* Databricks-specific tools
+
+---
+
+# 🔗 Links
+
+* **GitHub**: [https://github.com/vishalveerareddy123/Lynkr](https://github.com/vishalveerareddy123/Lynkr)
+* **Docs**: [https://deepwiki.com/vishalveerareddy123/Lynkr](https://deepwiki.com/vishalveerareddy123/Lynkr)
+* **Issues**: [https://github.com/vishalveerareddy123/Lynkr/issues](https://github.com/vishalveerareddy123/Lynkr/issues)
+
+If you use Databricks or Azure Anthropic and want rich Claude Code workflows, Lynkr gives you the control and extensibility you need.
+
+Feel free to open issues, contribute tools, or integrate with MCP servers!
+

package/docs/robots.txt

@@ -0,0 +1,4 @@
+User-agent: *
+Allow: /
+
+Sitemap: https://vishalveerareddy123.github.io/Lynkr/sitemap.xml

package/docs/sitemap.xml

@@ -0,0 +1,8 @@
+<?xml version="1.0" encoding="UTF-8"?>
+<urlset xmlns="http://www.sitemaps.org/schemas/sitemap/0.9">
+  <url>
+    <loc>https://vishalveerareddy123.github.io/Lynkr/</loc>
+    <changefreq>weekly</changefreq>
+    <priority>1.0</priority>
+  </url>
+</urlset>

package/docs/style.css

@@ -0,0 +1,24 @@
+/* E-ink-ish font */
+@import url('https://fonts.googleapis.com/css2?family=Literata:wght@400;600;700&display=swap');
+
+body {
+  font-family: "Literata", system-ui, -apple-system, BlinkMacSystemFont, "Segoe UI", sans-serif;
+  background-color: #fbf8f3;
+  color: #222;
+
+  /* 🔥 key part: make it flow instead of centered */
+  margin: 0;
+  padding: 1.5rem 2rem;
+  line-height: 1.65;
+}
+
+/* GitHub Pages often wraps content in .markdown-body – kill its max-width */
+.markdown-body {
+  max-width: none !important;
+}
+
+/* Optional: make headings breathe a bit */
+h1, h2, h3 {
+  font-weight: 600;
+  margin-top: 1.6em;
+}

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "lynkr",
-  "version": "0.1.0",
+  "version": "0.1.1",
   "description": "Self-hosted Claude Code proxy with Databricks and Azure Anthropic adapters, workspace tooling, and MCP integration.",
   "main": "index.js",
   "bin": {
@@ -31,7 +31,7 @@
   },
   "homepage": "https://github.com/vishalveerareddy123/Lynkr#readme",
   "engines": {
-    "node": ">=18.0.0"
+    "node": ">=20.0.0"
   },
   "dependencies": {
     "better-sqlite3": "^9.4.0",