@aigne/example-afs-local-fs 1.1.0-beta

package/.env.local.example

@@ -0,0 +1,44 @@
+# Change the name of this file to .env.local and fill in the following values
+
+# Uncomment the lines below to enable debug logging
+# DEBUG="aigne:*"
+
+# Use different Models
+
+# OpenAI
+# MODEL="openai/gpt-4.1"
+# OPENAI_API_KEY="YOUR_OPENAI_API_KEY"
+
+# Anthropic claude
+# MODEL="anthropic/claude-3-7-sonnet-latest"
+# ANTHROPIC_API_KEY=""
+
+# Gemini
+MODEL="google/gemini-2.5-pro"
+# GEMINI_API_KEY=""
+
+# Bedrock nova
+# MODEL=bedrock:us.amazon.nova-premier-v1:0
+# AWS_ACCESS_KEY_ID=""
+# AWS_SECRET_ACCESS_KEY=""
+# AWS_REGION=us-west-2
+
+# DeepSeek
+# MODEL="deepseek/deepseek-chat"
+# DEEPSEEK_API_KEY=""
+
+# OpenRouter
+# MODEL="openrouter/openai/gpt-4o"
+# OPEN_ROUTER_API_KEY=""
+
+# xAI
+# MODEL="xai/grok-2-latest"
+# XAI_API_KEY=""
+
+# Ollama
+# MODEL="ollama/llama3.2"
+# OLLAMA_DEFAULT_BASE_URL="http://localhost:11434/v1";
+
+
+# Setup proxy if needed
+# HTTPS_PROXY=http://localhost:7890

package/LICENSE.md

@@ -0,0 +1,93 @@
+Elastic License 2.0
+
+URL: https://www.elastic.co/licensing/elastic-license
+
+## Acceptance
+
+By using the software, you agree to all of the terms and conditions below.
+
+## Copyright License
+
+The licensor grants you a non-exclusive, royalty-free, worldwide,
+non-sublicensable, non-transferable license to use, copy, distribute, make
+available, and prepare derivative works of the software, in each case subject to
+the limitations and conditions below.
+
+## Limitations
+
+You may not provide the software to third parties as a hosted or managed
+service, where the service provides users with access to any substantial set of
+the features or functionality of the software.
+
+You may not move, change, disable, or circumvent the license key functionality
+in the software, and you may not remove or obscure any functionality in the
+software that is protected by the license key.
+
+You may not alter, remove, or obscure any licensing, copyright, or other notices
+of the licensor in the software. Any use of the licensor’s trademarks is subject
+to applicable law.
+
+## Patents
+
+The licensor grants you a license, under any patent claims the licensor can
+license, or becomes able to license, to make, have made, use, sell, offer for
+sale, import and have imported the software, in each case subject to the
+limitations and conditions in this license. This license does not cover any
+patent claims that you cause to be infringed by modifications or additions to
+the software. If you or your company make any written claim that the software
+infringes or contributes to infringement of any patent, your patent license for
+the software granted under these terms ends immediately. If your company makes
+such a claim, your patent license ends immediately for work on behalf of your
+company.
+
+## Notices
+
+You must ensure that anyone who gets a copy of any part of the software from you
+also gets a copy of these terms.
+
+If you modify the software, you must include in any modified copies of the
+software prominent notices stating that you have modified the software.
+
+## No Other Rights
+
+These terms do not imply any licenses other than those expressly granted in
+these terms.
+
+## Termination
+
+If you use the software in violation of these terms, such use is not licensed,
+and your licenses will automatically terminate. If the licensor provides you
+with a notice of your violation, and you cease all violation of this license no
+later than 30 days after you receive that notice, your licenses will be
+reinstated retroactively. However, if you violate these terms after such
+reinstatement, any additional violation of these terms will cause your licenses
+to terminate automatically and permanently.
+
+## No Liability
+
+*As far as the law allows, the software comes as is, without any warranty or
+condition, and the licensor will not be liable to you for any damages arising
+out of these terms or the use or nature of the software, under any kind of
+legal claim.*
+
+## Definitions
+
+The **licensor** is the entity offering these terms, and the **software** is the
+software the licensor makes available under these terms, including any portion
+of it.
+
+**you** refers to the individual or entity agreeing to these terms.
+
+**your company** is any legal entity, sole proprietorship, or other kind of
+organization that you work for, plus all organizations that have control over,
+are under the control of, or are under common control with that
+organization. **control** means ownership of substantially all the assets of an
+entity, or the power to direct its management and policies by vote, contract, or
+otherwise. Control can be direct or indirect.
+
+**your licenses** are all the licenses granted to you for the software under
+these terms.
+
+**use** means anything you do with the software requiring one of your licenses.
+
+**trademark** means trademarks, service marks, and similar rights.

