@everworker/oneringai

v0.5.2

Published

7 hours ago

Unified AI agent library with multi-vendor support for text generation, image generation, and agentic workflows

@everworker/oneringai

A unified AI agent library with multi-provider support for text generation, image/video generation, audio (TTS/STT), and agentic workflows.

Features
Quick Start — Installation, basic usage, tools, vision, audio, images, video, search, scraping
Supported Providers
Key Features
- 1. Agent with Plugins
- 2. Dynamic Tool Management
- 3. Tool Execution Plugins
- 4. Session Persistence
- Storage Registry
- 5. Working Memory
- 6. Research with Search Tools
- 7. Context Management
- 8. InContextMemory
- 9. Persistent Instructions
- 10. User Info
- 11. Direct LLM Access
- 12. Audio Capabilities
- Embeddings — Multi-vendor text embeddings with MRL dimension control
- 13. Model Registry
- 14. Streaming
- 15. OAuth for External APIs
- 16. Developer Tools
- 17. Custom Tool Generation — Agents create, test, and persist their own tools
- 18. Document Reader — PDF, DOCX, XLSX, PPTX, CSV, HTML, images
- 20. Routine Execution — Multi-step workflows with task dependencies, validation, and memory bridging
- 21. External API Integration — Scoped Registry, Vendor Templates, Tool Discovery
- 22. Microsoft Graph Connector Tools — Email, calendar, meetings, and Teams transcripts
- 23. Tool Catalog — Dynamic tool loading/unloading for agents with 100+ tools
- 24. Async (Non-Blocking) Tools — Background tool execution with auto-continuation
- 25. Long-Running Sessions (Suspend/Resume) — Suspend agent loops waiting for external input, resume days later
- 26. Agent Registry — Global tracking, deep inspection, parent/child hierarchy, event fan-in, external control
- 27. Agent Orchestrator — Multi-agent teams with shared workspace, delegation, and async execution
- 28. Telegram Connector Tools — Bot API tools for messaging, updates, and webhooks
- 29. Twilio Connector Tools — SMS and WhatsApp messaging tools
MCP Integration
Documentation
Examples
Development
Architecture
Troubleshooting
Contributing
License

Documentation

Start here if you're looking for detailed docs or the full API reference.

| Document | Description | |----------|-------------| | User Guide | Comprehensive guide covering every feature with examples — connectors, agents, context, plugins, audio, video, search, MCP, OAuth, and more | | API Reference | Auto-generated reference for all 600+ public exports — classes, interfaces, types, and functions with signatures | | CHANGELOG | Version history and migration notes |

Tutorial / Architecture Series

Part 0. One Lib to Rule Them All: Why We Built OneRingAI: introduction and architecture overview

Part 1. Your AI Agent Forgets Everything. Here’s How We Fixed It.: context management plugins

EVERWORKER DESKTOP APP

We realize that library alone in these times is not enough to get you excited, so we built a FREE FOREVER desktop app on top of this library to showcase its power! It's as easy to start using as cloning this library's repo, and then cd apps/hosea and then npm install and then npm run dev. Or watch the video first:

Or read the more detailed installation / setup instructions here

Better to see once and then dig in the code! :)

YOUetal

Showcasing another amazing "built with oneringai": "no saas" agentic business team

Features

✨ Unified API - One interface for 10+ AI providers (OpenAI, Anthropic, Google, Groq, DeepSeek, and more)
🔑 Connector-First Architecture - Single auth system with support for multiple keys per vendor
📊 Model Registry - Complete metadata for 35+ latest (2026) models with pricing and features
🎤 Audio Capabilities - Text-to-Speech (TTS) and Speech-to-Text (STT) with OpenAI and Groq
🖼️ Image Generation - DALL-E 3, gpt-image-1, Google Imagen 4 with editing and variations
🎬 Video Generation - NEW: OpenAI Sora 2 and Google Veo 3 for AI video creation
🔢 Embeddings - NEW: Multi-vendor embedding generation with MRL dimension control (OpenAI, Google, Ollama, Mistral)
🔍 Web Search - Connector-based search with Serper, Brave, Tavily, and RapidAPI providers
🔌 NextGen Context - Clean, plugin-based context management with AgentContextNextGen
🎛️ Dynamic Tool Management - Enable/disable tools at runtime, namespaces, priority-based selection
🔌 Tool Execution Plugins - NEW: Pluggable pipeline for logging, analytics, UI updates, custom behavior
💾 Session Persistence - Save and resume conversations with full state restoration
⏸️ Long-Running Sessions - NEW: Suspend agent loops via SuspendSignal, resume hours/days later with Agent.hydrate()
👤 Multi-User Support - Set userId once, flows automatically to all tool executions and session metadata
🔒 Auth Identities - Restrict agents to specific connectors (and accounts), composable with access policies
🤖 Universal Agent - ⚠️ Deprecated - Use Agent with plugins instead
🤖 Task Agents - ⚠️ Deprecated - Use Agent with WorkingMemoryPluginNextGen
🔬 Research Agent - ⚠️ Deprecated - Use Agent with search tools
🎯 Context Management - Algorithmic compaction with tool-result-to-memory offloading
📌 InContextMemory - Live key-value storage directly in LLM context with optional UI display (showInUI)
📝 Persistent Instructions - NEW: Agent-level custom instructions that persist across sessions on disk
👤 User Info Plugin - NEW: Per-user preferences/context automatically injected into LLM context, shared across agents
🛠️ Agentic Workflows - Built-in tool calling and multi-turn conversations
🔧 Developer Tools - NEW: Filesystem and shell tools for coding assistants (read, write, edit, grep, glob, bash)
🧰 Custom Tool Generation - NEW: Let agents create, test, and persist their own reusable tools at runtime — complete meta-tool system with VM sandbox
🖥️ Desktop Automation - NEW: OS-level computer use — screenshot, mouse, keyboard, and window control for vision-driven agent loops
📄 Document Reader - NEW: Universal file-to-text converter — PDF, DOCX, XLSX, PPTX, CSV, HTML, images auto-converted to markdown
🔌 MCP Integration - NEW: Model Context Protocol client for seamless tool discovery from local and remote servers
👁️ Vision Support - Analyze images with AI across all providers
📋 Clipboard Integration - Paste screenshots directly (like Claude Code!)
🔐 Scoped Connector Registry - NEW: Pluggable access control for multi-tenant connector isolation
💾 StorageRegistry - Centralized storage configuration — swap all backends (sessions, media, custom tools, etc.) with one configure() call
🔐 OAuth 2.0 - Full OAuth support for external APIs with encrypted token storage
📦 Vendor Templates - NEW: Pre-configured auth templates for 43+ services (GitHub, Slack, Stripe, etc.)
📧 Microsoft Graph Tools - NEW: Email, calendar, meetings, and Teams transcripts via Microsoft Graph API
🔁 Routine Execution - NEW: Multi-step workflows with task dependencies, LLM validation, retry logic, and memory bridging between tasks
📊 Execution Recording - NEW: Persist full routine execution history with createExecutionRecorder() — replaces manual hook wiring
⏰ Scheduling & Triggers - NEW: SimpleScheduler for interval/one-time schedules, EventEmitterTrigger for webhook/queue-driven execution
📦 Tool Catalog - NEW: Dynamic tool loading/unloading — agents discover and load only the categories they need at runtime
Async Tools - NEW: Non-blocking tool execution — long-running tools run in background while the agent continues reasoning, with auto-continuation when results arrive
📡 Agent Registry - NEW: Global tracking of all active agents — deep inspection, parent/child hierarchy, event fan-in, external control
📱 Telegram Tools - NEW: 6 Telegram Bot API tools — send messages/photos, get updates, webhooks, chat info
📞 Twilio Tools - NEW: 4 Twilio tools — SMS, WhatsApp messaging, message listing and details
🔄 Streaming - Real-time responses with event streams
📝 TypeScript - Full type safety and IntelliSense support

v0.2.0 — Multi-User Support: Set userId once on an agent and it automatically flows to all tool executions, OAuth token retrieval, session metadata, and connector scoping. Combine with identities and access policies for complete multi-tenant isolation. See Multi-User Support and Auth Identities in the User Guide.