package/README.md

@@ -0,0 +1,259 @@
+# AFS LocalFS Example
+
+<p align="center">
+  <picture>
+    <source srcset="https://raw.githubusercontent.com/AIGNE-io/aigne-framework/main/logo-dark.svg" media="(prefers-color-scheme: dark)">
+    <source srcset="https://raw.githubusercontent.com/AIGNE-io/aigne-framework/main/logo.svg" media="(prefers-color-scheme: light)">
+    <img src="https://raw.githubusercontent.com/AIGNE-io/aigne-framework/main/logo.svg" alt="AIGNE Logo" width="400" />
+  </picture>
+</p>
+
+This example shows how to mount your local file system as an AFS module, enabling AI agents to intelligently search, read, and interact with your files. We demonstrate mounting the AIGNE framework documentation.
+
+## What You'll See
+
+**User asks:** "What is AIGNE?"
+
+**Behind the scenes:**
+1. LLM calls `afs_search` → searches all files for "AIGNE"
+2. Finds `/modules/local-fs/docs/getting-started/what-is-aigne.md`
+3. LLM calls `afs_read` → reads the specific file
+4. LLM presents: "AIGNE is a framework and runtime engine for building LLM-powered applications..."
+
+**The power:** AI agents intelligently search your file system and retrieve exactly what's needed - no manual navigation required!
+
+## Prerequisites
+
+* [Node.js](https://nodejs.org) (>=20.0) and npm installed on your machine
+* An [OpenAI API key](https://platform.openai.com/api-keys) for interacting with OpenAI's services
+* Optional dependencies (if running the example from source code):
+  * [Pnpm](https://pnpm.io) for package management
+  * [Bun](https://bun.sh) for running unit tests & examples
+
+## Quick Start (No Installation Required)
+
+```bash
+export OPENAI_API_KEY=YOUR_OPENAI_API_KEY
+
+# Mount AIGNE framework docs (clone first)
+git clone https://github.com/AIGNE-io/aigne-framework
+npx -y @aigne/example-afs-local-fs --path ./aigne-framework --chat
+
+# Or mount any directory
+npx -y @aigne/example-afs-local-fs --path ~/Documents --description "My Documents" --chat
+
+# Ask a specific question
+npx -y @aigne/example-afs-local-fs --path . --input "What is AIGNE?"
+```
+
+## See It In Action
+
+Here's what happens when you ask "What is AIGNE?" with the framework docs mounted:
+
+```
+👤 You: "What is AIGNE?"
+
+🤖 Agent thinks: I should search the docs for information about AIGNE...
+   → Calls: afs_search(query: "AIGNE")
+
+📁 Found 15 matching files:
+   • docs/getting-started/what-is-aigne.md ⭐ (most relevant)
+   • README.md
+   • docs/core-concepts/overview.md
+   ...
+
+🤖 Agent thinks: Let me read the most relevant file...
+   → Calls: afs_read("docs/getting-started/what-is-aigne.md")
+
+📄 File loaded (2.4 KB)
+
+🤖 AI: "AIGNE is a framework and runtime engine for building LLM-powered
+       applications and AI agents. It provides:
+
+       • A unified Agentic File System (AFS) interface
+       • Support for multiple LLM providers (OpenAI, Anthropic, etc.)
+       • Tools for building autonomous agents
+       • Integration with external services via MCP
+
+       Would you like me to walk you through a quick-start tutorial, or
+       would you prefer to see specific examples?"
+```
+
+**Key insight:** The agent intelligently searches, finds the right file, reads it, and synthesizes a helpful answer - all automatically!
+
+## Installation
+
+### Clone the Repository
+
+```bash
+git clone https://github.com/AIGNE-io/aigne-framework
+```
+
+### Install Dependencies
+
+```bash
+cd aigne-framework/examples/afs-local-fs
+
+pnpm install
+```
+
+### Setup Environment Variables
+
+Setup your OpenAI API key in the `.env.local` file:
+
+```bash
+OPENAI_API_KEY="" # Set your OpenAI API key here
+```
+
+#### Using Different Models
+
+You can use different AI models by setting the `MODEL` environment variable along with the corresponding API key. The framework supports multiple providers:
+
+* **OpenAI**: `MODEL="openai:gpt-4.1"` with `OPENAI_API_KEY`
+* **Anthropic**: `MODEL="anthropic:claude-3-7-sonnet-latest"` with `ANTHROPIC_API_KEY`
+* **Google Gemini**: `MODEL="gemini:gemini-2.0-flash"` with `GEMINI_API_KEY`
+* **AWS Bedrock**: `MODEL="bedrock:us.amazon.nova-premier-v1:0"` with AWS credentials
+* **DeepSeek**: `MODEL="deepseek:deepseek-chat"` with `DEEPSEEK_API_KEY`