Quick Start

Installation

npm install @everworker/oneringai

Basic Usage

import { Connector, Agent, Vendor } from '@everworker/oneringai';

// 1. Create a connector (authentication)
Connector.create({
  name: 'openai',
  vendor: Vendor.OpenAI,
  auth: { type: 'api_key', apiKey: process.env.OPENAI_API_KEY! },
});

// 2. Create an agent
const agent = Agent.create({
  connector: 'openai',
  model: 'gpt-4',
});

// 3. Run
const response = await agent.run('What is the capital of France?');
console.log(response.output_text);
// Output: "The capital of France is Paris."

With Tools

import { ToolFunction } from '@everworker/oneringai';

const weatherTool: ToolFunction = {
  definition: {
    type: 'function',
    function: {
      name: 'get_weather',
      description: 'Get current weather',
      parameters: {
        type: 'object',
        properties: {
          location: { type: 'string' },
        },
        required: ['location'],
      },
    },
  },
  execute: async (args) => {
    return { temp: 72, location: args.location };
  },
};

const agent = Agent.create({
  connector: 'openai',
  model: 'gpt-4',
  tools: [weatherTool],
});

await agent.run('What is the weather in Paris?');

Vision

import { createMessageWithImages } from '@everworker/oneringai';

const agent = Agent.create({
  connector: 'openai',
  model: 'gpt-4o',
});

const response = await agent.run(
  createMessageWithImages('What is in this image?', ['./photo.jpg'])
);

Audio (NEW)

import { TextToSpeech, SpeechToText } from '@everworker/oneringai';

// Text-to-Speech
const tts = TextToSpeech.create({
  connector: 'openai',
  model: 'tts-1-hd',
  voice: 'nova',
});

await tts.toFile('Hello, world!', './output.mp3');

// Speech-to-Text
const stt = SpeechToText.create({
  connector: 'openai',
  model: 'whisper-1',
});

const result = await stt.transcribeFile('./audio.mp3');
console.log(result.text);

Image Generation (NEW)

import { ImageGeneration } from '@everworker/oneringai';

// OpenAI DALL-E
const imageGen = ImageGeneration.create({ connector: 'openai' });

const result = await imageGen.generate({
  prompt: 'A futuristic city at sunset',
  model: 'dall-e-3',
  size: '1024x1024',
  quality: 'hd',
});

// Save to file
const buffer = Buffer.from(result.data[0].b64_json!, 'base64');
await fs.writeFile('./output.png', buffer);

// Google Imagen
const googleGen = ImageGeneration.create({ connector: 'google' });

const googleResult = await googleGen.generate({
  prompt: 'A colorful butterfly in a garden',
  model: 'imagen-4.0-generate-001',
});

Video Generation (NEW)

import { VideoGeneration } from '@everworker/oneringai';

// OpenAI Sora
const videoGen = VideoGeneration.create({ connector: 'openai' });

// Start video generation (async - returns a job)
const job = await videoGen.generate({
  prompt: 'A cinematic shot of a sunrise over mountains',
  model: 'sora-2',
  duration: 8,
  resolution: '1280x720',
});

// Wait for completion
const result = await videoGen.waitForCompletion(job.jobId);

// Download the video
const videoBuffer = await videoGen.download(job.jobId);
await fs.writeFile('./output.mp4', videoBuffer);

// Google Veo
const googleVideo = VideoGeneration.create({ connector: 'google' });

const veoJob = await googleVideo.generate({
  prompt: 'A butterfly flying through a garden',
  model: 'veo-3.0-generate-001',
  duration: 8,
});

Embeddings (NEW)

import { Embeddings } from '@everworker/oneringai';

// OpenAI embeddings
const embeddings = Embeddings.create({ connector: 'openai' });

const result = await embeddings.embed(['Hello world', 'How are you?'], {
  model: 'text-embedding-3-small',
  dimensions: 512,  // MRL: reduce dimensions for faster search
});

console.log(result.embeddings.length);     // 2
console.log(result.embeddings[0].length);  // 512

// Ollama (local, free)
const local = Embeddings.create({ connector: 'ollama-local' });
const localResult = await local.embed('search query');
// Uses qwen3-embedding (4096 dims, #1 on MTEB multilingual)

Document Reader (NEW)

Read any document format — agents automatically get markdown text from PDFs, Word docs, spreadsheets, and more:

import { Agent, developerTools } from '@everworker/oneringai';

const agent = Agent.create({
  connector: 'openai',
  model: 'gpt-4',
  tools: developerTools,
});

// read_file auto-converts binary documents to markdown
await agent.run('Read /path/to/report.pdf and summarize the key findings');
await agent.run('Read /path/to/data.xlsx and describe the trends');
await agent.run('Read /path/to/presentation.pptx and list all slides');

Programmatic usage:

import { DocumentReader, readDocumentAsContent } from '@everworker/oneringai';

// Read any file to markdown pieces
const reader = DocumentReader.create();
const result = await reader.read('/path/to/report.pdf');
console.log(result.pieces); // DocumentPiece[] (text + images)

// One-call conversion to LLM Content[] (for multimodal input)
const content = await readDocumentAsContent('/path/to/slides.pptx', {
  imageFilter: { minWidth: 100, minHeight: 100 },
  imageDetail: 'auto',
});

const response = await agent.run([
  { type: 'input_text', text: 'Analyze this document:' },
  ...content,
]);

Supported Formats:

Office: DOCX, PPTX, ODT, ODP, ODS, RTF (via officeparser)
Spreadsheets: XLSX, CSV (via exceljs)
PDF (via unpdf)
HTML (via Readability + Turndown)
Text: TXT, MD, JSON, XML, YAML
Images: PNG, JPG, GIF, WEBP, SVG (pass-through as base64)

Web Search

Connector-based web search with multiple providers:

import { Connector, SearchProvider, ConnectorTools, Services, Agent, tools } from '@everworker/oneringai';

// Create search connector
Connector.create({
  name: 'serper-main',
  serviceType: Services.Serper,
  auth: { type: 'api_key', apiKey: process.env.SERPER_API_KEY! },
  baseURL: 'https://google.serper.dev',
});

// Option 1: Use SearchProvider directly
const search = SearchProvider.create({ connector: 'serper-main' });
const results = await search.search('latest AI developments 2026', {
  numResults: 10,
  country: 'us',
  language: 'en',
});

// Option 2: Use with Agent via ConnectorTools
const searchTools = ConnectorTools.for('serper-main');

const agent = Agent.create({
  connector: 'openai',
  model: 'gpt-4',
  tools: [...searchTools, tools.webFetch],
});

await agent.run('Search for quantum computing news and summarize');

Supported Search Providers:

Serper - Google search via Serper.dev (2,500 free queries)
Brave - Independent search index (privacy-focused)
Tavily - AI-optimized search with summaries
RapidAPI - Real-time web search (various pricing)

Web Scraping

Enterprise web scraping with automatic fallback and bot protection bypass:

import { Connector, ScrapeProvider, ConnectorTools, Services, Agent, tools } from '@everworker/oneringai';

// Create ZenRows connector for bot-protected sites
Connector.create({
  name: 'zenrows',
  serviceType: Services.Zenrows,
  auth: { type: 'api_key', apiKey: process.env.ZENROWS_API_KEY! },
  baseURL: 'https://api.zenrows.com/v1',
});

// Option 1: Use ScrapeProvider directly
const scraper = ScrapeProvider.create({ connector: 'zenrows' });
const result = await scraper.scrape('https://protected-site.com', {
  includeMarkdown: true,
  vendorOptions: {
    jsRender: true,        // JavaScript rendering
    premiumProxy: true,    // Residential IPs
  },
});

// Option 2: Use web_scrape tool with Agent via ConnectorTools
const scrapeTools = ConnectorTools.for('zenrows');

const agent = Agent.create({
  connector: 'openai',
  model: 'gpt-4',
  tools: [...scrapeTools, tools.webFetch],
});

// web_scrape auto-falls back: native → API
await agent.run('Scrape https://example.com and summarize');

Supported Scrape Providers:

ZenRows - Enterprise scraping with JS rendering, residential proxies, anti-bot bypass
Jina Reader - Clean content extraction with AI-powered readability
Firecrawl - Web scraping with JavaScript rendering
ScrapingBee - Headless browser scraping with proxy rotation

Supported Providers

| Provider | Text | Vision | TTS | STT | Image | Video | Tools | Context | |----------|------|--------|-----|-----|-------|-------|-------|---------| | OpenAI | ✅ | ✅ | ✅ | ✅ | ✅ | ✅ | ✅ | 128K | | Anthropic (Claude) | ✅ | ✅ | ❌ | ❌ | ❌ | ❌ | ✅ | 200K | | Google (Gemini) | ✅ | ✅ | ✅ | ❌ | ✅ | ✅ | ✅ | 1M | | Google Vertex AI | ✅ | ✅ | ❌ | ❌ | ❌ | ❌ | ✅ | 1M | | Grok (xAI) | ✅ | ✅ | ❌ | ❌ | ✅ | ✅ | ✅ | 128K | | Groq | ✅ | ❌ | ❌ | ✅ | ❌ | ❌ | ✅ | 128K | | Together AI | ✅ | Some | ❌ | ❌ | ❌ | ❌ | ✅ | 128K | | DeepSeek | ✅ | ❌ | ❌ | ❌ | ❌ | ❌ | ✅ | 64K | | Mistral | ✅ | ❌ | ❌ | ❌ | ❌ | ❌ | ✅ | 32K | | Ollama | ✅ | Varies | ❌ | ❌ | ❌ | ❌ | ✅ | Varies | | Custom | ✅ | Varies | ❌ | ❌ | ❌ | ❌ | ✅ | Varies |

Key Features

1. Agent with Plugins

The Agent class is the primary agent type, supporting all features through composable plugins:

import { Agent, createFileContextStorage } from '@everworker/oneringai';

// Create storage for session persistence
const storage = createFileContextStorage('my-assistant');

const agent = Agent.create({
  connector: 'openai',
  model: 'gpt-4',
  userId: 'user-123',            // Flows to all tool executions automatically
  identities: [                   // Only these connectors visible to tools
    { connector: 'github' },
    { connector: 'slack' },
  ],
  tools: [weatherTool, emailTool],
  context: {
    features: {
      workingMemory: true,      // Store/retrieve data across turns
      inContextMemory: true,    // Key-value pairs directly in context
      persistentInstructions: true,  // Agent instructions that persist to disk
    },
    agentId: 'my-assistant',
    storage,
  },
});

// Run the agent
const response = await agent.run('Check weather and email me the report');
console.log(response.output_text);

// Save session for later
await agent.context.save('session-001');

Features:

🔧 Plugin Architecture - Enable/disable features via context.features
💾 Session Persistence - Save/load full state with ctx.save() and ctx.load()
📝 Working Memory - Store findings with automatic eviction
📌 InContextMemory - Key-value pairs visible directly to LLM
🔄 Persistent Instructions - Agent instructions that persist across sessions

2. Dynamic Tool Management (NEW)

Control tools at runtime. AgentContextNextGen is the single source of truth - agent.tools and agent.context.tools are the same ToolManager instance:

import { Agent } from '@everworker/oneringai';

const agent = Agent.create({
  connector: 'openai',
  model: 'gpt-4',
  tools: [weatherTool, emailTool, databaseTool],
});

// Disable tool temporarily
agent.tools.disable('database_tool');

// Enable later
agent.tools.enable('database_tool');

// UNIFIED ACCESS: Both paths access the same ToolManager
console.log(agent.tools === agent.context.tools);  // true

// Changes via either path are immediately reflected
agent.context.tools.disable('email_tool');
console.log(agent.tools.listEnabled().includes('email_tool'));  // false

// Context-aware selection
const selected = agent.tools.selectForContext({
  mode: 'interactive',
  priority: 'high',
});

// Backward compatible
agent.addTool(newTool);        // Still works!
agent.removeTool('old_tool');  // Still works!

3. Tool Execution Plugins (NEW)

Extend tool execution with custom behavior through a pluggable pipeline architecture. Add logging, analytics, UI updates, permission prompts, or any custom logic:

import { Agent, LoggingPlugin, type IToolExecutionPlugin } from '@everworker/oneringai';

const agent = Agent.create({
  connector: 'openai',
  model: 'gpt-4',
  tools: [weatherTool],
});

// Add built-in logging plugin
agent.tools.executionPipeline.use(new LoggingPlugin());

// Create a custom plugin
const analyticsPlugin: IToolExecutionPlugin = {
  name: 'analytics',
  priority: 100,

  async beforeExecute(ctx) {
    console.log(`Starting ${ctx.toolName}`);
  },

  async afterExecute(ctx, result) {
    const duration = Date.now() - ctx.startTime;
    trackToolUsage(ctx.toolName, duration);
    return result; // Must return result (can transform it)
  },

  async onError(ctx, error) {
    reportError(ctx.toolName, error);
    return undefined; // Let error propagate (or return value to recover)
  },
};

agent.tools.executionPipeline.use(analyticsPlugin);

Plugin Lifecycle:

beforeExecute - Modify args, abort execution, or pass through
Tool execution
afterExecute - Transform results (runs in reverse priority order)
onError - Handle/recover from errors

Plugin Context (PluginExecutionContext):

interface PluginExecutionContext {
  toolName: string;           // Name of the tool being executed
  args: unknown;              // Original arguments (read-only)
  mutableArgs: unknown;       // Modifiable arguments
  metadata: Map<string, unknown>; // Share data between plugins
  startTime: number;          // Execution start timestamp
  tool: ToolFunction;         // The tool being executed
  executionId: string;        // Unique ID for this execution
}

Built-in Plugins:

LoggingPlugin - Logs tool execution with timing and result summaries

Pipeline Management:

// Add plugin
agent.tools.executionPipeline.use(myPlugin);

// Remove plugin
agent.tools.executionPipeline.remove('plugin-name');

// Check if registered
agent.tools.executionPipeline.has('plugin-name');

// Get plugin
const plugin = agent.tools.executionPipeline.get('plugin-name');

// List all plugins
const plugins = agent.tools.executionPipeline.list();

4. Tool Permissions (NEW)

Policy-based permission system with per-user rules, argument inspection, and pluggable storage. Permissions are enforced at the ToolManager pipeline level -- all tool execution paths are gated.

Zero-Config (Backward Compatible)

Existing code works unchanged. Safe tools (read-only, memory, catalog) are auto-allowed; all others default to prompting:

const agent = Agent.create({ connector: 'openai', model: 'gpt-4', tools: [readFile, bash] });

// read_file executes immediately (in DEFAULT_ALLOWLIST)
// bash triggers approval flow (write/shell tools require approval by default)

Per-User Permission Rules

User rules have the highest priority -- they override all built-in policies. Rules support argument inspection with conditions:

import { PermissionPolicyManager } from '@everworker/oneringai';

const manager = new PermissionPolicyManager({
  userRules: [
    // Allow bash, but only in the project directory
    {
      id: '1', toolName: 'bash', action: 'allow', enabled: true,
      createdBy: 'user', createdAt: new Date().toISOString(), updatedAt: new Date().toISOString(),
      conditions: [{ argName: 'command', operator: 'not_contains', value: 'rm -rf' }],
    },
    // Block all web tools unconditionally
    {
      id: '2', toolName: 'web_fetch', action: 'deny', enabled: true, unconditional: true,
      createdBy: 'admin', createdAt: new Date().toISOString(), updatedAt: new Date().toISOString(),
    },
  ],
});

Condition operators: starts_with, not_starts_with, contains, not_contains, equals, not_equals, matches (regex), not_matches.