+* **OpenRouter**: `MODEL="openrouter:openai/gpt-4o"` with `OPEN_ROUTER_API_KEY`
+* **xAI**: `MODEL="xai:grok-2-latest"` with `XAI_API_KEY`
+* **Ollama**: `MODEL="ollama:llama3.2"` with `OLLAMA_DEFAULT_BASE_URL`
+
+For detailed configuration examples, please refer to the `.env.local.example` file in this directory.
+
+### Run the Example
+
+```bash
+# Run with your current directory
+pnpm start --path .
+
+# Run with a specific directory
+pnpm start --path ~/Documents --description "My Documents"
+
+# Run in interactive chat mode
+pnpm start --path . --chat
+```
+
+## How It Works: 3 Simple Steps
+
+### 1. Create LocalFS Module
+
+```typescript
+import { LocalFS } from "@aigne/afs-local-fs";
+
+const localFS = new LocalFS({
+  localPath: './aigne-framework',
+  description: 'AIGNE framework documentation'
+});
+```
+
+### 2. Mount It as an AFS Module
+
+```typescript
+import { AFS } from "@aigne/afs";
+import { AFSHistory } from "@aigne/afs-history";
+
+const afs = new AFS()
+  .mount(new AFSHistory({ storage: { url: ":memory:" } }))
+  .mount(localFS);  // Mounted at /modules/local-fs
+```
+
+### 3. Create an AI Agent
+
+```typescript
+import { AIAgent } from "@aigne/core";
+
+const agent = AIAgent.from({
+  instructions: "Help users find and read files from the local file system.",
+  inputKey: "message",
+  afs,  // Agent gets: afs_list, afs_read, afs_write, afs_search
+});
+```
+
+**That's it!** The agent can now intelligently search and retrieve files from your local directory.
+
+### What the Agent Can Do
+
+- **`afs_list`** - List files and directories (with recursive depth control)
+- **`afs_read`** - Read file contents and metadata
+- **`afs_write`** - Create or update files
+- **`afs_search`** - Fast full-text search using ripgrep (supports regex)
+
+All operations are sandboxed to the mounted directory for safety.
+
+## Try These Examples
+
+```bash
+# Mount AIGNE docs and ask questions
+git clone https://github.com/AIGNE-io/aigne-framework
+npx -y @aigne/example-afs-local-fs --path ./aigne-framework --input "What is AIGNE?"
+
+# Ask about specific features
+npx -y @aigne/example-afs-local-fs --path ./aigne-framework --input "How does AFS work?"
+
+# Search your codebase
+npx -y @aigne/example-afs-local-fs --path . --input "Find all TypeScript files with TODO comments"
+
+# Interactive mode - ask follow-up questions
+npx -y @aigne/example-afs-local-fs --path ~/Documents --chat
+```
+
+**In chat mode, try:**
+- "What files are in this directory?"
+- "Show me the README"
+- "Search for 'authentication' in all files"
+- "Find all Python files"
+- "What does the config.json file contain?"
+
+## Use Cases
+
+### Documentation Chat
+Mount your project docs and let users ask questions:
+```typescript
+const afs = new AFS()
+  .mount(new LocalFS({ localPath: './docs', description: 'Project documentation' }));
+// Users can now ask: "How do I configure authentication?"
+```
+
+### Codebase Analysis
+Give AI agents access to your codebase:
+```typescript
+const afs = new AFS()
+  .mount(new LocalFS({ localPath: './src', description: 'Source code' }));
+// Agent can search, read, and explain code
+```
+
+### File Organization
+Let AI help organize your files:
+```typescript
+const afs = new AFS()
+  .mount(new LocalFS({ localPath: '~/Downloads', description: 'Downloads folder' }));
+// Ask: "Find all PDFs from last week" or "Organize these files by type"
+```
+
+### Multi-Directory Access
+Mount multiple directories simultaneously:
+```typescript
+const afs = new AFS()
+  .mount("/docs", new LocalFS({ localPath: './docs' }))
+  .mount("/src", new LocalFS({ localPath: './src' }))
+  .mount("/tests", new LocalFS({ localPath: './tests' }));
+// Agent can search across all mounted directories
+```
+
+## Related Examples
+
+- [AFS Memory Example](../afs-memory/README.md) - Conversational memory with user profiles
+- [AFS MCP Server Example](../afs-mcp-server/README.md) - Integration with MCP servers
+
+## Related Packages
+
+- [@aigne/afs](../../afs/README.md) - AFS core package
+- [@aigne/afs-local-fs](../../afs/local-fs/README.md) - LocalFS module documentation
+
+## TypeScript Support
+
+This package includes full TypeScript type definitions.
+
+## License
+
+[MIT](../../LICENSE.md)