Built-in Policies

Eight composable policies evaluated in priority order (deny short-circuits):

| Policy | Description | |--------|-------------| | AllowlistPolicy | Auto-allow tools in the allowlist (read-only, memory, catalog) | | BlocklistPolicy | Hard-block tools in the blocklist (no approval possible) | | SessionApprovalPolicy | Cache approvals per-session with optional argument-scoped keys | | PathRestrictionPolicy | Restrict file tools to allowed directory roots | | BashFilterPolicy | Block/flag dangerous shell commands by pattern | | UrlAllowlistPolicy | Restrict web tools to allowed URL domains | | RolePolicy | Role-based access control (map user roles to tool permissions) | | RateLimitPolicy | Limit tool invocations per time window |

import { PathRestrictionPolicy, BashFilterPolicy } from '@everworker/oneringai';

const agent = Agent.create({
  connector: 'openai', model: 'gpt-4',
  permissions: {
    policies: [
      new PathRestrictionPolicy({ allowedPaths: ['/workspace'] }),
      new BashFilterPolicy({ blockedPatterns: ['rm -rf', 'sudo'] }),
    ],
  },
});

Approval Dialog Integration

When a tool needs approval, the onApprovalRequired callback fires. Return a createRule to persist the decision:

const agent = Agent.create({
  connector: 'openai', model: 'gpt-4',
  permissions: {
    onApprovalRequired: async (ctx) => {
      const userChoice = await showApprovalDialog(ctx.toolName, ctx.args);

      return {
        approved: userChoice.allow,
        // Persist as a user rule so it won't ask again
        createRule: userChoice.remember ? {
          description: `Auto-allow ${ctx.toolName}`,
          conditions: [{ argName: 'path', operator: 'starts_with', value: '/workspace' }],
        } : undefined,
      };
    },
  },
});

Tool Self-Declaration

Tool authors declare permission defaults on the tool definition. App developers can override at registration:

const myTool: ToolFunction = {
  definition: { type: 'function', function: { name: 'deploy', description: '...', parameters: {...} } },
  execute: async (args) => { /* ... */ },
  // Author-declared defaults
  permission: {
    scope: 'once',
    riskLevel: 'high',
    approvalMessage: 'This will deploy to production',
    sensitiveArgs: ['environment', 'version'],
  },
};

// App developer can override at registration
agent.tools.register(myTool, {
  permission: { scope: 'session' },  // Relax to session-level approval
});

For complete documentation, see the User Guide.

5. Session Persistence

Save and resume full context state including conversation history and plugin states:

import { AgentContextNextGen, createFileContextStorage } from '@everworker/oneringai';

// Create storage for the agent
const storage = createFileContextStorage('my-assistant');

// Create context with storage
const ctx = AgentContextNextGen.create({
  model: 'gpt-4',
  features: { workingMemory: true },
  storage,
});

// Build up state
ctx.addUserMessage('Remember: my favorite color is blue');
await ctx.memory?.store('user_color', 'User favorite color', 'blue');

// Save session with metadata
await ctx.save('session-001', { title: 'User Preferences' });

// Later... load session
const ctx2 = AgentContextNextGen.create({ model: 'gpt-4', storage });
const loaded = await ctx2.load('session-001');

if (loaded) {
  // Full state restored: conversation, plugin states, etc.
  const color = await ctx2.memory?.retrieve('user_color');
  console.log(color); // 'blue'
}

What's Persisted:

Complete conversation history
All plugin states (WorkingMemory entries, InContextMemory, etc.)
System prompt

Storage Location: ~/.oneringai/agents/<agentId>/sessions/<sessionId>.json

Storage Registry

Swap all storage backends (sessions, media, custom tools, OAuth tokens, etc.) with a single configure() call at init time. No breaking changes — all existing APIs continue to work.

import { StorageRegistry } from '@everworker/oneringai';

StorageRegistry.configure({
  media: new S3MediaStorage(),
  oauthTokens: new EncryptedFileTokenStorage(),
  // Context-aware factories — optional StorageContext for multi-tenant partitioning
  customTools: (ctx) => new MongoCustomToolStorage(ctx?.userId),
  sessions: (agentId, ctx) => new RedisContextStorage(agentId, ctx?.tenantId),
  persistentInstructions: (agentId, ctx) => new DBInstructionsStorage(agentId, ctx?.userId),
  workingMemory: (ctx) => new RedisMemoryStorage(ctx?.tenantId),
  routineDefinitions: (ctx) => new MongoRoutineStorage(ctx?.userId),
});

// All agents and tools automatically use these backends
const agent = Agent.create({ connector: 'openai', model: 'gpt-4' });

Resolution order: explicit constructor param > StorageRegistry > file-based default.

Multi-tenant: Factories receive an optional StorageContext (opaque, like ConnectorAccessContext). Set via StorageRegistry.setContext({ userId, tenantId }) — auto-forwarded to all factory calls for per-user/per-tenant storage partitioning.

See the User Guide for full documentation.

6. Working Memory

Use the WorkingMemoryPluginNextGen for agents that need to store and retrieve data:

import { Agent } from '@everworker/oneringai';

const agent = Agent.create({
  connector: 'openai',
  model: 'gpt-4',
  tools: [weatherTool, emailTool],
  context: {
    features: { workingMemory: true },
  },
});

// Agent now has unified store_get, store_set, store_delete, store_list, store_action tools
await agent.run('Check weather for SF and remember the result');

Features:

📝 Working Memory - Store and retrieve data with priority-based eviction
🏗️ Hierarchical Memory - Raw → Summary → Findings tiers for research tasks
🧠 Context Management - Automatic handling of context limits
💾 Session Persistence - Save/load via ctx.save() and ctx.load()

7. Research with Search Tools

Use Agent with search tools and WorkingMemoryPluginNextGen for research workflows:

import { Agent, ConnectorTools, Connector, Services, tools } from '@everworker/oneringai';

// Setup search connector
Connector.create({
  name: 'serper-main',
  serviceType: Services.Serper,
  auth: { type: 'api_key', apiKey: process.env.SERPER_API_KEY! },
  baseURL: 'https://google.serper.dev',
});

// Create agent with search and memory
const searchTools = ConnectorTools.for('serper-main');

const agent = Agent.create({
  connector: 'openai',
  model: 'gpt-4',
  tools: [...searchTools, tools.webFetch],
  context: {
    features: { workingMemory: true },
  },
});

// Agent can search and store findings in memory
await agent.run('Research AI developments in 2026 and store key findings');

Features:

🔍 Web Search - SearchProvider with Serper, Brave, Tavily, RapidAPI
📝 Working Memory - Store findings with priority-based eviction
🏗️ Tiered Memory - Raw → Summary → Findings pattern

8. Context Management

AgentContextNextGen is the modern, plugin-based context manager. It provides clean separation of concerns with composable plugins:

import { Agent, AgentContextNextGen } from '@everworker/oneringai';

// Option 1: Use AgentContextNextGen directly (standalone)
const ctx = AgentContextNextGen.create({
  model: 'gpt-4',
  systemPrompt: 'You are a helpful assistant.',
  features: { workingMemory: true, inContextMemory: true },
});

ctx.addUserMessage('What is the weather in Paris?');
const { input, budget } = await ctx.prepare(); // Ready for LLM call

// Option 2: Via Agent.create
const agent = Agent.create({
  connector: 'openai',
  model: 'gpt-4',
  context: {
    features: { workingMemory: true },
  },
});

// Agent uses AgentContextNextGen internally
await agent.run('Check the weather');

Feature Configuration

Enable/disable features independently. Disabled features = no associated tools registered:

// Minimal stateless agent (no memory)
const agent = Agent.create({
  connector: 'openai',
  model: 'gpt-4',
  context: {
    features: { workingMemory: false }
  }
});

// Full-featured agent with all plugins
const agent = Agent.create({
  connector: 'openai',
  model: 'gpt-4',
  context: {
    features: {
      workingMemory: true,
      inContextMemory: true,
      persistentInstructions: true
    },
    agentId: 'my-assistant',  // Required for persistentInstructions
  }
});

Available Features: | Feature | Default | Plugin | Associated Tools | |---------|---------|--------|------------------| | workingMemory | true | WorkingMemoryPluginNextGen | Unified store_* tools (store="memory"). Actions: cleanup_raw, query | | inContextMemory | false | InContextMemoryPluginNextGen | Unified store_* tools (store="context") | | persistentInstructions | false | PersistentInstructionsPluginNextGen | Unified store_* tools (store="instructions"). Actions: clear | | userInfo | false | UserInfoPluginNextGen | Unified store_* tools (store="user_info") + todo_add/update/remove | | toolCatalog | false | ToolCatalogPluginNextGen | tool_catalog_search/load/unload | | sharedWorkspace | false | SharedWorkspacePluginNextGen | Unified store_* tools (store="workspace"). Actions: log, history, archive, clear |

AgentContextNextGen architecture:

Plugin-first design - All features are composable plugins
ToolManager - Tool registration, execution, circuit breakers
Single system message - All context components combined
Smart compaction - Happens once, right before LLM call

Compaction strategy:

algorithmic (default) - Moves large tool results to Working Memory, limits tool pairs, applies rolling window. Triggers at 75% context usage.

Context preparation:

const { input, budget, compacted, compactionLog } = await ctx.prepare();

console.log(budget.totalUsed);           // Total tokens used
console.log(budget.available);           // Remaining tokens
console.log(budget.utilizationPercent);  // Usage percentage

9. InContextMemory

Store key-value pairs directly in context for instant LLM access without retrieval calls:

import { AgentContextNextGen } from '@everworker/oneringai';

const ctx = AgentContextNextGen.create({
  model: 'gpt-4',
  features: { inContextMemory: true },
  plugins: {
    inContextMemory: { maxEntries: 20 },
  },
});

// Access the plugin
const plugin = ctx.getPlugin('in_context_memory');

// Store data - immediately visible to LLM
plugin.set('current_state', 'Task processing state', { step: 2, status: 'active' });
plugin.set('user_prefs', 'User preferences', { verbose: true }, 'high');

// Store data with UI display - shown in the host app's sidebar panel
plugin.set('dashboard', 'Progress dashboard', '## Progress\n- [x] Step 1\n- [ ] Step 2', 'normal', true);

// LLM uses unified store tools: store_set("context", ...), store_get("context", ...), etc.
// Or access directly via plugin API
const state = plugin.get('current_state');  // { step: 2, status: 'active' }

Key Difference from WorkingMemory:

WorkingMemory: External storage + index → requires store_get("memory", key) for values
InContextMemory: Full values in context → instant access, no retrieval needed

UI Display (showInUI): Entries with showInUI: true are displayed in the host application's sidebar panel with full markdown rendering (code blocks, tables, charts, diagrams, etc.). The LLM sets this via store_set("context", key, { ..., showInUI: true }). Users can also pin specific entries to always display them regardless of the agent's setting. See the User Guide for details.

Use cases: Session state, user preferences, counters, flags, small accumulated results, live dashboards.

10. Persistent Instructions

Store agent-level custom instructions that persist across sessions on disk:

import { Agent } from '@everworker/oneringai';

const agent = Agent.create({
  connector: 'openai',
  model: 'gpt-4',
  context: {
    agentId: 'my-assistant',  // Required for storage path
    features: {
      persistentInstructions: true,
    },
  },
});

// LLM uses unified store tools: store_set("instructions", ...), store_delete("instructions", ...), etc.
// Instructions persist to ~/.oneringai/agents/my-assistant/custom_instructions.json

Key Features:

📁 Disk Persistence - Instructions survive process restarts and sessions
🔧 LLM-Modifiable - Agent can update its own instructions during execution
🔄 Auto-Load - Instructions loaded automatically on agent start
🛡️ Never Compacted - Critical instructions always preserved in context

Store Tools (via unified store_* interface):

store_set("instructions", key, { content }) - Add or update a single instruction by key
store_delete("instructions", key) - Remove a single instruction by key
store_list("instructions") - List all instructions with keys and content
store_action("instructions", "clear", { confirm: true }) - Remove all instructions

Use cases: Agent personality/behavior, user preferences, learned rules, tool usage patterns.

11. User Info

Store user-specific preferences and context that are automatically injected into the LLM system message:

import { Agent } from '@everworker/oneringai';

const agent = Agent.create({
  connector: 'openai',
  model: 'gpt-4',
  userId: 'alice',  // Optional — defaults to 'default' user
  context: {
    features: {
      userInfo: true,
    },
  },
});

// LLM uses unified store tools: store_set("user_info", ...), store_get("user_info", ...), etc.
// Data persists to ~/.oneringai/users/alice/user_info.json
// All entries are automatically shown in context — no need to call store_get each turn

Key Features:

📁 Disk Persistence - User info survives process restarts and sessions
🔄 Auto-Inject - Entries rendered as markdown and included in the system message automatically
👥 User-Scoped - Data is per-user, not per-agent — different agents share the same user data
🔧 LLM-Modifiable - Agent can update user info during execution

Store Tools (via unified store_* interface):

store_set("user_info", key, { value, description? }) - Store/update user information
store_get("user_info", key?) - Retrieve one entry or all entries
store_delete("user_info", key) - Remove a specific entry
store_action("user_info", "clear", { confirm: true }) - Clear all entries

TODO Tools (built into the same plugin):

todo_add - Create a TODO (title, description?, people?, dueDate?, tags?)
todo_update - Update a TODO (id, plus any fields to change including status: 'done')
todo_remove - Delete a TODO by id

TODOs are stored alongside user info and rendered in a separate "Current TODOs" checklist in context. The agent proactively suggests creating TODOs when conversation implies action items, reminds about due/overdue items once per day, and auto-cleans completed TODOs after 48 hours.

Use cases: User preferences (theme, language, timezone), user context (role, location), accumulated knowledge about the user, task/TODO tracking with deadlines and people.

12. Direct LLM Access

Bypass all context management for simple, stateless LLM calls:

const agent = Agent.create({ connector: 'openai', model: 'gpt-4' });

// Direct call - no history tracking, no memory, no context preparation
const response = await agent.runDirect('What is 2 + 2?');
console.log(response.output_text);  // "4"

// With options
const response = await agent.runDirect('Summarize this', {
  instructions: 'Be concise',
  temperature: 0.5,
  maxOutputTokens: 100,
});

// Multimodal (text + image)
const response = await agent.runDirect([
  { type: 'message', role: 'user', content: [
    { type: 'input_text', text: 'What is in this image?' },
    { type: 'input_image', image_url: 'https://example.com/image.png' }
  ]}
]);

// Streaming
for await (const event of agent.streamDirect('Tell me a story')) {
  if (event.type === 'output_text_delta') {
    process.stdout.write(event.delta);
  }
}

Comparison:

| Aspect | run() | runDirect() | |--------|-------------------|---------------| | History tracking | ✅ | ❌ | | Memory/Cache | ✅ | ❌ | | Context preparation | ✅ | ❌ | | Agentic loop (tool execution) | ✅ | ❌ | | Overhead | Full context management | Minimal |

Use cases: Quick one-off queries, embeddings-like simplicity, testing, hybrid workflows.