package/index.test.ts

@@ -0,0 +1,11 @@
+import { expect, test } from "bun:test";
+import { runExampleTest } from "@aigne/test-utils/run-example-test.js";
+
+test(
+  "should successfully run the chatbot",
+  async () => {
+    const { status } = await runExampleTest();
+    expect(status).toBe(0);
+  },
+  { timeout: 600000 },
+);

package/index.ts

@@ -0,0 +1,44 @@
+#!/usr/bin/env npx -y bun
+
+import { AFS } from "@aigne/afs";
+import { AFSHistory } from "@aigne/afs-history";
+import { LocalFS } from "@aigne/afs-local-fs";
+import { loadAIGNEWithCmdOptions, runWithAIGNE } from "@aigne/cli/utils/run-with-aigne.js";
+import { AIAgent } from "@aigne/core";
+import yargs from "yargs";
+
+const argv = yargs()
+  .option("path", {
+    type: "string",
+    describe: "Path to the directory to mount",
+    default: ".",
+  })
+  .option("description", {
+    type: "string",
+    default: "Working directory mounted from local file system",
+    describe: "Description of the mounted file system",
+  })
+  .demandOption("path")
+  .strict(false)
+  .parseSync(process.argv);
+
+const aigne = await loadAIGNEWithCmdOptions();
+
+const afs = new AFS()
+  .mount(new AFSHistory({ storage: { url: ":memory:" } })) // In-memory history for this example
+  .mount(new LocalFS({ localPath: argv.path, description: argv.description }));
+
+const agent = AIAgent.from({
+  instructions:
+    "You are a friendly chatbot that can retrieve files from a virtual file system. You should use the provided functions to list, search, and read files as needed to answer user questions.",
+  inputKey: "message",
+  afs,
+});
+
+await runWithAIGNE(agent, {
+  aigne,
+  chatLoopOptions: {
+    welcome:
+      "Hello! I'm a chatbot that can help you interact with a local file system mounted on AFS. Ask me anything about the files!",
+  },
+});

package/package.json

@@ -0,0 +1,35 @@
+{
+  "name": "@aigne/example-afs-local-fs",
+  "version": "1.1.0-beta",
+  "description": "A demonstration of using AIGNE Framework with AFS LocalFS module",
+  "author": "Arcblock <blocklet@arcblock.io> https://github.com/blocklet",
+  "homepage": "https://github.com/AIGNE-io/aigne-framework/tree/main/examples/afs-local-fs",
+  "license": "MIT",
+  "repository": {
+    "type": "git",
+    "url": "git+https://github.com/AIGNE-io/aigne-framework"
+  },
+  "bin": "index.ts",
+  "files": [
+    ".env.local.example",
+    "*.ts",
+    "README.md"
+  ],
+  "dependencies": {
+    "yargs": "^18.0.0",
+    "@aigne/afs": "^1.2.0-beta",
+    "@aigne/afs-history": "^1.0.0",
+    "@aigne/afs-local-fs": "^1.1.0-beta",
+    "@aigne/cli": "^1.55.0-beta",
+    "@aigne/core": "^1.68.0-beta"
+  },
+  "devDependencies": {
+    "@types/bun": "^1.2.22",
+    "@aigne/test-utils": "^0.5.60-beta"
+  },
+  "scripts": {
+    "start": "bun run index.ts",
+    "lint": "tsc --noEmit",
+    "test:llm": "bun test index.test.ts"
+  }
+}