Thinking / Reasoning (Per-Call)

Control reasoning effort per call — vendor-agnostic API that maps to OpenAI's reasoning_effort, Anthropic's budget_tokens, and Google's thinkingBudget:

const agent = Agent.create({ connector: 'anthropic', model: 'claude-sonnet-4-6' });

// Set reasoning at agent level (applies to all calls)
const agent2 = Agent.create({
  connector: 'openai', model: 'o3-mini',
  thinking: { enabled: true, effort: 'medium' },
});

// Override per call via RunOptions
const deep = await agent.run('Prove this theorem', {
  thinking: { enabled: true, budgetTokens: 16384 },
});

const quick = await agent.run('What is 2+2?', {
  thinking: { enabled: true, effort: 'low' },
});

// Streaming with reasoning
for await (const event of agent.stream('Analyze this code', {
  thinking: { enabled: true, effort: 'high' },
})) { /* ... */ }

// Also works with runDirect()
const resp = await agent.runDirect('Quick question', {
  thinking: { enabled: true, effort: 'medium' },
});

RunOptions (for run() / stream()): thinking, temperature, vendorOptions — override agent-level config for a single call.

13. Audio Capabilities

Text-to-Speech and Speech-to-Text with multiple providers:

import { TextToSpeech, SpeechToText } from '@everworker/oneringai';

// === Text-to-Speech ===
const tts = TextToSpeech.create({
  connector: 'openai',
  model: 'tts-1-hd',       // or 'gpt-4o-mini-tts' for instruction steering
  voice: 'nova',
});

// Synthesize to file
await tts.toFile('Hello, world!', './output.mp3');

// Synthesize with options
const audio = await tts.synthesize('Speak slowly', {
  format: 'wav',
  speed: 0.75,
});

// Introspection
const voices = await tts.listVoices();
const models = tts.listAvailableModels();

// === Speech-to-Text ===
const stt = SpeechToText.create({
  connector: 'openai',
  model: 'whisper-1',      // or 'gpt-4o-transcribe'
});

// Transcribe
const result = await stt.transcribeFile('./audio.mp3');
console.log(result.text);

// With timestamps
const detailed = await stt.transcribeWithTimestamps(audioBuffer, 'word');
console.log(detailed.words);  // [{ word, start, end }, ...]

// Translation
const english = await stt.translate(frenchAudio);

Streaming TTS — for real-time voice applications:

// Stream audio chunks as they arrive from the API
for await (const chunk of tts.synthesizeStream('Hello!', { format: 'pcm' })) {
  if (chunk.audio.length > 0) playPCMChunk(chunk.audio);  // 24kHz 16-bit LE mono
  if (chunk.isFinal) break;
}

// VoiceStream wraps agent text streams with interleaved audio events
const voice = VoiceStream.create({
  ttsConnector: 'openai', ttsModel: 'tts-1-hd', voice: 'nova',
});
for await (const event of voice.wrap(agent.stream('Tell me a story'))) { ... }

Available Models:

TTS: OpenAI (tts-1, tts-1-hd, gpt-4o-mini-tts), Google (gemini-tts)
STT: OpenAI (whisper-1, gpt-4o-transcribe), Groq (whisper-large-v3 - 12x cheaper!)

Embeddings (NEW)

Generate text embeddings across multiple vendors with a unified API. Supports Matryoshka Representation Learning (MRL) for flexible output dimensions.

import { Embeddings, Connector, Vendor } from '@everworker/oneringai';

// Setup
Connector.create({
  name: 'openai',
  vendor: Vendor.OpenAI,
  auth: { type: 'api_key', apiKey: process.env.OPENAI_API_KEY! },
});

const embeddings = Embeddings.create({ connector: 'openai' });

// Single text
const result = await embeddings.embed('Hello world');
console.log(result.embeddings[0].length);  // 1536 (default for text-embedding-3-small)

// Batch with custom dimensions (MRL)
const batch = await embeddings.embed(
  ['search query', 'document chunk 1', 'document chunk 2'],
  { dimensions: 512 }
);
console.log(batch.embeddings.length);     // 3
console.log(batch.embeddings[0].length);  // 512

// Local with Ollama (free, no API key)
Connector.create({
  name: 'ollama-local',
  vendor: Vendor.Ollama,
  auth: { type: 'none' },
  baseURL: 'http://localhost:11434/v1',
});

const local = Embeddings.create({ connector: 'ollama-local' });
const localResult = await local.embed('semantic search query');
// Uses qwen3-embedding by default (4096 dims, #1 on MTEB multilingual)

Model introspection and cost estimation:

import {
  getEmbeddingModelInfo,
  getEmbeddingModelsByVendor,
  calculateEmbeddingCost,
  EMBEDDING_MODELS,
  Vendor,
} from '@everworker/oneringai';

// Model details
const info = getEmbeddingModelInfo('text-embedding-3-small');
console.log(info.capabilities.maxDimensions);       // 1536
console.log(info.capabilities.features.matryoshka);  // true (supports MRL)
console.log(info.capabilities.maxTokens);            // 8191

// Cost estimation
const cost = calculateEmbeddingCost('text-embedding-3-small', 1_000_000);
console.log(`$${cost} per 1M tokens`);  // $0.02

// Browse models by vendor
const ollamaModels = getEmbeddingModelsByVendor(Vendor.Ollama);
console.log(ollamaModels.map(m => `${m.name} (${m.capabilities.defaultDimensions}d)`));
// ['qwen3-embedding (4096d)', 'qwen3-embedding:4b (4096d)', 'qwen3-embedding:0.6b (1024d)', ...]

Available Embedding Models:

| Vendor | Model | Dims | MRL | Tokens | Price/1M | |--------|-------|------|-----|--------|----------| | OpenAI | text-embedding-3-small | 1536 | yes | 8191 | $0.02 | | OpenAI | text-embedding-3-large | 3072 | yes | 8191 | $0.13 | | Google | text-embedding-004 | 768 | yes | 2048 | Free | | Mistral | mistral-embed | 1024 | no | 8192 | $0.10 | | Ollama | qwen3-embedding (8B) | 4096 | yes | 8192 | Free (local) | | Ollama | qwen3-embedding:0.6b | 1024 | yes | 8192 | Free (local) | | Ollama | nomic-embed-text | 768 | yes | 8192 | Free (local) |

14. Model Registry

Complete metadata for 23+ models:

import { getModelInfo, calculateCost, LLM_MODELS, Vendor } from '@everworker/oneringai';

// Get model information
const model = getModelInfo('gpt-5.2');
console.log(model.features.input.tokens);  // 400000
console.log(model.features.input.cpm);     // 1.75 (cost per million)

// Calculate costs
const cost = calculateCost('gpt-5.2', 50_000, 2_000);
console.log(`Cost: $${cost}`);  // $0.1155

// With caching
const cachedCost = calculateCost('gpt-5.2', 50_000, 2_000, {
  useCachedInput: true
});
console.log(`Cached: $${cachedCost}`);  // $0.0293 (90% discount)

Available Models:

OpenAI (12): GPT-5.2 series, GPT-5 family, GPT-4.1, GPT-4o, o3-mini, o1
Anthropic (7): Claude 4.5 series, Claude 4.x, Claude 3.7 Sonnet, Claude 3 Haiku
Google (7): Gemini 3, Gemini 2.5
Grok (9): Grok 4.1, Grok 4, Grok Code, Grok 3, Grok 2 Vision

15. Streaming

Real-time responses:

import { StreamHelpers } from '@everworker/oneringai';

for await (const text of StreamHelpers.textOnly(agent.stream('Hello'))) {
  process.stdout.write(text);
}

16. OAuth for External APIs

import { OAuthManager, FileStorage } from '@everworker/oneringai';

const oauth = new OAuthManager({
  flow: 'authorization_code',
  clientId: process.env.GITHUB_CLIENT_ID!,
  clientSecret: process.env.GITHUB_CLIENT_SECRET!,
  authorizationUrl: 'https://github.com/login/oauth/authorize',
  tokenUrl: 'https://github.com/login/oauth/access_token',
  storage: new FileStorage({ directory: './tokens' }),
});

const authUrl = await oauth.startAuthFlow('user123');

17. Developer Tools

File system and shell tools for building coding assistants:

import { developerTools } from '@everworker/oneringai';

const agent = Agent.create({
  connector: 'openai',
  model: 'gpt-4',
  tools: developerTools, // Includes all 7 tools
});

// Agent can now:
// - Read files (read_file)
// - Write files (write_file)
// - Edit files with surgical precision (edit_file)
// - Search files by pattern (glob)
// - Search content with regex (grep)
// - List directories (list_directory)
// - Execute shell commands (bash)

await agent.run('Read package.json and tell me the dependencies');
await agent.run('Find all TODO comments in the src directory');
await agent.run('Run npm test and report any failures');

Available Tools:

read_file - Read file contents with line numbers
write_file - Create/overwrite files
edit_file - Surgical find/replace edits
glob - Find files by pattern (**/*.ts)
grep - Search content with regex
list_directory - List directory contents
bash - Execute shell commands with safety guards

Safety Features:

Blocked dangerous commands (rm -rf /, fork bombs)
Configurable blocked directories (node_modules, .git)
Timeout protection (default 2 min)
Output truncation for large outputs

18. Custom Tool Generation (NEW)

Let agents create their own tools at runtime — draft, test, iterate, save, and reuse. The agent writes JavaScript code, validates it, tests it in the VM sandbox, and persists it for future use. All 6 meta-tools are auto-registered and visible in Everworker Desktop.

import { createCustomToolMetaTools, hydrateCustomTool } from '@everworker/oneringai';

// Give an agent the ability to create tools
const agent = Agent.create({
  connector: 'openai',
  model: 'gpt-4',
  tools: [...createCustomToolMetaTools()],
});

// The agent can now: draft → test → save tools autonomously
await agent.run('Create a tool that fetches weather data from the OpenWeather API');

// Later: load and use a saved tool
import { createFileCustomToolStorage } from '@everworker/oneringai';
const storage = createFileCustomToolStorage();
const definition = await storage.load(undefined, 'fetch_weather'); // undefined = default user
const weatherTool = hydrateCustomTool(definition!);

// Register on any agent
agent.tools.register(weatherTool, { source: 'custom', tags: ['weather', 'api'] });

Meta-Tools: custom_tool_draft (validate), custom_tool_test (execute in sandbox), custom_tool_save (persist), custom_tool_list (search), custom_tool_load (retrieve), custom_tool_delete (remove)

Dynamic Descriptions: Draft and test tools use descriptionFactory to show all available connectors and the full sandbox API — automatically updated when connectors are added or removed.

Pluggable Storage: Default FileCustomToolStorage saves to ~/.oneringai/users/<userId>/custom-tools/ (defaults to ~/.oneringai/users/default/custom-tools/ when no userId). Implement ICustomToolStorage for MongoDB, S3, or any backend.

See the User Guide for the complete workflow, sandbox API reference, and examples.

19. Desktop Automation Tools (NEW)

OS-level desktop automation for building "computer use" agents — screenshot the screen, send to a vision model, receive tool calls (click, type, etc.), execute them, repeat:

import { desktopTools } from '@everworker/oneringai';

const agent = Agent.create({
  connector: 'openai',
  model: 'gpt-4',
  tools: desktopTools, // All 11 desktop tools
});

// Agent can now see and interact with the desktop:
await agent.run('Take a screenshot and describe what you see');
await agent.run('Open Safari and search for "weather forecast"');

Available Tools:

desktop_screenshot - Capture full screen or region (returns image to vision model)
desktop_mouse_move - Move cursor to position
desktop_mouse_click - Click (left/right/middle, single/double/triple)
desktop_mouse_drag - Drag from one position to another
desktop_mouse_scroll - Scroll wheel (vertical and horizontal)
desktop_get_cursor - Get current cursor position
desktop_keyboard_type - Type text
desktop_keyboard_key - Press shortcuts (e.g., ctrl+c, cmd+shift+s, enter)
desktop_get_screen_size - Get screen dimensions and scale factor
desktop_window_list - List visible windows
desktop_window_focus - Bring a window to the foreground

Key Design:

All coordinates are in physical pixel space (same as screenshot pixels) — no manual Retina scaling needed
Screenshots use the __images convention for automatic multimodal handling across all providers (Anthropic, OpenAI, Google)
Requires @nut-tree-fork/nut-js as an optional peer dependency: npm install @nut-tree-fork/nut-js

20. Document Reader

Universal file-to-LLM-content converter. Reads arbitrary document formats and produces clean markdown text with optional image extraction:

import { DocumentReader, mergeTextPieces } from '@everworker/oneringai';

const reader = DocumentReader.create({
  defaults: {
    maxTokens: 50_000,
    extractImages: true,
    imageFilter: { minWidth: 100, minHeight: 100 },
  },
});

// Read from file path, URL, Buffer, or Blob
const result = await reader.read('/path/to/report.pdf');
const result = await reader.read('https://example.com/doc.xlsx');
const result = await reader.read({ type: 'buffer', buffer: myBuffer, filename: 'doc.docx' });

// Get merged markdown text
const markdown = mergeTextPieces(result.pieces);

// Metadata
console.log(result.metadata.format);          // 'pdf'
console.log(result.metadata.estimatedTokens); // 12500
console.log(result.metadata.processingTimeMs); // 234

Automatic Integration — No Code Changes Needed:

read_file tool — Agents calling read_file on a PDF, DOCX, or XLSX get markdown text automatically
web_fetch tool — Documents downloaded from URLs are auto-converted to markdown

Content Bridge for Multimodal Input:

import { readDocumentAsContent } from '@everworker/oneringai';

// Convert document directly to Content[] for LLM input
const content = await readDocumentAsContent('/path/to/slides.pptx', {
  extractImages: true,
  imageDetail: 'auto',
  maxImages: 20,
});

// Use in agent.run() with text + images
await agent.run([
  { type: 'input_text', text: 'Analyze this presentation:' },
  ...content,
]);

Pluggable Architecture:

6 built-in format handlers (Office, Excel, PDF, HTML, Text, Image)
3 default transformers (header, table formatting, truncation)
Custom handlers and transformers via DocumentReader.create({ handlers, ... })
All heavy dependencies lazy-loaded (officeparser, exceljs, unpdf)

Image Filtering:

Configurable min dimensions, min size, max count, pattern exclusions
Automatically removes junk images (logos, icons, tiny backgrounds)
Applied both at extraction time and at content conversion time

See the User Guide for complete API reference and configuration options.

21. Routine Execution (NEW)

Execute multi-step AI workflows where tasks run in dependency order with automatic validation:

import { executeRoutine, createRoutineDefinition } from '@everworker/oneringai';

const routine = createRoutineDefinition({
  name: 'Research Report',
  tasks: [
    {
      name: 'Research',
      description: 'Search for information about quantum computing',
      suggestedTools: ['web_search'],
      validation: {
        completionCriteria: ['At least 3 sources found', 'Key findings stored in memory'],
      },
    },
    {
      name: 'Write Report',
      description: 'Write a report based on research findings',
      dependsOn: ['Research'],
      validation: {
        completionCriteria: ['Report has introduction and conclusion', 'Sources are cited'],
      },
    },
  ],
});

const execution = await executeRoutine({
  definition: routine,
  connector: 'openai',
  model: 'gpt-4',
  tools: [...searchTools],
  onTaskComplete: (task, exec) => console.log(`[${exec.progress}%] ${task.name} done`),
});

console.log(execution.status); // 'completed' | 'failed'

Key Features:

Task Dependencies - DAG-based ordering via dependsOn
Memory Bridging - In-context memory (store_set("context", ...)) + working memory (store_set("memory", ...)) persist across tasks while conversation is cleared
LLM Validation - Self-reflection against completion criteria with configurable score thresholds
Retry Logic - Configurable maxAttempts per task with automatic retry on validation failure
Smart Error Classification - Permanent errors (auth, config, model-not-found) skip retry; transient errors retry normally
Control Flow - map, fold, and until flows with optional per-iteration timeout (iterationTimeoutMs)
Progress Tracking - Real-time callbacks and progress percentage
Failure Modes - fail-fast (default) or continue for independent tasks
Custom Prompts - Override system, task, or validation prompts
ROUTINE_KEYS export - Well-known ICM/WM key constants for custom integrations

Control Flow with Timeout:

const routine = createRoutineDefinition({
  name: 'Process Batch',
  tasks: [{
    name: 'Process Each',
    description: 'Process each item',
    controlFlow: {
      type: 'map',
      source: '__items',
      resultKey: '__results',
      iterationTimeoutMs: 60000, // 1 min per item
      tasks: [{ name: 'Process', description: 'Handle the current item' }],
    },
  }],
});

Execution Recording: Persist full execution history (steps, task snapshots, progress) with createExecutionRecorder(). Replaces ~140 lines of manual hook wiring with a single factory call:

import {
  createRoutineExecutionRecord, createExecutionRecorder,
  type IRoutineExecutionStorage,
} from '@everworker/oneringai';

const record = createRoutineExecutionRecord(definition, 'openai', 'gpt-4');
const execId = await storage.insert(userId, record);
const recorder = createExecutionRecorder({ storage, executionId: execId });

executeRoutine({
  definition, agent, inputs,
  hooks: recorder.hooks,
  onTaskStarted: recorder.onTaskStarted,
  onTaskComplete: recorder.onTaskComplete,
  onTaskFailed: recorder.onTaskFailed,
  onTaskValidation: recorder.onTaskValidation,
})
  .then(exec => recorder.finalize(exec))
  .catch(err => recorder.finalize(null, err));

Scheduling & Triggers: Run routines on a timer or from external events:

import { SimpleScheduler, EventEmitterTrigger } from '@everworker/oneringai';

// Schedule: run every hour
const scheduler = new SimpleScheduler();
scheduler.schedule('hourly-report', { intervalMs: 3600000 }, () => executeRoutine({ ... }));

// Event trigger: run from webhook
const trigger = new EventEmitterTrigger();
trigger.on('new-order', (payload) => executeRoutine({ ... }));
// In your webhook handler:
trigger.emit('new-order', { orderId: '123' });

Routine Persistence: Save and load routine definitions with FileRoutineDefinitionStorage (or implement IRoutineDefinitionStorage for custom backends). Per-user isolation via optional userId. Integrated into StorageRegistry as routineDefinitions.

import { createFileRoutineDefinitionStorage, createRoutineDefinition } from '@everworker/oneringai';

const storage = createFileRoutineDefinitionStorage();
const routine = createRoutineDefinition({ name: 'Daily Report', description: '...', tasks: [...] });
await storage.save(undefined, routine);  // undefined = default user
const loaded = await storage.load(undefined, routine.id);
const all = await storage.list(undefined, { tags: ['daily'] });

See the User Guide for the complete API reference, architecture details, and examples.

22. External API Integration

Connect your AI agents to 35+ external services with enterprise-grade resilience:

import { Connector, ConnectorTools, Services, Agent } from '@everworker/oneringai';

// Create a connector for an external service
Connector.create({
  name: 'github',
  serviceType: Services.Github,
  auth: { type: 'api_key', apiKey: process.env.GITHUB_TOKEN! },
  baseURL: 'https://api.github.com',

  // Enterprise resilience features
  timeout: 30000,
  retry: { maxRetries: 3, baseDelayMs: 1000 },
  circuitBreaker: { enabled: true, failureThreshold: 5 },
});

// Generate tools from the connector
// GitHub connectors get 7 dedicated tools + generic API automatically:
// search_files, search_code, read_file, get_pr, pr_files, pr_comments, create_pr
const tools = ConnectorTools.for('github');

// Use with an agent — userId flows to all tools automatically
const agent = Agent.create({
  connector: 'openai',
  model: 'gpt-4',
  userId: 'user-123',  // All tool API calls use this user's OAuth tokens
  tools: tools,
});

await agent.run('Find all TypeScript files in src/ and show me the entry point');
await agent.run('Show me PR #42 and summarize the review comments');

Supported Services (35+):

Communication: Slack, Discord, Microsoft Teams, Twilio
Development: GitHub (7 built-in tools), GitLab, Jira, Linear, Bitbucket
Microsoft: Microsoft Graph (6 built-in tools) — email, calendar, meetings, Teams transcripts
Productivity: Notion, Asana, Monday, Airtable, Trello
CRM: Salesforce, HubSpot, Zendesk, Intercom
Payments: Stripe, PayPal, Square
Cloud: AWS, Azure, GCP, DigitalOcean
And more...

Enterprise Features:

🔄 Automatic retry with exponential backoff
⚡ Circuit breaker for failing services
⏱️ Configurable timeout
📊 Metrics tracking (requests, latency, success rate)
🔐 Protected auth headers (cannot be overridden)

// Direct fetch with connector
const connector = Connector.get('github');
const data = await connector.fetchJSON('/repos/owner/repo/issues');

// Metrics
const metrics = connector.getMetrics();
console.log(`Success rate: ${metrics.successCount / metrics.requestCount * 100}%`);

Scoped Connector Registry (NEW)

Limit connector visibility by user, group, or tenant in multi-user systems:

import { Connector, ScopedConnectorRegistry } from '@everworker/oneringai';
import type { IConnectorAccessPolicy } from '@everworker/oneringai';

// Define an access policy
const policy: IConnectorAccessPolicy = {
  canAccess: (connector, context) => {
    const tags = connector.config.tags as string[] | undefined;
    return !!tags && tags.includes(context.tenantId as string);
  },
};

// Set the global policy
Connector.setAccessPolicy(policy);

// Create a scoped view for a specific tenant
const registry = Connector.scoped({ tenantId: 'acme-corp' });

//

Published

Vulnerabilities

Links

Maintainers

Keywords

Readme

@everworker/oneringai

Table of Contents

Documentation

Tutorial / Architecture Series

EVERWORKER DESKTOP APP

YOUetal

Features

Quick Start

Installation

Basic Usage

With Tools

Vision

Audio (NEW)

Image Generation (NEW)

Video Generation (NEW)

Embeddings (NEW)

Document Reader (NEW)

Web Search

Web Scraping

Supported Providers

Key Features

1. Agent with Plugins

2. Dynamic Tool Management (NEW)

3. Tool Execution Plugins (NEW)

4. Tool Permissions (NEW)

Zero-Config (Backward Compatible)

Per-User Permission Rules

Built-in Policies

Approval Dialog Integration

Tool Self-Declaration

5. Session Persistence

Storage Registry

6. Working Memory

7. Research with Search Tools

8. Context Management

Feature Configuration

9. InContextMemory

10. Persistent Instructions

11. User Info

12. Direct LLM Access

Thinking / Reasoning (Per-Call)

13. Audio Capabilities

Embeddings (NEW)

14. Model Registry

15. Streaming

16. OAuth for External APIs

17. Developer Tools

18. Custom Tool Generation (NEW)

19. Desktop Automation Tools (NEW)

20. Document Reader

21. Routine Execution (NEW)

22. External API Integration

Scoped Connector Registry (NEW)